https://www.explainxkcd.com/wiki/api.php?action=feedcontributions&user=162.158.186.192&feedformat=atomexplain xkcd - User contributions [en]2022-10-05T03:07:44ZUser contributionsMediaWiki 1.30.0https://www.explainxkcd.com/wiki/index.php?title=Talk:2242:_Ground_vs_Air&diff=184724Talk:2242: Ground vs Air2019-12-17T01:12:03Z<p>162.158.186.192: </p>
<hr />
<div><!--Please sign your posts with ~~~~ and don't delete this text. New comments should be added at the bottom.--><br />
<br />
Wow; it took longer than I care to admit to realize 'thick' wasn't 'viscosity'...but 'altitude'. [[User:Elvenivle|Elvenivle]] ([[User talk:Elvenivle|talk]]) 01:08, 17 December 2019 (UTC)<br />
<br />
A link to the article is here: https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2005GL025621. [[Special:Contributions/162.158.186.192|162.158.186.192]] 01:12, 17 December 2019 (UTC)</div>162.158.186.192https://www.explainxkcd.com/wiki/index.php?title=Talk:2069:_Wishlist&diff=165654Talk:2069: Wishlist2018-11-07T15:18:36Z<p>162.158.186.192: Adding line breaks after comments for clarity.</p>
<hr />
<div><!--Please sign your posts with ~~~~ and don't delete this text. New comments should be added at the bottom.--><br />
Inspired by the current furore over Super Smash Bros being branded racist over the character Mr Game And Watch, perhaps? I know people started yelling over the last few days, but don't play the game so I don't have any further details. Feel free to delete / expand. [[Special:Contributions/172.69.62.160|172.69.62.160]] 09:36, 7 November 2018 (UTC)<br />
<br />
Clippy: "It was an intelligent user interface that assisted users." Really? Did you have a different clippy? [[Special:Contributions/141.101.69.45|141.101.69.45]] 10:05, 7 November 2018 (UTC)<br />
<br />
Randall should submit his list to McLeodGaming, maybe they will put one of these into SSF3. https://mcleodgaming.fandom.com/wiki/Character#Playable_characters_2 --[[Special:Contributions/162.158.88.44|162.158.88.44]] 10:53, 7 November 2018 (UTC)<br />
<br />
The Mario and Luigi hybrid might be a reference to [https://knowyourmeme.com/memes/bowsette this monstrosity]. [[User:Fabian42|Fabian42]] ([[User talk:Fabian42|talk]]) 12:09, 7 November 2018 (UTC)<br />
<br />
InstallShield Wizard Final Smash: Install malware. Screen glitches out, game blue screens, everyone takes damage and goes flying. [[User:Linker|Linker]] ([[User talk:Linker|talk]]) 14:17, 7 November 2018 (UTC)</div>162.158.186.192https://www.explainxkcd.com/wiki/index.php?title=Talk:2056:_Horror_Movies&diff=164289Talk:2056: Horror Movies2018-10-17T05:28:24Z<p>162.158.186.192: Example of new Ian Malcolm quote from new horror-based JP movie</p>
<hr />
<div><!--Please sign your posts with ~~~~ and don't delete this text. New comments should be added at the bottom.--><br />
<br />
Horror is about my least favorite genre of film. Westerns rank around the same. I find both pretty boring, though there are some suspense films, when done right, that I do like. [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 17:55, 8 October 2018 (UTC)<br />
:I agree about horror but the Western {{w|A Fistful of Dollars}} and some more by {{w|Sergio Leone}} are on my personal top movie list. --[[User:Dgbrt|Dgbrt]] ([[User talk:Dgbrt|talk]]) 18:02, 8 October 2018 (UTC)<br />
::Actually, I can enjoy almost any genre if its a humorous spoof of the genre. I love Blazing Saddles, for example. And there are rare examples in genres that can appeal to outsiders. I may have to give Sergio Leone's movies a try. [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 18:13, 8 October 2018 (UTC)<br />
:::Oh, from the {{w|Dollars Trilogy}} you should start with the third, running three hours and still the best. And for comedy horror this is a widely unknown great one: {{w|Little Shop of Horrors (film)}}. Check the cast. --[[User:Dgbrt|Dgbrt]] ([[User talk:Dgbrt|talk]]) 19:00, 8 October 2018 (UTC)<br />
Early XKCD issues frequently referenced Randall's fear of velociraptors. There hasn't been a reference to this fear in many years though. Did Randall forget this trope? Is he no longer scared of dinosaurs? [[Special:Contributions/108.162.216.112|108.162.216.112]] 19:55, 8 October 2018 (UTC)<br />
: It could be he hasn't encountered a velociraptor recently and has therefore lost his fear. [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 21:04, 8 October 2018 (UTC)<br />
