explain xkcd - User contributions [en]

Talk:1146: Honest

2012-12-12T15:17:59Z

50.0.38.245:

Ya can't explain this one![[Special:Contributions/176.61.46.230|176.61.46.230]] 11:06, 12 December 2012 (UTC)
:No, other work is getting in the way. Someone else'll do it. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>[talk]</tt>]] 11:15, 12 December 2012 (UTC)
:The honesty of this comic makes it pretty self-explanatory. I like it. [[Special:Contributions/76.122.5.96|76.122.5.96]] 12:21, 12 December 2012 (UTC)

That 1-line explanation by anon 69.143.0.147 is ''brilliant''.

1145: Sky Color

2012-12-10T08:08:46Z

50.0.38.245: /* Explanation */ Single typo fix

{{comic
| number = 1145
| date = December 10, 2012
| title = Sky Color
| image = sky color.png
| titletext = Feynman recounted another good one upperclassmen would use on freshmen physics students: When you look at words in a mirror, how come they're reversed left to right but not top to bottom? What's special about the horizontal axis?
}}

==Explanation==
{{W|Rayleigh scattering}} is the phenomenon that explains the color of the sky, where light of shorter wavelengths gets scattered by the air by the inverse of the fourth power of the wavelength as given in the comic. In the {{w|visibile spectrum}}, blue light has a wavelength of 450–495 nm while violet has a shorter wavelength of 380–450 nm. Violet light does indeed get scattered more than blue light, however the lower portion of the spectrum for sunlight consists of blue light and eyes are much more sensitive to blue light than violet light. This leaves the impression of a blue sky.

The title text refers to a {{w|mirror image}}. A mirror image is a virtual image produced by the reflection of light on a mirror. It does not have an inherent direction of inversion, in terms of horizontal vs. vertical (perhaps one could say it is inverted in depth). The "horizontal" aspect that we perceive is due to the fact that we normally swivel horizontally (about a vertical axis) to look behind us. The image of the world behind us has left and right switched, but not top and bottom. If we somehow normally swiveled vertically about a horizontal axis to look behind, we'd be accustomed to seeing up and down switched, but not left and right, in the view behind. We would then categorize the image in the mirror as inverted vertically, and perhaps wonder why it's not inverted horrizontally.

==Transcript==
:[Girl and her mother, Megan. Megan is at a desk and facing the girl.]
:Girl: Mommy, why is the sky blue?
:Megan: Rayleigh scattering! Short wavelengths get scattered ''way'' more (proportional to 1/''λ''4). Blue light dominates because it's so short.
:Girl: Oh.
:Girl: So why ''isn't'' the sky violet?
:Megan: Well, because, uh... ...hmm.

{{comic discussion}}
[[Category:Comics featuring Megan]]
[[Category:Physics]]
[[Category:My Hobby]]

1145: Sky Color

2012-12-10T08:07:10Z

50.0.38.245:

{{comic
| number = 1145
| date = December 10, 2012
| title = Sky Color
| image = sky color.png
| titletext = Feynman recounted another good one upperclassmen would use on freshmen physics students: When you look at words in a mirror, how come they're reversed left to right but not top to bottom? What's special about the horizontal axis?
}}

==Explanation==
{{W|Rayleigh scattering}} is the phenomenon that explains the color of the sky, where light of shorter wavelengths gets scattered by the air by the inverse of the fourth power of the wavelength as given in the comic. In the {{w|visibile spectrum}}, blue light has a wavelength of 450–495 nm while violet has a shorter wavelength of 380–450 nm. Violet light does indeed get scattered more than blue light, however the lower portion of the spectrum for sunlight consists of blue light and eyes are much more sensitive to blue light than violet light. This leaves the impression of a blue sky.

The title text refer to a {{w|mirror image}}. A mirror image is a virtual image produced by the reflection of light on a mirror. It does not have an inherent direction of inversion, in terms of horizontal vs. vertical (perhaps one could say it is inverted in depth). The "horizontal" aspect that we perceive is due to the fact that we normally swivel horizontally (about a vertical axis) to look behind us. The image of the world behind us has left and right switched, but not top and bottom. If we somehow normally swiveled vertically about a horizontal axis to look behind, we'd be accustomed to seeing up and down switched, but not left and right, in the view behind. We would then categorize the image in the mirror as inverted vertically, and perhaps wonder why it's not inverted horrizontally.

==Transcript==
:[Girl and her mother, Megan. Megan is at a desk and facing the girl.]
:Girl: Mommy, why is the sky blue?
:Megan: Rayleigh scattering! Short wavelengths get scattered ''way'' more (proportional to 1/''λ''4). Blue light dominates because it's so short.
:Girl: Oh.
:Girl: So why ''isn't'' the sky violet?
:Megan: Well, because, uh... ...hmm.

{{comic discussion}}
[[Category:Comics featuring Megan]]
[[Category:Physics]]
[[Category:My Hobby]]

Talk:Main Page

2012-11-28T15:46:41Z

50.0.38.245: /* Updating the Rules */ forgot to sign

{{notice|This page is for discussion of the [[Main Page]] itself. Other issues probably belong at the [[Explain XKCD:Community portal]].}}

As a new user, I think the first page is very important. So I thought why not begin a discussion here what to have on the first page every user visits.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT) Re-signed here - b/c I broke the comment in two when I added the "List of comics" header. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 23:01, 2 August 2012 (EDT)

==List of comics==
I was thinking of having a quick link to the list of comics that is explained. Right know, it took me a while to even see any of them. Eventually I found the "List All Pages" (found it in Special pages) where I could find the comics that have been explained. What do you think?
:A category tag will do that for you automatically. Having a list of comics indexed by its number would be a little different.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT)
::Sounds like a great list - I ''think'' it'd have to be manually maintained until/unless we get someone who knows how to make a bot update it. Categories will be useful, but they only work if someone added the category to the page in the first place. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:21, 1 August 2012 (EDT)
:::A (somewhat) related question - should [[:Category:Comics]] be sorted alphabetically or by comic number? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:43, 1 August 2012 (EDT)
::::I think [[:Category:Comics]] should be sorted by comic number. If you are looking for a specific comic, you will use the search field. Is there a way to make that happen? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::::They are two different functions. For the former, instead of adding <nowiki>[[Category:Comics]]</nowiki>, add, say, <nowiki>[[Category:Comics|1]]</nowiki>. For the second, we can create redirects. Normally, I'd say just make sure the search term was in the article text, but since numbers are going to be use for other purposes than just comic titles, it may be better to create [[1]] and [[Comic 1]] as redirects to the relevant articles right off the bat. --08:24, 1 August 2012 (EDT)
::::::We could also have a comic-list template on the Main Page, I suppose, or perhaps two - one for number and one for name? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:54, 1 August 2012 (EDT)
:::::::Here's what I was thinking of for that: {{tl|Comics navbox}} Thoughts? ''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]]
:(outdent) It's ugly, but a sortable wikitable [[User:SurturZ/sandbox|(click here for example)]] could be used as a checklist to see what has been uploaded and what hasn't. What's the project namespace here, anyway (analogue of "WP:")? --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:04, 3 August 2012 (EDT)
:OK, I've found a way to get all the titles of the comics, so I was confident enough to create <big>[[Explain XKCD:Checklist]]</big> which can be used to fill in the gaps. --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:41, 3 August 2012 (EDT)
::I'm liking the checklist! That should do quite nicely as a "tool for editors". (I'm linking to it at the Community Portal). We still need the "template for readers." Did you think {{tl|Comics navbox}} was on the right track or should we do something else for that? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:09, 3 August 2012 (EDT)
::Better idea - I'm throwing it directly onto the Main Page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:10, 3 August 2012 (EDT)

==Admin list==
You can find a system-accurate list of admins [{{canonicalurl:Special:ListUsers|group=sysop}} here], so that might good to share, along with the manual list. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:13, 1 August 2012 (EDT)
:Added to page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:10, 1 August 2012 (EDT)
::That's exactly what I wanted, but couldn't find the auto page for it. I knew it was somewhere. I don't see any reason to keep the link to the manual page. Do you? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::Not unless you want it. I'll remove it. Should I add the similar link for 'crats or is that unnecessary at this point? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:25, 1 August 2012 (EDT)
::::To be honest, I have no idea what the Burecrats role does. Might be unnecessary now but helpful in the future? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 11:16, 1 August 2012 (EDT)
:::::Bureaucrats can turn other users into administrators (or indeed, other bureaucrats). That privilege isn't available to ordinary administrators. I'd keep it to yourself for the time being. :-) --[[User:Yirba|Yirba]] ([[User talk:Yirba|talk]]) 17:39, 1 August 2012 (EDT)
::::::You can actually see a technical list of which rights each group confers at [[Special:ListGroupRights]]. As the wiki grows, you might want to spin off a few, such as the ability to grant rollbacker and autopatrolled, to admins as some other wikis have. But for the time being, at least, there's really no reason for the wiki to have more than one 'crat. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:07, 2 August 2012 (EDT)

== Community portal ==

I've created the [[Explain XKCD:Community portal]] as a tools/help page. If that's not what you want, feel free to change/move/whatever it, but I thought it'd be nice to save this page for discussion of the Main Page and discuss the wiki as a whole/ask for help there. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:36, 1 August 2012 (EDT)

== Direct link to latest comic ==

There should be a direct link to the latest comic at the top of the Main page. A nice thing about going to explainxkcd.com was that the latest comic is right there at the top. For those changing their default link to the wiki, there should be an easy "Latest Comic" link that quickly takes them there. I'm sure some folks actually skip xkcd.com and come directly here instead to read the latest offering from Randall. They shouldn't have to search for it.
[[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:59, 1 August 2012 (EDT)

: Maybe the page [[latest]] should redirect to the most recent comic? Could that be taken care of by some sort of script/template so it doesn't have to be manually updated? Should each explination page also have "next", "previous", "random", "first" and "latest" links, possibly also generated automatically via scripts/templates? Additionally, shouldn't the number page be the canonical one? It seems like [[Internal monologue]] should redirect to [[1089]] rather than the other way around - certainly it would make a bunch of scripting types of things a lot easier. [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:02, 1 August 2012 (EDT)
:::If you wanted, we could even use wiki-magic to show the title of the page as the Comic name, but the URL as the number - in order to parallel the actual XKCD website. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:09, 2 August 2012 (EDT)
:: Shouldn't there be a way to programmatically find the comic with the highest number that has a page with content? That would work as long as no one puts future comic pages up. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 20:25, 1 August 2012 (EDT)
:::It's all sounding like folks are over-complicating something quite easy. All I'm suggesting is a prominent link to http://www.xkcd.com/. No need, I think, to list which number the latest is, or include the next/last/random buttons, etc. [[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:41, 3 August 2012 (EDT)
::::Oh. We've got that, now, in the sidebar - labeled as "XKCD." I do think that having an internal link to the latest (explained) comic would be a great thing, though. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 16:36, 4 August 2012 (EDT)

You can transclude the latest comic on the main page like this: <nowiki>{{:pagename}} e.g. {{:Internal_monologue}} </nowiki>--[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 00:25, 2 August 2012 (EDT)
: I've started with just a manual link to the latest comic. Ideally it will be automatic, but a manual link will work for now as I've had quite a few people ask for it. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 21:09, 1 August 2012 (EDT)

Transclusion of the latest comic is great. Someone with the right permissions should add (for instance on the top-right corner of the grey transclusion area) a link to edit the corresponding wiki page, so that people seeing something they could add would feel invited to do so (wiki style). In my opinion this would be a good way to improve the quality of the user-generated explanations.
Also, all the "XKCD"s in the "New here?" section should be converted to the lowercase "xkcd"...
[[User:Cos|Cos]] ([[User talk:Cos|talk]]) 14:00, 6 August 2012 (UTC)
:Good points. I've done both. --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 15:48, 6 August 2012 (UTC)

Call me dumb, but... You've got a link called "prev" that goes to the explaination for the previous comic. Then a link called "comic #42" but that goes to xkcd. And then a smaller, less prominent link called "go to this comic" that doesn't go to the comic but to its explaination. Anyone else think that's a little back-to-front? [[User:Zootle|Zootle]] ([[User talk:Zootle|talk]]) 17:18, 31 August 2012 (UTC)
:OK, you're dumb :-). The standard template for an explanation page includes the header with "Prev", "Comic # (date)", and "Next" links. If we don't have explanation pages for the previous or next comic, we don't show the respective link. I hadn't noticed that the "Comic # (date)" bit was a link to the xkcd site before, but in context it makes sense to me. Including a link to the Explain page for the comic who's explain page you are already looking at doesn't make sense.
:The explanation page for the latest comic is "transcluded" in the main page pretty much as-is, so we get the header, the comic, the explanation, etc. We don't get the discussion, which is visible at the bottom of the Explain page. Because there is never an explanation for a comic that hasn't been released yet, there is never a "Next" link on the main page's transcluded header. So you get "Prev" and "Comic" links. The "Go to this comic" link is added by the main page above the transcluded explain page.
:I can see how the "Go to this comic" link might be poorly worded especially as it's placement seems to be within the explanation it's linking to. [[User:Blaisepascal|Blaisepascal]] ([[User talk:Blaisepascal|talk]]) 18:16, 31 August 2012 (UTC)
::Rather than "Go to this comic" maybe it could be "Go to full explanation" ? Something else? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:38, 5 September 2012 (UTC)
::There was [http://www.explainxkcd.com/wiki/index.php?title=explain_xkcd:Community_portal/Admin_requests#.22Edit_this_explanation.22_link_on_main_page a discussion at one point] about a wittier/more descriptive link - but no one came up with anything. I do like "Go to Full Explanation" better, for what it's worth. --[[User:DanB|DanB]] ([[User talk:DanB|talk]]) 15:31, 5 September 2012 (UTC)
:::My problem with that suggestion is that it implies that the main page explanation is not full. As of right now, the full explanation is transcluded on the main page. There's nothing more to see by clicking that link (explanation wise) Perhaps "Go to full explanation page" but that doesn't quite sound right to me... [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 15:42, 7 September 2012 (UTC)
::::How about "Go to this Comic Explanation Page"? One nice thing about the specific page rather than the [[Main_Page]] transcoding is that it nicely includes the discussion as well. I have a bookmark to the [[Main_Page]] that I look at every day, but I want to easily read the discussions, not only the explanation. Humm, maybe we could have a page [[most recent comic]] that automagically redirects to the most recent comic? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 12:42, 8 September 2012 (UTC)
:::::I tried to get [[most recent comic]] to redirect to LATESTCOMIC, but can't get the syntax working - it is possible? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:03, 8 September 2012 (UTC)
::::::Apparently it isn't. I would have tried <code><nowiki>#REDIRECT [[{{LATESTCOMIC}}]]</nowiki></code> like you did, but since that doesn't work, I'll delete the page for now. --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 16:38, 20 November 2012 (UTC)

== Discussion of latest comic ==
Perhaps include the discussions of the latest comic here? I almost missed there was a discussion field a few times because I would only read about the latest comic on the main page. [[User:Carewolf|Carewolf]] ([[User talk:Carewolf|talk]]) 14:54, 22 September 2012 (UTC)

This comics's explanation is complete bollocks, I think. Of course it is NOT a "fact that such a room exists". This comics parodies trope often used in cop movies - an elderly cop goes to work for the last time before his retirement, packs things, plans fishing the next day ... only to be called to one more case (possibly with a new, young and brash partner). And despites his efforts not to screw anything and stay clear of danger, he is either mortally wounded or screws big time and is degraded. So much clichè, that if someone says "It's my last day or service", you might be sure one of the two options above happens. See http://tvtropes.org/pmwiki/pmwiki.php/Main/Retirony [[User:edheldil|Edheldil]] 10:17, 26 September 2012 (UTC)

== The comic explanation count is wrong ==

The adjustment is currently 3, but there are now 6 subcategories and one list making the current correct adjustment 7.
If the wiki was upgraded to version 1.20, a form exists to automatically exclude subcategories.
--[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 09:56, 8 October 2012 (UTC)

:Looks like another week of the wiki going down then.
:But seriously, I've been noticing this too. Didn't know what was causing it, but it's going to have to be fixed sometime.[[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 10:25, 8 October 2012 (UTC)

::The text reads <pre><nowiki>We already have [[:Category:Comics|'''{{#expr:{{PAGESINCAT:Comics}}-3}}''' comic explanations]]!</nowiki></pre> The -3 is to account for the subcategories and non-explanation pages in the category. There apparently used to be three such pages, and now there are seven. I would fix this myself, but the page is protected. If the wiki where upgraded to version 1.20, the categories could be explicitly excluded, but the [[List of all comics]] would still be in the category. (Note that the -3 actually appears twice.) --[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 05:03, 11 October 2012 (UTC)

:::Mediawiki 1.20 fixes this issue, although it'd be nice if this could be fixed in the meantime via the hack reccommended by divad. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

:Looks like Waldir updated the "Comic Correction Count" to "10" (as of 20 November 2012):
<nowiki> We already have [[:Category:Comics|'''{{#expr:{{PAGESINCAT:Comics}}-10}}''' comic explanations]]!</big>
Note: the -10 in the calculation above is to discount subcategories (there are 7 of them as of 20 November 2012),
non-comic pages (2 as of same date: [[List of all comics]] and [[Exoplanet]])
and the comic 404, which was deliberately not posted. Thus 7 + 2 + 1 = 10
(But there are still {{#expr:{{LATESTCOMIC}}-({{PAGESINCAT:Comics}}-10)}} to go. Come and [[List of all comics|add yours]]!)</nowiki>
:Could we possibly make this more dynamic by creating a "IGNORE_IN_COUNT" category or something? and then using something like: <nowiki>{#expr:{{PAGESINCAT:Comics}}-{{PAGESINCAT:IGNORE_IN_COUNT}}}</nowiki>? Then any additional entries to the "Comics" category (that are 'special' entries) could just have the special category added and no main page editing would be necessary? --[[User:Bpothier|B. P.]] ([[User talk:Bpothier|talk]]) 07:50, 22 November 2012 (UTC)

==Make Jeff stop apologizing==
The apology for server downtime has been around for a while now. Can we take it down? [[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 04:41, 11 October 2012 (UTC)

== Spambots ==

I think someone should install [http://www.mediawiki.org/wiki/Extension:AbuseFilter AbuseFilter]. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 10:09, 13 October 2012 (UTC)

== Purge ==

We should regularly purge the server's cache for the main page using http://www.explainxkcd.com/wiki/index.php?title=Main_Page&action=purge to keep the explanation up to date. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 02:28, 3 November 2012 (UTC)

== Updating the Rules ==

I've been having a lovely discussion with someone who apparently thought the "edit anything you want" rule applied to the Talk pages. As we don't have any codified rules for ''here'' and can only point to "well the canonical way this is done on Wikipedia is..." I think that there are a few things we need to put into the list of Rules on the front page, and then have a link to a more in-depth talk about why the rules exist and what-not.