: It could also be he has encountered a velociraptor recently but she was friendly and assured him humans are not among her prey list and she just eats evil T-rex professors who screw around with the speed of light. [[Special:Contributions/141.101.76.58|141.101.76.58]] 10:47, 9 October 2018 (UTC)<br />
:I've always seen it as a LOVE for velociraptors, not a fear, that he's often brought them up. As Jurassic Park has told everybody they're killing machines, it makes the most sense to mention them in regards to attacks. :) [[User:NiceGuy1|NiceGuy1]] ([[User talk:NiceGuy1|talk]]) 05:24, 12 October 2018 (UTC)<br />
<br />
I understand the idea: I don't care about horrors, but I like fantasy and sci-fi movies and was never stopped by someone classifying some fantasy/sci-fi movie as horror ... like in case of Dracula, Frankenstein, The Exorcist ... or Underworld, Constantine, Alien ... wait, is Alien classified as horror or not? -- [[User:Hkmaly|Hkmaly]] ([[User talk:Hkmaly|talk]]) 22:34, 8 October 2018 (UTC)<br />
: Alien is quite surely a horror movie, I would say. Aliens (=the second movie) sets a different tone and includes elements of an action movie. Sebastian --[[Special:Contributions/172.68.110.34|172.68.110.34]] 06:47, 9 October 2018 (UTC)<br />
: You'd like Sunshine then. Personally, even that had too much horror for me. --[[Special:Contributions/162.158.38.196|162.158.38.196]] 11:17, 9 October 2018 (UTC)<br />
<br />
If we take it as reverse analogy, the title text hints he didn't liked/watched the part where Jeff tried to convince the executives to build the park in the original movie, as it was observed as a Horror part for him. --[[User:Nachuo|Nachuo]] ([[User talk:Nachuo|talk]]) 06:41, 9 October 2018 (UTC)<br />
<br />
I don't think the explanation should say that Randall is the one talking in the title text. I have to assume that that is still a conversation between Cueball and White Hat. I doubt Randall is talking to himself there... [[Special:Contributions/162.158.78.130|162.158.78.130]] 14:26, 9 October 2018 (UTC)<br />
:You are right, it's a conversation between Cueball and White Hat. But as it's explained before Cueball represents Randall, not uncommon at xkcd. --[[User:Dgbrt|Dgbrt]] ([[User talk:Dgbrt|talk]]) 20:59, 9 October 2018 (UTC)<br />
<br />
Haha, I'm totally with Randall on this one. I just don't get horror movies. ¯\_(ツ)_/¯<br>--[[User:Sensorfire|Sensorfire]] ([[User talk:Sensorfire|talk]]) 17:40, 9 October 2018 (UTC)<br />
: There's actually some serious research which had been done. In most case the pleasant sensation some people experience, comes from "watching terrible things happen to *other* people". i.e.: it's due to their brains suddenly realizing that *they* did not get any horrible thing. It hapenned to someone else and they managed to "survive" it. [[Special:Contributions/162.158.111.133|162.158.111.133]] 17:26, 10 October 2018 (UTC)<br />
<br />
Yeah, I agree too, don’t much like horror movies, but have been intending to watch Jurassic Park for the science and dinosaurs, despite the horror theme. I think the part of the book that stuck with me the most was the idea of “what could they possibly be doing with THREE CRAY 1 SUPERCOMPUTERS?!” 😜 [[User:PotatoGod|PotatoGod]] ([[User talk:PotatoGod|talk]]) 18:41, 9 October 2018 (UTC)<br />
<br />
Why am I getting deja vu? Is there a similar xkcd comic or a similar joke on another comic?<br />
[[Special:Contributions/172.69.134.9|172.69.134.9]] 01:37, 10 October 2018 (UTC)<br />
<br />
<br />
A recent edit changed it from Cueball being sarcastic in his supposed enthusiasm for horror films, to one where he is a genuine fan. I believe this is incorrect, and he really is being sarcastic. But I didn't want to change it back without some discussion. Who thinks Cueball is a fan, who thinks he's just being sarcastic, and who thinks we should try to include both theories in the explanation? [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 13:58, 10 October 2018 (UTC)<br />
:I'm coming around to the idea that he's a real fan. Since I'm not, I just assumed he was being sarcastic. :-) I've added that possibility and tweaked it a little. [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 14:28, 10 October 2018 (UTC)<br />
:I believe your first impression was correct - to me, the caption reinforces the idea that the response in the comic panel is a sarcastic answer to White Hat. [[User:Ianrbibtitlht|Ianrbibtitlht]] ([[User talk:Ianrbibtitlht|talk]]) 14:58, 10 October 2018 (UTC)<br />