Specifically, I'm talking about writing "Feel free to edit any page on the wiki to be better. But, treat talk pages like you would blog comments: comments by other people ''cannot be changed by you'', you can only respond to them." as a new rule to be plastered on the front page, as there seems to be an increasing number social neophytes that seem to think that editing words that are attributed as being said by another person is perfectly legitimate and non-controversial.

Shall we discuss? [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:25, 15 November 2012 (UTC)

:We could add the etiquette rules as an addendum to the signature reminder at the top of the page. Just an extra note below the alert box asking people to not edit other people's comments. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

::It really should be right down with the "edited mercilessly" description, because this is an exception to that statement. Shouldn't have two sets of contradictory instructions in different places. When I made my improper edit, I had a semi-conscious moment of doubt about whether changing the other guy's comment was ok, even though this is a wiki (and even though it wasn't really clear to me that this "discussion" box held something totally separate from the page content), but that statement at the bottom put all such doubts to rest. I read it multiple times to be sure. But I did not notice that line at the top about the four tildes until ''much'' later. It's somewhat lost, visually, in the header line, when you're not looking directly at it.[[Special:Contributions/50.0.38.245|50.0.38.245]] 18:32, 18 November 2012 (UTC)

:::There's discussion to replace that message with a more noticeable alert box. The message at the bottom of the page appears for all pages, including talk pages, so a talk-page specific message there would not entirely fit. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 00:18, 19 November 2012 (UTC)

::::If that text at the bottom is in fact alterable, it should be written to take every case into account. It's an extremely poor user interface that has instructions appearing on a page stating rules that are the exact opposite of reality. And note that the altert box on the top looks a lot like a banner add, when you don't focus on it and read it. People will tend to habitually filter out anything written there from their perception. Also, it can easily be scrolled off the top of the screen when the discussion starts to get long, and they have a preview displayed.
::::So I think after the "...then do not submit it here.", it should add, "'''Exception''': others' comments in Discussion pages are not to be altered. See full rules at <<link to appropriate wikipedia page>>."[[Special:Contributions/50.0.38.245|50.0.38.245]] 15:46, 28 November 2012 (UTC)

== Update after changes ==

The front page explanation hasn't been updated at all day to match changes in the explanation on the comic's page. This is a major problem i think, as it is the front page explanation people visitors will most often read. --[[User:St.nerol|St.nerol]] ([[User talk:St.nerol|talk]]) 20:43, 26 November 2012 (UTC)
: It might be a caching issue. Appending <code>&action=purge</code> to the URL will probably fix it. Can you confirm it looks good to you now? --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 00:29, 27 November 2012 (UTC)
::Yep, now it updates instantly! Well done, whatever you did! :) --[[User:St.nerol|St.nerol]] ([[User talk:St.nerol|talk]]) 16:24, 27 November 2012 (UTC)

Talk:Main Page

2012-11-28T15:45:53Z

50.0.38.245: /* Updating the Rules */

{{notice|This page is for discussion of the [[Main Page]] itself. Other issues probably belong at the [[Explain XKCD:Community portal]].}}

As a new user, I think the first page is very important. So I thought why not begin a discussion here what to have on the first page every user visits.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT) Re-signed here - b/c I broke the comment in two when I added the "List of comics" header. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 23:01, 2 August 2012 (EDT)

==List of comics==
I was thinking of having a quick link to the list of comics that is explained. Right know, it took me a while to even see any of them. Eventually I found the "List All Pages" (found it in Special pages) where I could find the comics that have been explained. What do you think?
:A category tag will do that for you automatically. Having a list of comics indexed by its number would be a little different.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT)
::Sounds like a great list - I ''think'' it'd have to be manually maintained until/unless we get someone who knows how to make a bot update it. Categories will be useful, but they only work if someone added the category to the page in the first place. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:21, 1 August 2012 (EDT)
:::A (somewhat) related question - should [[:Category:Comics]] be sorted alphabetically or by comic number? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:43, 1 August 2012 (EDT)
::::I think [[:Category:Comics]] should be sorted by comic number. If you are looking for a specific comic, you will use the search field. Is there a way to make that happen? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::::They are two different functions. For the former, instead of adding <nowiki>[[Category:Comics]]</nowiki>, add, say, <nowiki>[[Category:Comics|1]]</nowiki>. For the second, we can create redirects. Normally, I'd say just make sure the search term was in the article text, but since numbers are going to be use for other purposes than just comic titles, it may be better to create [[1]] and [[Comic 1]] as redirects to the relevant articles right off the bat. --08:24, 1 August 2012 (EDT)
::::::We could also have a comic-list template on the Main Page, I suppose, or perhaps two - one for number and one for name? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:54, 1 August 2012 (EDT)
:::::::Here's what I was thinking of for that: {{tl|Comics navbox}} Thoughts? ''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]]
:(outdent) It's ugly, but a sortable wikitable [[User:SurturZ/sandbox|(click here for example)]] could be used as a checklist to see what has been uploaded and what hasn't. What's the project namespace here, anyway (analogue of "WP:")? --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:04, 3 August 2012 (EDT)
:OK, I've found a way to get all the titles of the comics, so I was confident enough to create <big>[[Explain XKCD:Checklist]]</big> which can be used to fill in the gaps. --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:41, 3 August 2012 (EDT)
::I'm liking the checklist! That should do quite nicely as a "tool for editors". (I'm linking to it at the Community Portal). We still need the "template for readers." Did you think {{tl|Comics navbox}} was on the right track or should we do something else for that? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:09, 3 August 2012 (EDT)
::Better idea - I'm throwing it directly onto the Main Page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:10, 3 August 2012 (EDT)

==Admin list==
You can find a system-accurate list of admins [{{canonicalurl:Special:ListUsers|group=sysop}} here], so that might good to share, along with the manual list. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:13, 1 August 2012 (EDT)
:Added to page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:10, 1 August 2012 (EDT)
::That's exactly what I wanted, but couldn't find the auto page for it. I knew it was somewhere. I don't see any reason to keep the link to the manual page. Do you? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::Not unless you want it. I'll remove it. Should I add the similar link for 'crats or is that unnecessary at this point? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:25, 1 August 2012 (EDT)
::::To be honest, I have no idea what the Burecrats role does. Might be unnecessary now but helpful in the future? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 11:16, 1 August 2012 (EDT)
:::::Bureaucrats can turn other users into administrators (or indeed, other bureaucrats). That privilege isn't available to ordinary administrators. I'd keep it to yourself for the time being. :-) --[[User:Yirba|Yirba]] ([[User talk:Yirba|talk]]) 17:39, 1 August 2012 (EDT)
::::::You can actually see a technical list of which rights each group confers at [[Special:ListGroupRights]]. As the wiki grows, you might want to spin off a few, such as the ability to grant rollbacker and autopatrolled, to admins as some other wikis have. But for the time being, at least, there's really no reason for the wiki to have more than one 'crat. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:07, 2 August 2012 (EDT)

== Community portal ==

I've created the [[Explain XKCD:Community portal]] as a tools/help page. If that's not what you want, feel free to change/move/whatever it, but I thought it'd be nice to save this page for discussion of the Main Page and discuss the wiki as a whole/ask for help there. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:36, 1 August 2012 (EDT)

== Direct link to latest comic ==

There should be a direct link to the latest comic at the top of the Main page. A nice thing about going to explainxkcd.com was that the latest comic is right there at the top. For those changing their default link to the wiki, there should be an easy "Latest Comic" link that quickly takes them there. I'm sure some folks actually skip xkcd.com and come directly here instead to read the latest offering from Randall. They shouldn't have to search for it.
[[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:59, 1 August 2012 (EDT)

: Maybe the page [[latest]] should redirect to the most recent comic? Could that be taken care of by some sort of script/template so it doesn't have to be manually updated? Should each explination page also have "next", "previous", "random", "first" and "latest" links, possibly also generated automatically via scripts/templates? Additionally, shouldn't the number page be the canonical one? It seems like [[Internal monologue]] should redirect to [[1089]] rather than the other way around - certainly it would make a bunch of scripting types of things a lot easier. [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:02, 1 August 2012 (EDT)
:::If you wanted, we could even use wiki-magic to show the title of the page as the Comic name, but the URL as the number - in order to parallel the actual XKCD website. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:09, 2 August 2012 (EDT)
:: Shouldn't there be a way to programmatically find the comic with the highest number that has a page with content? That would work as long as no one puts future comic pages up. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 20:25, 1 August 2012 (EDT)
:::It's all sounding like folks are over-complicating something quite easy. All I'm suggesting is a prominent link to http://www.xkcd.com/. No need, I think, to list which number the latest is, or include the next/last/random buttons, etc. [[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:41, 3 August 2012 (EDT)
::::Oh. We've got that, now, in the sidebar - labeled as "XKCD." I do think that having an internal link to the latest (explained) comic would be a great thing, though. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 16:36, 4 August 2012 (EDT)

You can transclude the latest comic on the main page like this: <nowiki>{{:pagename}} e.g. {{:Internal_monologue}} </nowiki>--[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 00:25, 2 August 2012 (EDT)
: I've started with just a manual link to the latest comic. Ideally it will be automatic, but a manual link will work for now as I've had quite a few people ask for it. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 21:09, 1 August 2012 (EDT)

Transclusion of the latest comic is great. Someone with the right permissions should add (for instance on the top-right corner of the grey transclusion area) a link to edit the corresponding wiki page, so that people seeing something they could add would feel invited to do so (wiki style). In my opinion this would be a good way to improve the quality of the user-generated explanations.
Also, all the "XKCD"s in the "New here?" section should be converted to the lowercase "xkcd"...
[[User:Cos|Cos]] ([[User talk:Cos|talk]]) 14:00, 6 August 2012 (UTC)
:Good points. I've done both. --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 15:48, 6 August 2012 (UTC)

Call me dumb, but... You've got a link called "prev" that goes to the explaination for the previous comic. Then a link called "comic #42" but that goes to xkcd. And then a smaller, less prominent link called "go to this comic" that doesn't go to the comic but to its explaination. Anyone else think that's a little back-to-front? [[User:Zootle|Zootle]] ([[User talk:Zootle|talk]]) 17:18, 31 August 2012 (UTC)
:OK, you're dumb :-). The standard template for an explanation page includes the header with "Prev", "Comic # (date)", and "Next" links. If we don't have explanation pages for the previous or next comic, we don't show the respective link. I hadn't noticed that the "Comic # (date)" bit was a link to the xkcd site before, but in context it makes sense to me. Including a link to the Explain page for the comic who's explain page you are already looking at doesn't make sense.
:The explanation page for the latest comic is "transcluded" in the main page pretty much as-is, so we get the header, the comic, the explanation, etc. We don't get the discussion, which is visible at the bottom of the Explain page. Because there is never an explanation for a comic that hasn't been released yet, there is never a "Next" link on the main page's transcluded header. So you get "Prev" and "Comic" links. The "Go to this comic" link is added by the main page above the transcluded explain page.
:I can see how the "Go to this comic" link might be poorly worded especially as it's placement seems to be within the explanation it's linking to. [[User:Blaisepascal|Blaisepascal]] ([[User talk:Blaisepascal|talk]]) 18:16, 31 August 2012 (UTC)
::Rather than "Go to this comic" maybe it could be "Go to full explanation" ? Something else? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:38, 5 September 2012 (UTC)
::There was [http://www.explainxkcd.com/wiki/index.php?title=explain_xkcd:Community_portal/Admin_requests#.22Edit_this_explanation.22_link_on_main_page a discussion at one point] about a wittier/more descriptive link - but no one came up with anything. I do like "Go to Full Explanation" better, for what it's worth. --[[User:DanB|DanB]] ([[User talk:DanB|talk]]) 15:31, 5 September 2012 (UTC)
:::My problem with that suggestion is that it implies that the main page explanation is not full. As of right now, the full explanation is transcluded on the main page. There's nothing more to see by clicking that link (explanation wise) Perhaps "Go to full explanation page" but that doesn't quite sound right to me... [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 15:42, 7 September 2012 (UTC)
::::How about "Go to this Comic Explanation Page"? One nice thing about the specific page rather than the [[Main_Page]] transcoding is that it nicely includes the discussion as well. I have a bookmark to the [[Main_Page]] that I look at every day, but I want to easily read the discussions, not only the explanation. Humm, maybe we could have a page [[most recent comic]] that automagically redirects to the most recent comic? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 12:42, 8 September 2012 (UTC)
:::::I tried to get [[most recent comic]] to redirect to LATESTCOMIC, but can't get the syntax working - it is possible? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:03, 8 September 2012 (UTC)
::::::Apparently it isn't. I would have tried <code><nowiki>#REDIRECT [[{{LATESTCOMIC}}]]</nowiki></code> like you did, but since that doesn't work, I'll delete the page for now. --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 16:38, 20 November 2012 (UTC)

== Discussion of latest comic ==
Perhaps include the discussions of the latest comic here? I almost missed there was a discussion field a few times because I would only read about the latest comic on the main page. [[User:Carewolf|Carewolf]] ([[User talk:Carewolf|talk]]) 14:54, 22 September 2012 (UTC)

This comics's explanation is complete bollocks, I think. Of course it is NOT a "fact that such a room exists". This comics parodies trope often used in cop movies - an elderly cop goes to work for the last time before his retirement, packs things, plans fishing the next day ... only to be called to one more case (possibly with a new, young and brash partner). And despites his efforts not to screw anything and stay clear of danger, he is either mortally wounded or screws big time and is degraded. So much clichè, that if someone says "It's my last day or service", you might be sure one of the two options above happens. See http://tvtropes.org/pmwiki/pmwiki.php/Main/Retirony [[User:edheldil|Edheldil]] 10:17, 26 September 2012 (UTC)

== The comic explanation count is wrong ==

The adjustment is currently 3, but there are now 6 subcategories and one list making the current correct adjustment 7.
If the wiki was upgraded to version 1.20, a form exists to automatically exclude subcategories.
--[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 09:56, 8 October 2012 (UTC)

:Looks like another week of the wiki going down then.
:But seriously, I've been noticing this too. Didn't know what was causing it, but it's going to have to be fixed sometime.[[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 10:25, 8 October 2012 (UTC)

::The text reads <pre><nowiki>We already have [[:Category:Comics|'''{{#expr:{{PAGESINCAT:Comics}}-3}}''' comic explanations]]!</nowiki></pre> The -3 is to account for the subcategories and non-explanation pages in the category. There apparently used to be three such pages, and now there are seven. I would fix this myself, but the page is protected. If the wiki where upgraded to version 1.20, the categories could be explicitly excluded, but the [[List of all comics]] would still be in the category. (Note that the -3 actually appears twice.) --[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 05:03, 11 October 2012 (UTC)

:::Mediawiki 1.20 fixes this issue, although it'd be nice if this could be fixed in the meantime via the hack reccommended by divad. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

:Looks like Waldir updated the "Comic Correction Count" to "10" (as of 20 November 2012):
<nowiki> We already have [[:Category:Comics|'''{{#expr:{{PAGESINCAT:Comics}}-10}}''' comic explanations]]!</big>
Note: the -10 in the calculation above is to discount subcategories (there are 7 of them as of 20 November 2012),
non-comic pages (2 as of same date: [[List of all comics]] and [[Exoplanet]])
and the comic 404, which was deliberately not posted. Thus 7 + 2 + 1 = 10
(But there are still {{#expr:{{LATESTCOMIC}}-({{PAGESINCAT:Comics}}-10)}} to go. Come and [[List of all comics|add yours]]!)</nowiki>
:Could we possibly make this more dynamic by creating a "IGNORE_IN_COUNT" category or something? and then using something like: <nowiki>{#expr:{{PAGESINCAT:Comics}}-{{PAGESINCAT:IGNORE_IN_COUNT}}}</nowiki>? Then any additional entries to the "Comics" category (that are 'special' entries) could just have the special category added and no main page editing would be necessary? --[[User:Bpothier|B. P.]] ([[User talk:Bpothier|talk]]) 07:50, 22 November 2012 (UTC)

==Make Jeff stop apologizing==
The apology for server downtime has been around for a while now. Can we take it down? [[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 04:41, 11 October 2012 (UTC)

== Spambots ==

I think someone should install [http://www.mediawiki.org/wiki/Extension:AbuseFilter AbuseFilter]. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 10:09, 13 October 2012 (UTC)

== Purge ==

We should regularly purge the server's cache for the main page using http://www.explainxkcd.com/wiki/index.php?title=Main_Page&action=purge to keep the explanation up to date. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 02:28, 3 November 2012 (UTC)

== Updating the Rules ==

I've been having a lovely discussion with someone who apparently thought the "edit anything you want" rule applied to the Talk pages. As we don't have any codified rules for ''here'' and can only point to "well the canonical way this is done on Wikipedia is..." I think that there are a few things we need to put into the list of Rules on the front page, and then have a link to a more in-depth talk about why the rules exist and what-not.

Specifically, I'm talking about writing "Feel free to edit any page on the wiki to be better. But, treat talk pages like you would blog comments: comments by other people ''cannot be changed by you'', you can only respond to them." as a new rule to be plastered on the front page, as there seems to be an increasing number social neophytes that seem to think that editing words that are attributed as being said by another person is perfectly legitimate and non-controversial.