:I'm 100% certain that Cueball is being sarcastic. [[User:Tarcas|Tarcas]] ([[User talk:Tarcas|talk]]) 15:44, 10 October 2018 (UTC)<br />
:He's being sarcastic, no question. Him being sarcastic fits in with the caption. AND the title text, sarcasm means the conversation is simply continuing in the title text. Plus Cueball is generally the "on-screen" representation of Cueball, him being sarcastic would be Randall being sarcastic, which, again, fits in with Randall's sentiment in the caption and title text. :) You've fallen prey to the usual ExplainXKCD fallacy of introducing doubt and uncertainty where there is none, LOL! And I SO agree with Randall on this comic, and I have the added thing that horror movies don't work on me anyway (even if I WAS interested in getting scared), outside of cheap jump scares. [[User:NiceGuy1|NiceGuy1]] ([[User talk:NiceGuy1|talk]]) 05:24, 12 October 2018 (UTC)<br />
<br />
The idea of breeding an island full of killers is actually a good description of the horror movie The Brood.[[User:JeroenRL|JeroenRL]] ([[User talk:JeroenRL|talk]]) 14:10, 10 October 2018 (UTC)<br />
<br />
I don't really agree with the section that says Randall admits he's criticising from a position of ignorance. He's shown that he's not ignorant of horror movies, he merely doesn't understand why they're popular. [[Special:Contributions/172.69.55.166|172.69.55.166]] 15:22, 10 October 2018 (UTC)<br />
<br />
"Death, uh... finds a way." -Ian Malcolm, <i>Serial Killer Park</i> --Electro-- [[Special:Contributions/162.158.186.192|162.158.186.192]] 05:28, 17 October 2018 (UTC)</div>162.158.186.192https://www.explainxkcd.com/wiki/index.php?title=Talk:2053:_Incoming_Calls&diff=163640Talk:2053: Incoming Calls2018-10-03T23:57:59Z<p>162.158.186.192: </p>
<hr />
<div><!--Please sign your posts with ~~~~ and don't delete this text. New comments should be added at the bottom.--><br />
The "other scammers" section is far too small. [[Special:Contributions/108.162.216.166|108.162.216.166]] 16:54, 1 October 2018 (UTC)<br />
<br />
We have two title texts explanations. With slightly conflicting information. Combine and brush up or should we just do one or the other for now? I like the CBS source in the first so I think we should absolutely preserve that at least. [[User:Lukeskylicker|Lukeskylicker]] ([[User talk:Lukeskylicker|talk]]) 17:15, 1 October 2018 (UTC)<br />
<br />
: Supposing that you are correct, I have to add that I have never heard of the headset trick being used to buy time to connect you to a real scammer. But then again, I don't get scammed that often. [[User:Kwonunn|Kwonunn]] ([[User talk:Kwonunn|talk]]) 17:44, 2 October 2018 (UTC)<br />
<br />
He forgot bill collectors. {{unsigned ip|162.158.63.52}}<br />
<br />
As the link from the first title text explanation points out, they don't *need* your credit card or social security number as many phone companies, especially mobile companies, will allow a third party to add charges to your phone bill if you've agreed to pay the money. With that in mind, I don't think the second explanation flies. [[Special:Contributions/162.158.186.90|162.158.186.90]] 17:42, 1 October 2018 (UTC)<br />
<br />
This only makes sense if it’s proportional or percentage based. But then that makes one wonder if some of this might be because the number of calls dropped over time. {{unsigned|Mr.Dude}}<br />
<br />
There's a contradiction between "it's safe to assume that calls from his family didn't decrease over the years", and "Over time, Randall's friends and family have been less likely to make phone calls to him, likely due to the use of text messages and other messaging apps.". I'd suggest rephrasing the first part to say "it's possible the calls from family didn't decrease over the years, in which case they only make up a smaller fraction as the number of total calls increases since 1990.", or simply "some of the categories like family calls appear to be occurring less often but may only be decreasing in frequency in proportion to total calls" [[Special:Contributions/162.158.142.28|162.158.142.28]] 21:10, 1 October 2018 (UTC)<br />
:I know for me personally family calls have decreased as texting and other messaging apps have become more common, and the same might have happened for him. It is clear that this graph excludes texting as by the present the only friend calling is that one friend that hates texting. That person may be the best way to figure out if the absolute volume of calls has increased...it appears the volume of total calls has increased, at least recently, as that one friend originally took up a larger proportion of the vertical space (of course the frequency of correspondence with that friend may also have changed).[[Special:Contributions/172.68.46.5|172.68.46.5]] 16:51, 2 October 2018 (UTC)<br />