Shall we discuss? [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:25, 15 November 2012 (UTC)

:We could add the etiquette rules as an addendum to the signature reminder at the top of the page. Just an extra note below the alert box asking people to not edit other people's comments. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

::It really should be right down with the "edited mercilessly" description, because this is an exception to that statement. Shouldn't have two sets of contradictory instructions in different places. When I made my improper edit, I had a semi-conscious moment of doubt about whether changing the other guy's comment was ok, even though this is a wiki (and even though it wasn't really clear to me that this "discussion" box held something totally separate from the page content), but that statement at the bottom put all such doubts to rest. I read it multiple times to be sure. But I did not notice that line at the top about the four tildes until ''much'' later. It's somewhat lost, visually, in the header line, when you're not looking directly at it.[[Special:Contributions/50.0.38.245|50.0.38.245]] 18:32, 18 November 2012 (UTC)

:::There's discussion to replace that message with a more noticeable alert box. The message at the bottom of the page appears for all pages, including talk pages, so a talk-page specific message there would not entirely fit. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 00:18, 19 November 2012 (UTC)

::::If that text at the bottom is in fact alterable, it should be written to take every case into account. It's an extremely poor user interface that has instructions appearing on a page stating rules that are the exact opposite of reality. And note that the altert box on the top looks a lot like a banner add, when you don't focus on it and read it. People will tend to habitually filter out anything written there from their perception. Also, it can easily be scrolled off the top of the screen when the discussion starts to get long, and they have a preview displayed.
::::So I think after the "...then do not submit it here.", it should add, "'''Exception''': others' comments in Discussion pages are not to be altered. See full rules at <<link to appropriate wikipedia page>>."

== Update after changes ==

The front page explanation hasn't been updated at all day to match changes in the explanation on the comic's page. This is a major problem i think, as it is the front page explanation people visitors will most often read. --[[User:St.nerol|St.nerol]] ([[User talk:St.nerol|talk]]) 20:43, 26 November 2012 (UTC)
: It might be a caching issue. Appending <code>&action=purge</code> to the URL will probably fix it. Can you confirm it looks good to you now? --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 00:29, 27 November 2012 (UTC)
::Yep, now it updates instantly! Well done, whatever you did! :) --[[User:St.nerol|St.nerol]] ([[User talk:St.nerol|talk]]) 16:24, 27 November 2012 (UTC)

Talk:1140: Calendar of Meaningful Dates

2012-11-28T15:33:25Z

50.0.38.245:

Seeing how the (northern hemisphere) summer months are bolder than the winter ones, I remember that someone said that "historical things" like wars and battles used to occur during the good weather months. Same for e.g. romance novels - people date and love on those dates. {{unsigned|‎81.34.231.6}}

If the search included Spanish dates in English texts, May 5th would be larger. {{unsigned|214.4.253.121}}

I wonder if he took into account the month/day swap between the US and UK dating system (among other countries). [[Special:Contributions/76.122.5.96|76.122.5.96]] 14:22, 28 November 2012 (UTC)

Interesting about the 11ths -- perhaps that correlates with low passenger loads on airplanes as well, and thus why the 11th was chosen for the attack (the month of September having been chosen for some other reason).[[Special:Contributions/50.0.38.245|50.0.38.245]] 15:33, 28 November 2012 (UTC)

Talk:Main Page

2012-11-18T18:32:42Z

50.0.38.245: /* Updating the Rules */

{{notice|This page is for discussion of the [[Main Page]] itself. Other issues probably belong at the [[Explain XKCD:Community portal]].}}

As a new user, I think the first page is very important. So I thought why not begin a discussion here what to have on the first page every user visits.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT) Re-signed here - b/c I broke the comment in two when I added the "List of comics" header. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 23:01, 2 August 2012 (EDT)

==List of comics==
I was thinking of having a quick link to the list of comics that is explained. Right know, it took me a while to even see any of them. Eventually I found the "List All Pages" (found it in Special pages) where I could find the comics that have been explained. What do you think?
:A category tag will do that for you automatically. Having a list of comics indexed by its number would be a little different.--[[User:Relic|Relic]] ([[User talk:Relic|talk]]) 05:59, 1 August 2012 (EDT)
::Sounds like a great list - I ''think'' it'd have to be manually maintained until/unless we get someone who knows how to make a bot update it. Categories will be useful, but they only work if someone added the category to the page in the first place. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:21, 1 August 2012 (EDT)
:::A (somewhat) related question - should [[:Category:Comics]] be sorted alphabetically or by comic number? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:43, 1 August 2012 (EDT)
::::I think [[:Category:Comics]] should be sorted by comic number. If you are looking for a specific comic, you will use the search field. Is there a way to make that happen? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::::They are two different functions. For the former, instead of adding <nowiki>[[Category:Comics]]</nowiki>, add, say, <nowiki>[[Category:Comics|1]]</nowiki>. For the second, we can create redirects. Normally, I'd say just make sure the search term was in the article text, but since numbers are going to be use for other purposes than just comic titles, it may be better to create [[1]] and [[Comic 1]] as redirects to the relevant articles right off the bat. --08:24, 1 August 2012 (EDT)
::::::We could also have a comic-list template on the Main Page, I suppose, or perhaps two - one for number and one for name? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:54, 1 August 2012 (EDT)
:::::::Here's what I was thinking of for that: {{tl|Comics navbox}} Thoughts? ''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]]
:(outdent) It's ugly, but a sortable wikitable [[User:SurturZ/sandbox|(click here for example)]] could be used as a checklist to see what has been uploaded and what hasn't. What's the project namespace here, anyway (analogue of "WP:")? --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:04, 3 August 2012 (EDT)
:OK, I've found a way to get all the titles of the comics, so I was confident enough to create <big>[[Explain XKCD:Checklist]]</big> which can be used to fill in the gaps. --[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 03:41, 3 August 2012 (EDT)
::I'm liking the checklist! That should do quite nicely as a "tool for editors". (I'm linking to it at the Community Portal). We still need the "template for readers." Did you think {{tl|Comics navbox}} was on the right track or should we do something else for that? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:09, 3 August 2012 (EDT)
::Better idea - I'm throwing it directly onto the Main Page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 20:10, 3 August 2012 (EDT)

==Admin list==
You can find a system-accurate list of admins [{{canonicalurl:Special:ListUsers|group=sysop}} here], so that might good to share, along with the manual list. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 07:13, 1 August 2012 (EDT)
:Added to page. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:10, 1 August 2012 (EDT)
::That's exactly what I wanted, but couldn't find the auto page for it. I knew it was somewhere. I don't see any reason to keep the link to the manual page. Do you? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 08:11, 1 August 2012 (EDT)
:::Not unless you want it. I'll remove it. Should I add the similar link for 'crats or is that unnecessary at this point? --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:25, 1 August 2012 (EDT)
::::To be honest, I have no idea what the Burecrats role does. Might be unnecessary now but helpful in the future? --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 11:16, 1 August 2012 (EDT)
:::::Bureaucrats can turn other users into administrators (or indeed, other bureaucrats). That privilege isn't available to ordinary administrators. I'd keep it to yourself for the time being. :-) --[[User:Yirba|Yirba]] ([[User talk:Yirba|talk]]) 17:39, 1 August 2012 (EDT)
::::::You can actually see a technical list of which rights each group confers at [[Special:ListGroupRights]]. As the wiki grows, you might want to spin off a few, such as the ability to grant rollbacker and autopatrolled, to admins as some other wikis have. But for the time being, at least, there's really no reason for the wiki to have more than one 'crat. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:07, 2 August 2012 (EDT)

== Community portal ==

I've created the [[Explain XKCD:Community portal]] as a tools/help page. If that's not what you want, feel free to change/move/whatever it, but I thought it'd be nice to save this page for discussion of the Main Page and discuss the wiki as a whole/ask for help there. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 08:36, 1 August 2012 (EDT)

== Direct link to latest comic ==

There should be a direct link to the latest comic at the top of the Main page. A nice thing about going to explainxkcd.com was that the latest comic is right there at the top. For those changing their default link to the wiki, there should be an easy "Latest Comic" link that quickly takes them there. I'm sure some folks actually skip xkcd.com and come directly here instead to read the latest offering from Randall. They shouldn't have to search for it.
[[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:59, 1 August 2012 (EDT)

: Maybe the page [[latest]] should redirect to the most recent comic? Could that be taken care of by some sort of script/template so it doesn't have to be manually updated? Should each explination page also have "next", "previous", "random", "first" and "latest" links, possibly also generated automatically via scripts/templates? Additionally, shouldn't the number page be the canonical one? It seems like [[Internal monologue]] should redirect to [[1089]] rather than the other way around - certainly it would make a bunch of scripting types of things a lot easier. [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:02, 1 August 2012 (EDT)
:::If you wanted, we could even use wiki-magic to show the title of the page as the Comic name, but the URL as the number - in order to parallel the actual XKCD website. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 17:09, 2 August 2012 (EDT)
:: Shouldn't there be a way to programmatically find the comic with the highest number that has a page with content? That would work as long as no one puts future comic pages up. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 20:25, 1 August 2012 (EDT)
:::It's all sounding like folks are over-complicating something quite easy. All I'm suggesting is a prominent link to http://www.xkcd.com/. No need, I think, to list which number the latest is, or include the next/last/random buttons, etc. [[User:Christopher Foxx|- CFoxx]] ([[User talk:Christopher Foxx|talk]]) 11:41, 3 August 2012 (EDT)
::::Oh. We've got that, now, in the sidebar - labeled as "XKCD." I do think that having an internal link to the latest (explained) comic would be a great thing, though. --''[[User:Philosopher|Philosopher]]'' [[User talk:Philosopher|Let us reason together.]] 16:36, 4 August 2012 (EDT)

You can transclude the latest comic on the main page like this: <nowiki>{{:pagename}} e.g. {{:Internal_monologue}} </nowiki>--[[User:SurturZ|SurturZ]] ([[User talk:SurturZ|talk]]) 00:25, 2 August 2012 (EDT)
: I've started with just a manual link to the latest comic. Ideally it will be automatic, but a manual link will work for now as I've had quite a few people ask for it. --[[User:Jeff|Jeff]] ([[User talk:Jeff|talk]]) 21:09, 1 August 2012 (EDT)

Transclusion of the latest comic is great. Someone with the right permissions should add (for instance on the top-right corner of the grey transclusion area) a link to edit the corresponding wiki page, so that people seeing something they could add would feel invited to do so (wiki style). In my opinion this would be a good way to improve the quality of the user-generated explanations.
Also, all the "XKCD"s in the "New here?" section should be converted to the lowercase "xkcd"...
[[User:Cos|Cos]] ([[User talk:Cos|talk]]) 14:00, 6 August 2012 (UTC)
:Good points. I've done both. --[[User:Waldir|Waldir]] ([[User talk:Waldir|talk]]) 15:48, 6 August 2012 (UTC)

Call me dumb, but... You've got a link called "prev" that goes to the explaination for the previous comic. Then a link called "comic #42" but that goes to xkcd. And then a smaller, less prominent link called "go to this comic" that doesn't go to the comic but to its explaination. Anyone else think that's a little back-to-front? [[User:Zootle|Zootle]] ([[User talk:Zootle|talk]]) 17:18, 31 August 2012 (UTC)
:OK, you're dumb :-). The standard template for an explanation page includes the header with "Prev", "Comic # (date)", and "Next" links. If we don't have explanation pages for the previous or next comic, we don't show the respective link. I hadn't noticed that the "Comic # (date)" bit was a link to the xkcd site before, but in context it makes sense to me. Including a link to the Explain page for the comic who's explain page you are already looking at doesn't make sense.
:The explanation page for the latest comic is "transcluded" in the main page pretty much as-is, so we get the header, the comic, the explanation, etc. We don't get the discussion, which is visible at the bottom of the Explain page. Because there is never an explanation for a comic that hasn't been released yet, there is never a "Next" link on the main page's transcluded header. So you get "Prev" and "Comic" links. The "Go to this comic" link is added by the main page above the transcluded explain page.
:I can see how the "Go to this comic" link might be poorly worded especially as it's placement seems to be within the explanation it's linking to. [[User:Blaisepascal|Blaisepascal]] ([[User talk:Blaisepascal|talk]]) 18:16, 31 August 2012 (UTC)
::Rather than "Go to this comic" maybe it could be "Go to full explanation" ? Something else? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:38, 5 September 2012 (UTC)
::There was [http://www.explainxkcd.com/wiki/index.php?title=explain_xkcd:Community_portal/Admin_requests#.22Edit_this_explanation.22_link_on_main_page a discussion at one point] about a wittier/more descriptive link - but no one came up with anything. I do like "Go to Full Explanation" better, for what it's worth. --[[User:DanB|DanB]] ([[User talk:DanB|talk]]) 15:31, 5 September 2012 (UTC)
:::My problem with that suggestion is that it implies that the main page explanation is not full. As of right now, the full explanation is transcluded on the main page. There's nothing more to see by clicking that link (explanation wise) Perhaps "Go to full explanation page" but that doesn't quite sound right to me... [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 15:42, 7 September 2012 (UTC)
::::How about "Go to this Comic Explanation Page"? One nice thing about the specific page rather than the [[Main_Page]] transcoding is that it nicely includes the discussion as well. I have a bookmark to the [[Main_Page]] that I look at every day, but I want to easily read the discussions, not only the explanation. Humm, maybe we could have a page [[most recent comic]] that automagically redirects to the most recent comic? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 12:42, 8 September 2012 (UTC)
:::::I tried to get [[most recent comic]] to redirect to LATESTCOMIC, but can't get the syntax working - it is possible? [[User:J-beda|J-beda]] ([[User talk:J-beda|talk]]) 13:03, 8 September 2012 (UTC)

== Discussion of latest comic ==
Perhaps include the discussions of the latest comic here? I almost missed there was a discussion field a few times because I would only read about the latest comic on the main page. [[User:Carewolf|Carewolf]] ([[User talk:Carewolf|talk]]) 14:54, 22 September 2012 (UTC)

This comics's explanation is complete bollocks, I think. Of course it is NOT a "fact that such a room exists". This comics parodies trope often used in cop movies - an elderly cop goes to work for the last time before his retirement, packs things, plans fishing the next day ... only to be called to one more case (possibly with a new, young and brash partner). And despites his efforts not to screw anything and stay clear of danger, he is either mortally wounded or screws big time and is degraded. So much clichè, that if someone says "It's my last day or service", you might be sure one of the two options above happens. See http://tvtropes.org/pmwiki/pmwiki.php/Main/Retirony [[User:edheldil|Edheldil]] 10:17, 26 September 2012 (UTC)

== The comic explanation count is wrong ==

The adjustment is currently 3, but there are now 6 subcategories and one list making the current correct adjustment 7.
If the wiki was upgraded to version 1.20, a form exists to automatically exclude subcategories.
--[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 09:56, 8 October 2012 (UTC)

:Looks like another week of the wiki going down then.
:But seriously, I've been noticing this too. Didn't know what was causing it, but it's going to have to be fixed sometime.[[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 10:25, 8 October 2012 (UTC)

::The text reads <pre><nowiki>We already have [[:Category:Comics|'''{{#expr:{{PAGESINCAT:Comics}}-3}}''' comic explanations]]!</nowiki></pre> The -3 is to account for the subcategories and non-explanation pages in the category. There apparently used to be three such pages, and now there are seven. I would fix this myself, but the page is protected. If the wiki where upgraded to version 1.20, the categories could be explicitly excluded, but the [[List of all comics]] would still be in the category. (Note that the -3 actually appears twice.) --[[User:Divad27182|Divad27182]] ([[User talk:Divad27182|talk]]) 05:03, 11 October 2012 (UTC)

:::Mediawiki 1.20 fixes this issue, although it'd be nice if this could be fixed in the meantime via the hack reccommended by divad. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

==Make Jeff stop apologizing==
The apology for server downtime has been around for a while now. Can we take it down? [[User:Davidy22|Davidy22]] ([[User talk:Davidy22|talk]]) 04:41, 11 October 2012 (UTC)

== Spambots ==

I think someone should install [http://www.mediawiki.org/wiki/Extension:AbuseFilter AbuseFilter]. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 10:09, 13 October 2012 (UTC)

== Purge ==

We should regularly purge the server's cache for the main page using http://www.explainxkcd.com/wiki/index.php?title=Main_Page&action=purge to keep the explanation up to date. --[[User:Kronf|Kronf]] ([[User talk:Kronf|talk]]) 02:28, 3 November 2012 (UTC)

== Updating the Rules ==

I've been having a lovely discussion with someone who apparently thought the "edit anything you want" rule applied to the Talk pages. As we don't have any codified rules for ''here'' and can only point to "well the canonical way this is done on Wikipedia is..." I think that there are a few things we need to put into the list of Rules on the front page, and then have a link to a more in-depth talk about why the rules exist and what-not.

Specifically, I'm talking about writing "Feel free to edit any page on the wiki to be better. But, treat talk pages like you would blog comments: comments by other people ''cannot be changed by you'', you can only respond to them." as a new rule to be plastered on the front page, as there seems to be an increasing number social neophytes that seem to think that editing words that are attributed as being said by another person is perfectly legitimate and non-controversial.