::Thanks for your written thoughts. You also can enhance the explanation. But for now I've added a new paragraph about texting, just because it's not part of the comic. And, sorry I missed it, I also hate tex...ng ;) --[[User:Dgbrt|Dgbrt]] ([[User talk:Dgbrt|talk]]) 17:29, 2 October 2018 (UTC)<br />
<br />
At least not being British he missed the PPI calls. [[Special:Contributions/162.158.154.235|162.158.154.235]] 21:16, 1 October 2018 (UTC)<br />
:Along with the current spate of automated calls telling me that my IP address needs to be changed as it has been "compromised in multiple countries". [[User:Gearoid|Gearóid]] ([[User talk:Gearoid|talk]]) 06:44, 3 October 2018 (UTC)<br />
<br />
The trick is not always just to get you thinking you're talking to a real person. More likely it is to get a recording of you saying "yes", which can be used maliciously.--[[Special:Contributions/162.158.94.20|162.158.94.20]] 08:19, 2 October 2018 (UTC)<br />
<br />
AFAIK, that has only been done once, there is a question on it here: https://skeptics.stackexchange.com/questions/42050/have-phone-scammers-recorded-yes-statements-to-fraudulently-authorise-payments (I was going to say that it was probably a myth, but the accepted answer had not been written when I last read that page. Pays to check sources I guess, be it for updated webpages, or to counter scammers [[User:Baldrickk|Baldrickk]] ([[User talk:Baldrickk|talk]]) 12:57, 3 October 2018 (UTC)<br />
<br />
Referencing "the famous WhatsApp" seems unnecessary. It could be replaced with something like "various mobile messaging apps" [[Special:Contributions/172.68.133.168|172.68.133.168]] anonanon<br />
<br />
Could someone please provide more information about that "auto insurance scammer" part? From my foreign perspective, this means nothing at all and it seems odd that Randall's scammer calls were so numerous and so single-minded in their focus for such a long time. Were these calls really the only scams during that time? Did other scammers then copy their methods? It may seem obvious to you but it certainly isn't for me.[[Special:Contributions/141.101.88.196|141.101.88.196]] 09:30, 3 October 2018 (UTC)<br />
<br />
: I don't specifically know what that scam is; maybe that was just a scam that Randall personally got a lot of calls about and/or has an especially vivid memory about? [[User:N0lqu|-boB]] ([[User talk:N0lqu|talk]]) 14:06, 3 October 2018 (UTC)<br />
:: I can provide some anecdotal context, because we (my fiancee and I) still receive this particular type of scam call, to the exclusion of any other type for some reason. Basically, they call and say that they are calling about your car insurance bill and that it's a critical issue. I don't know exactly how it proceeds from there because we don't have a car and well, that's our response to the call. My assumption here is, with Randall iirc living quite near where I live (eastern US), he received much the same call for a long time. [[Special:Contributions/162.158.186.108|162.158.186.108]] 23:55, 3 October 2018 (UTC)<br />
"Rachel" from credit card services deserves her own category. Whenever I have a few minutes to kill, I wait for a "representative" and then keep asking WHICH of my cards he's calling about and torment them with stupid questions until they hang up (or ask for the person in charge of office supplies and try to sell them toner). Also deserving of their own category are the scammers who call about changing my energy supplier and those offering solar panels. To these I usually tell that I like paying higher rates to my electric company, that we have a nuclear reactor in the basement, or that we steal our electricity from our neighbors. - alex<br />
: Honestly the card services scams are particularly toxic because some banks use a very similarly named department to report potentially fraudulent charges and attempt to confirm with you whether or not they were authorized. I have had a few legitimate card services calls in my life. [[Special:Contributions/162.158.186.192|162.158.186.192]] 23:57, 3 October 2018 (UTC)</div>162.158.186.192https://www.explainxkcd.com/wiki/index.php?title=2027:_Lightning_Distance&diff=1631782027: Lightning Distance2018-09-24T15:09:48Z<p>162.158.186.192: /* Explanation */</p>