Shall we discuss? [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:25, 15 November 2012 (UTC)

:We could add the etiquette rules as an addendum to the signature reminder at the top of the page. Just an extra note below the alert box asking people to not edit other people's comments. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 06:40, 16 November 2012 (UTC)

::It really should be right down with the "edited mercilessly" description, because this is an exception to that statement. Shouldn't have two sets of contradictory instructions in different places. When I made my improper edit, I had a semi-conscious moment of doubt about whether changing the other guy's comment was ok, even though this is a wiki (and even though it wasn't really clear to me that this "discussion" box held something totally separate from the page content), but that statement at the bottom put all such doubts to rest. I read it multiple times to be sure. But I did not notice that line at the top about the four tildes until ''much'' later. It's somewhat lost, visually, in the header line, when you're not looking directly at it.[[Special:Contributions/50.0.38.245|50.0.38.245]] 18:32, 18 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T09:16:39Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

{{Collapse top|title=Discussion hidden}}
:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by an admin, no less.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::::Explain XKCD follows the editing guidelines followed by mainline Wikipedia by default. The policy page in question is {{w|WP:TPO}}. Editing other people's talk page entries tends to be frowned upon as it leads to misrepresentation of other people's opinions. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 03:21, 15 November 2012 (UTC)

::::::::And it's appropriate to threaten to ban someone permanently from the site when they mistakenly break this rule once? Isn't there a line on the main page that says "Don't be a jerk"?[[Special:Contributions/50.0.38.245|50.0.38.245]] 05:32, 15 November 2012 (UTC)

:::::::::There is no possible way for me to answer this without coming off like a jerk. See "{{w|Loaded question|When did you stop beating your wife?}}". Either I say, yes it's appropriate, in a "give one warning, then consequences" "spare the rod, spoil the child" kind of way and seem like hard-ass. Or I say no, and become a hypocrite. So all I'm going to say is, Welcome to explain xkcd, a wiki devoted to explaining xkcd. Please help better the wiki, ask questions if you need help or don't understand something, and someone will let you know if you've overstepped your bounds. We don't have any official rules written specifically for here but [http://en.wikipedia.org/wiki/Help:Getting_started Wikipedia] does. P.S. simply being around for awhile does not make me infallible, I'm still human, prone to anachronistic failures. There I said it. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 06:30, 15 November 2012 (UTC)

::::::::::I guess your "only human" statement is as close as you'll come to an apology for your excessive harshness. So a bit of advice: if you're "imploring" people to contribute, perhaps you should be setting an example of an environment that is ''not'' a minefield.[[Special:Contributions/50.0.38.245|50.0.38.245]] 07:30, 15 November 2012 (UTC)

:::::::::: To try to clarify further: this was not simply "one warning, then consequences." It's more like "one warning, then death." As if a cop shoved his gun in someone's face for failing to use turn signals.[[Special:Contributions/50.0.38.245|50.0.38.245]] 07:40, 15 November 2012 (UTC)

:::::::::::This discussion adds no value to the relevant page, and so I have hidden it from regular view. Please cease this argument or take it to a user talk page. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 08:17, 15 November 2012 (UTC)

I'd be willing to see this whole mess replaced with the following (i.e. I give permission for my comments within the collapse field to be deleted if all comments within the field are replaced with the below, or something similar):

:::Please don't edit others' comments on talk pages; it's considered quite rude. On a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
If not agreed, I give permission for anyone to delete these three paragraphs I just added[[Special:Contributions/50.0.38.245|50.0.38.245]] 09:16, 15 November 2012 (UTC)
{{Collapse bottom}}

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T07:40:05Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by an admin, no less.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::::Explain XKCD follows the editing guidelines followed by mainline Wikipedia by default. The policy page in question is {{w|WP:TPO}}. Editing other people's talk page entries tends to be frowned upon as it leads to misrepresentation of other people's opinions. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 03:21, 15 November 2012 (UTC)

::::::::And it's appropriate to threaten to ban someone permanently from the site when they mistakenly break this rule once? Isn't there a line on the main page that says "Don't be a jerk"?[[Special:Contributions/50.0.38.245|50.0.38.245]] 05:32, 15 November 2012 (UTC)

:::::::::There is no possible way for me to answer this without coming off like a jerk. See "{{w|Loaded question|When did you stop beating your wife?}}". Either I say, yes it's appropriate, in a "give one warning, then consequences" "spare the rod, spoil the child" kind of way and seem like hard-ass. Or I say no, and become a hypocrite. So all I'm going to say is, Welcome to explain xkcd, a wiki devoted to explaining xkcd. Please help better the wiki, ask questions if you need help or don't understand something, and someone will let you know if you've overstepped your bounds. We don't have any official rules written specifically for here but [http://en.wikipedia.org/wiki/Help:Getting_started Wikipedia] does. P.S. simply being around for awhile does not make me infallible, I'm still human, prone to anachronistic failures. There I said it. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 06:30, 15 November 2012 (UTC)

::::::::::I guess your "only human" statement is as close as you'll come to an apology for your excessive harshness. So a bit of advice: if you're "imploring" people to contribute, perhaps you should be setting an example of an environment that is ''not'' a minefield.[[Special:Contributions/50.0.38.245|50.0.38.245]] 07:30, 15 November 2012 (UTC)

:::::::::: To try to clarify further: this was not simply "one warning, then consequences." It's more like "one warning, then death." As if a cop shoved his gun in someone's face for failing to use turn signals.[[Special:Contributions/50.0.38.245|50.0.38.245]] 07:40, 15 November 2012 (UTC)

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T07:30:43Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by an admin, no less.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::::Explain XKCD follows the editing guidelines followed by mainline Wikipedia by default. The policy page in question is {{w|WP:TPO}}. Editing other people's talk page entries tends to be frowned upon as it leads to misrepresentation of other people's opinions. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 03:21, 15 November 2012 (UTC)

::::::::And it's appropriate to threaten to ban someone permanently from the site when they mistakenly break this rule once? Isn't there a line on the main page that says "Don't be a jerk"?[[Special:Contributions/50.0.38.245|50.0.38.245]] 05:32, 15 November 2012 (UTC)

:::::::::There is no possible way for me to answer this without coming off like a jerk. See "{{w|Loaded question|When did you stop beating your wife?}}". Either I say, yes it's appropriate, in a "give one warning, then consequences" "spare the rod, spoil the child" kind of way and seem like hard-ass. Or I say no, and become a hypocrite. So all I'm going to say is, Welcome to explain xkcd, a wiki devoted to explaining xkcd. Please help better the wiki, ask questions if you need help or don't understand something, and someone will let you know if you've overstepped your bounds. We don't have any official rules written specifically for here but [http://en.wikipedia.org/wiki/Help:Getting_started Wikipedia] does. P.S. simply being around for awhile does not make me infallible, I'm still human, prone to anachronistic failures. There I said it. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 06:30, 15 November 2012 (UTC)

::::::::::I guess your "only human" statement is as close as you'll come to an apology for your excessive harshness. So a bit of advice: if you're "imploring" people to contribute, perhaps you should be setting an example of an environment that is ''not'' a minefield.[[Special:Contributions/50.0.38.245|50.0.38.245]] 07:30, 15 November 2012 (UTC)

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T05:32:39Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by an admin, no less.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::::Explain XKCD follows the editing guidelines followed by mainline Wikipedia by default. The policy page in question is {{w|WP:TPO}}. Editing other people's talk page entries tends to be frowned upon as it leads to misrepresentation of other people's opinions. [[User:Davidy22|Davidy22]][[User talk:Davidy22|<tt>(talk)</tt>]] 03:21, 15 November 2012 (UTC)

::::::::And it's appropriate to threaten to ban someone permanently from the site when they mistakenly break this rule once? Isn't there a line on the main page that says "Don't be a jerk"?[[Special:Contributions/50.0.38.245|50.0.38.245]] 05:32, 15 November 2012 (UTC)

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T01:58:56Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by a main editor, no less.[[Special:Contributions/50.0.38.245|50.0.38.245]] 01:58, 15 November 2012 (UTC)

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T01:41:41Z

50.0.38.245:

Something should be added about the prior probability of the sun going nova, as that is the primary substantive point. "The neutrino detector is evidence that the Sun has exploded. It's showing an observation which is 35 times more likely to appear if the Sun has exploded than if it hasn't (likelihood ratio of 35:1). The Bayesian just doesn't think that's strong enough evidence to overcome the prior odds, i.e., after multiplying the prior odds by 35 they still aren't very high." - http://lesswrong.com/r/discussion/lw/fe5/xkcd_frequentist_vs_bayesians/ [[Special:Contributions/209.65.52.92|209.65.52.92]] 23:51, 9 November 2012 (UTC)

Note: taking that bet would be a mistake. If the Bayesian is right, you're out $50. If he's wrong, everyone is about to die and you'll never get to spend the winnings. Of course, this meta-analysis is itself a type of Bayesian thinking, so [http://lmgtfy.com/?q=dunning-kruger+effect Dunning-Kruger Effect] would apply. - [[User:Frankie|Frankie]] ([[User talk:Frankie|talk]]) 13:50, 9 November 2012 (UTC)
: You don't think you could spend fifty bucks in eight minutes? ;-) (PS: wikipedia is probably a better link than lmgtfy: {{w|Dunning-Kruger effect}}) -- [[User:IronyChef|IronyChef]] ([[User talk:IronyChef|talk]]) 15:35, 9 November 2012 (UTC)
Randall has referenced the Labyrinth guards before: [http://xkcd.com/246/ xkcd 246:Labyrinth puzzle]. Plus he has satirized p<0.05 in [http://www.explainxkcd.com/wiki/index.php?title=882:_Significant xkcd 882:Significant]--[[User:Prooffreader|Prooffreader]] ([[User talk:Prooffreader|talk]]) 15:59, 9 November 2012 (UTC)

A bit of maths. Let event N be the sun going nova and event Y be the detector giving the answer "Yes". The detector has already given a positive answer so we want to compute P(N|Y). Applying the Bayes' theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: P(Y|N) = 1
: P(N) = 0.0000....
: P(Y|N) * P(N) = 0.0000...
: P(Y) = p(Y|N)*P(N) + P(Y|-N)*P(-N)
: P(Y|-N) = 1/36
: P(-N) = 0.999999...
: P(Y) = 0 + 1/36 = 1/36
: P(N|Y) = 0 / (1/36) = 0
Quite likely it's not entirely correct. [[User:Lmpk|Lmpk]] ([[User talk:Lmpk|talk]]) 16:22, 9 November 2012 (UTC)

Here's what I get for the application of Bayes' Theorem:
: P(N|Y) = P(Y|N) * P(N) / P(Y)
: = P(Y|N) * P(N) / [P(Y|N) * P(N) + P(Y|~N) * P(~N)]
: = 35/36 * P(N) / [35/36 * P(N) + 1/36 * (1 - P(N))]
: = 35 * P(N) / [35 * P(N) - P(N) + 1]
: < 35 * P(N)
: = 35 * (really small number)

So, if you believe it's extremely unlikely for the sun to go nova, then you should also believe it's unlikely a Yes answer is true.

I wouldn't say the comic is about election prediction models. It's about a long-standing dispute between two different schools of statisticians, a dispute that began before Nate Silver was born. It's possible that the recent media attention for Silver and his ilk inspired this subject, but it's the kind of geeky issue Randall would typically take on in other circumstances too. [[User:MGK|MGK]] ([[User talk:MGK|talk]]) 19:44, 9 November 2012 (UTC)

I agree - this is not directed at the US-presidential election. I also want to add, that Bayesian btatistics assumes that parameters of distributions (e.g. mean of gaussian) are also random variables. These random variables have prior distributions - in this case p(sun explodes). The Bayesian statistitian in this comic has access to this prior distribution and so has other estimates for an error of the neutrino detector. The knowlege of the prior distribution is somewhat considered a "black art" by other statisticians.

My personal interpretation of the "bet you $50 it hasn't" reply is in the case of the sun going nova, no one would be alive to ask the neutrino detector, the probability of the sun going nova is always 0. [[User:Paps|Paps]]

:Yes, you would be able to ask. While neutrinos move almost at speed of light, the plasma of the explosion is significally slower, [http://en.wikipedia.org/wiki/Supernova 10% of speed of light tops]. You will have more that hour to ask. (Note that technically, sun can't go [http://en.wikipedia.org/wiki/Nova nova], because nova is white dwarf with external source of hydrogen. It can (and will), however, go supernova, which I assume is what Randall means.) -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 09:19, 12 November 2012 (UTC)

:: Our sun will not go supernova, as it has insufficient mass. It will slowly become hotter, rendering Earth uninhabitable in a few billion years. In about 5 billion years it will puff up into a red giant, swallowing the inner planets. After that, it will gradually blow off its lighter gasses, eventually leaving behind the core, a white dwarf. [[User:dcmeserve|dcmeserve]]

:::I left your comment here so I can set you straight on something. '''''DO NOT EVER''''' edit any editor's comments on a discussion page. You can reply to their comment, but you do not edit another person's words. You do that again, you get the banhammer. [[User:Lcarsos|lcarsos]] ([[User talk:Lcarsos|talk]]) 17:38, 13 November 2012 (UTC)
:::: Quote from the instructions at the bottom of the discussion edit page: "Please note that all contributions to explain xkcd '''may be edited, altered, or removed by other contributors'''. If you do not want '''your writing to be edited mercilessly''', then do not submit it here." But don't worry, I won't be contributing again, if it can be met with this kind of attitude.[[User:dcmeserve|dcmeserve]]

:::::If you'll note, those instructions are on the bottom of every edit page. Indeed, the notice is intended to be for article pages, where it is encouraged that an editor with an improvement, improve upon the words of another editor. However, on a talk page, discourse is meant to be conducted, by editors for the betterment of the article. For constructive discourse to occur, a person's words must be left in tact. The act of censorship hurts the common goal of betterment. Per [http://en.wikipedia.org/wiki/Wikipedia:Talk_page_guidelines#Editing_comments Wikipedia], the authoritative source on how a wiki works best: "you ''should not'' edit or delete the comments of other editors without their permission." I encourage, nay, ''implore'', you to assist in the improvement this wiki. But please, do it without editing other people's comments on a talk page, that's simply rude. [[User:Lcarsos|lcarsos]]_a ([[User talk:Lcarsos|talk]]) 01:08, 15 November 2012 (UTC)

::::::This was my first time contributing to a wiki discussion page. There was nothing written here to lead me to believe that it was different in this regard from any other wiki page; quite the opposite, as I mentioned. Perhaps you can find a way to describe this exception in the instructions at the bottom of the edit page. I'm sure you found out or helped form this bit of wiki etiquette long ago, but people who are new to contributing should not be verbally assaulted for not having heard of it already. And by a main editor, no less.[[User:dcmeserve|dcmeserve]]

I think the explanation is wrong or otherwise lacking in its explanation: The P-value is not the entire problem with the frequentist's viewpoint (or alternatively, the problem with the p-value hasn't been explained). The Frequentist has looked strictly at a two case scenario: Either the machine rolls 6-6 and is lying, or it doesn't rolls 6-6 and it is telling the truth. Therefore, there is a 35/36 probability (97.22%) that the machine is telling the truth and therefore the sun has exploded. The Bayesian is factoring in outside facts and information to improve the accuracy of the probability model. He says "Either the machine rolls 6-6 (a 1/36 probability, or 2.77%) or the sun has exploded (an aparently far less likely scenario). Given the comparison, the Bayesian believes it is MORE probable that the machine rolled 6-6 than the sun exploded, given the relative probabilities. If the latter is a 1 in a million chance (0.000001%), it is 2,777,777 times more likely that the machine rolled 6-6 than the sun exploded.
To borrow a demonstration/explanation technique from the Monty Hall problem, if the machine told you a coin flip was heads, that would be 50% chance of occuring while a 2.7% chance of the machine lying, the probabilities would clearly suggest that the machine was more likely to be telling the truth. Whereas if the machine said that 100 coin flips had all come up heads (7.88x10^-31%). Is it more likely that 100 coin flips all came up heads or is it more likely the machine is lying? What about 1000 coin flips? or 1,000,000? I think the question is, whether one could assign a probability to the sun exploding. Also, I think they could have avoided the whole thing by asking the machine a second time and see what it answered. [[User:TheHYPO|TheHYPO]] ([[User talk:TheHYPO|talk]]) 19:09, 12 November 2012 (UTC)

Another source of explanation: http://stats.stackexchange.com/questions/43339/whats-wrong-with-xkcds-frequentists-vs-bayesians-comic --[[User:JakubNarebski|JakubNarebski]] ([[User talk:JakubNarebski|talk]]) 20:12, 12 November 2012 (UTC)

The P-value really has nothing to do with it. If I think that there is a 35/36 chance that the sun has exploded, then I should we willing to take any bet that the sun has exploded with better than 1:35 odds. For example, if someone bets me that the sun has exploded in which they will pay me $2 if the sun has exploded and I will pay them $35 if it hasn't, then based on my belief that the sun has exploded with 35/36 probability, then my expected value for this bet is 2*35/36 - 35 * 1/36 = 35/36 dollars and I will take this bet. Clearly I would also take a bet with 1:1 odds - my estimated expected value in the proposed bet in the comic would be 50*35/36 - 50 * 1/36 = $49 (approximately), and I would for sure take this bet. The Bayesian on the other hand has a much lower belief that the sun has exploded because he takes into account the prior probability of the sun exploding, so he would take the reverse side of the bet. The difference is that the Bayesian uses prior probabilities in computing his belief in an event, whereas frequentists do not believe that you can put prior probabilities on events in the real world. Also note that this comic has nothing to do with whether people would die if the sun went nova - the comic is titled "Frequentists vs Bayesians" and is about the difference between these two approaches. {{unsigned|171.64.68.120}}

The Labyrinth reference reminds me of an old Doctor Who episode (Pyramid of Mars), where the Doctor is also faced with a truthful and untruthful set of guards. Summarized here: http://tardis.wikia.com/wiki/Pyramids_of_Mars_(TV_story) [[User:Fermax|Fermax]] ([[User talk:Fermax|talk]]) 04:49, 14 November 2012 (UTC)

Talk:1132: Frequentists vs. Bayesians

2012-11-15T00:42:16Z

50.0.38.245:

Talk:1132: Frequentists vs. Bayesians

2012-11-13T13:23:36Z

50.0.38.245:

Talk:1132: Frequentists vs. Bayesians

2012-11-13T13:15:33Z

50.0.38.245:

Talk:1132: Frequentists vs. Bayesians

2012-11-13T13:14:08Z

50.0.38.245: Edited comment by Hkmaly to remove assertion that sun will go supernova; added comment that it will become red giant then white dwarf