<hr />
<div>{{comic<br />
| number = 2027<br />
| date = August 1, 2018<br />
| title = Lightning Distance<br />
| image = lightning_distance.png<br />
| titletext = The index of radio refraction does have a lot of variation, which might throw off your calculations, so you can also look at the difference in brightness between the visible flash and more-attenuated UV and x-rays.<br />
}}<br />
<br />
==Explanation==<br />
The usual trick for determining the distance to a {{w|lightning}} flash is to count the seconds from when you see the flash until when you hear {{w|thunder}}, and divide by five to get miles (or three to get kilometers). This works because the {{w|speed of light|transmission of light}} is essentially instantaneous over the relevant distances, while the {{w|speed of sound}} is 331.2 m/s (1,087 ft/s, 1,192 km/h, or 741 mph, varying a bit based on temperature), or about 1/5 mile per second (1/3 kilometer per second).<br />
<br />
This comic subverts the usual trick by having Megan describe a highly impractical alternative method. Megan's method is based on the fact that the speed of electromagnetic radiation, which includes light and radio waves, is not truly fixed and varies by wavelength in a refractive medium.(Consider the classic case of visible light in a prism.) The radiation produced by lightning on Earth also has to travel through air, which changes its speed in a fashion which depends on its frequency.<br />
<br />
According to {{w|List_of_refractive_indices|Wikipedia}} and [https://hypertextbook.com/facts/2005/MayaBarsky.shtml other sources], refractive index of air at 0&deg;C is about 1.000277, which equates to a speed of light around 299709.4 km/s (186230.8 miles/s). According to [https://www.fig.net/resources/proceedings/fig_proceedings/fig_2002/Js28/JS28_rueger.pdf this paper] (table on page 8), refractive index for radio waves in similar conditions is 1.000315, which equates to a speed around 299698.1 km/s (186223.7 miles/s). This means that to get the distance, the time difference in seconds between visible flash and radio burst should be multiplied by about 4.9 billion for miles, or about 7.9 billion for kilometers. More details for the calculations are in the comments below.<br />
<br />
Using a setup similar to that used for [https://hackaday.com/2015/06/05/building-your-own-sdr-based-passive-radar-on-a-shoestring/ passive radar], it would theoretically be possible to use this effect to determine the distance to a source of extremely short bursts of visible light and radio waves. The joke is that it is impractical for people who haven't been exposed to hobby radio engineering, because they can't measure such small time intervals (one nanosecond for every 4.9 miles or 7.9 kilometers of atmosphere) and because they can't detect radiation outside the visible spectrum, without buying an obscure $20 radio dongle.<br />
<br />
Although {{w|Lightning|lightning lasts about 60 to 70 microseconds}}, during which time the signals we receive would rise and fall somewhat erratically, a software-defined radio can sample the phase and strength of the signal in detail during this time and provide a record of it for comparison with a recording at a different frequency. A more expensive radio would make life easier, as a sampling rate of at least a few GHz would allow for the time discrepency to be measured directly using the onset of the signal, rather than inferred from phase differences at different frequencies.<br />
<br />
For the purpose of the joke, the "5 billion" value used in the comic is a fair estimate which also references the original rule of 5 seconds per mile nicely, though the result can have a huge margin of error depending on actual conditions (temperature, humidity, etc.), as the title text suggests ("the index of radio refraction does have a lot of variation").<br />
<br />
Even if lightning was farther away, for example, if we were observing another planet, the time difference still would not be substantial, because the visible and radio waves travel at essential the same speed as each other in the vacuum of space (the difference in speed discussed above applies only to travel through air).<br />
<br />
The title text suggests another method of calculating distance to lightning. Since the absorption of light is also different in different wavelengths, it would be possible to calculate the difference by comparing the brightness instead of delays. This would, however, require the knowledge about prior relative brightness of lightning, i.e. the spectrum, in the compared wavelengths.<br />
<br />
==Transcript==<br />
:[Cueball and Megan stand on either side of a window, observing a bolt of lightning in a dark sky.]<br />
:Cueball: What's that trick for telling how many miles away lightning is?<br />
:Megan: Just count the seconds between the visible flash and the radio wave burst, then multiply by 5 billion.<br />
{{comic discussion}}<br />
<br />
[[Category:Comics featuring Cueball]]<br />
[[Category:Comics featuring Megan]]</div>162.158.186.192https://www.explainxkcd.com/wiki/index.php?title=2048:_Curve-Fitting&diff=1629832048: Curve-Fitting2018-09-20T19:34:28Z<p>162.158.186.192: /* Logarithmic */ Improved notation</p>
<hr />
<div>{{comic<br />
| number = 2048<br />
| date = September 19, 2018<br />
| title = Curve-Fitting<br />
| image = curve_fitting.png<br />
| titletext = Cauchy-Lorentz: "Something alarmingly mathematical is happening, and you should probably pause to Google my name and check what field I originally worked in."<br />
}}<br />
<br />
==Explanation==<br />
{{incomplete|Please edit the explanation below and only mention here why it isn't complete. Do NOT delete this tag too soon.}}<br />
<br />
An illustration of several plots of the same data with curves fitted to the points, paired with conclusions that you might draw about the person who made them. This data, when plotted on an X/Y graph, looks somewhat random and there is a desire or need to determine some kind of pattern. With some kinds of data the pattern can visually obvious, and perhaps a straight or diagonal line, represented by a simple mathematical formula, hits or comes very near hitting all the points. In other cases where it's not as intuitively obvious, one begins to look for more sophisticated mathematical formulas that appear to fit the data, in order to be able to extrapolate other data that wasn't in the initial sampling.<br />
<br />
When modeling such problem statistically, it is common to search for trends, and fitted curves can help reveal these trends. Much of the work of a data scientist or statistician is knowing which fitting method to use for the data in question. Here we see various hypothetical scientists or statisticians each applying their own interpretations, and the comic mocks each of them for their various personal biases or other assorted excuses.<br />
<br />
In general, the researcher will specify the form of an equation for the line to be drawn, and an algorithm will produce the actual line.<br />
<br />
This comic is similar to [[977: Map Projections]] which also uses a scientific method not commonly thought about by the general public to determine specific characteristics of one's personality and approach to science.<br />
<br />
Regressions have been the subject of several previous comics. [[1725: Linear Regression]] was about linear regressions on uncorrelated or poorly correlated data. [[1007: Sustainable]] and [[1204: Detail]] depict linear regressions on data that was actually logistic, leading to bizarre extrapolations. [[605: Extrapolating]] shows a line extrapolating from just two data points.<br />
<br />
===Linear===<br />
<math>f(x) = mx + b</math> <p>Linear regression is the most basic form of regression; it tries to find the straight line that best approximates the data.</p><p>As it's the simplest, most widely taught form of regression, and in general derivable function are locally well approximated by a straight line, it's usually the first and most trivial attempt of fit.</p><br />
===Quadratic===<br />
<math>f(x) = ax^2 + bx + c</math> <p>Quadratic fit (i.e. fitting a parabola through the data) is the lowest grade polynomial that can be used to fit data through a curved line; if the data exhibits clearly "curved" behavior (or if the experimenter feels that its growth should be more than linear), a parabola is often the first stab at fitting the data.</p><br />
===Logarithmic===<br />
<math>f(x) = a\log_b(x) + c</math> <p>A logarithmic curve is typical of a phenomenon whose growth gets slower and slower as time passes (indeed, its derivative - i.e. its growth rate - is <math>\propto \frac{1}{x} \rightarrow 0</math> for <math>x \rightarrow +\infty</math>), but still grows without bound rather than approaching a horizontal asymptote. (If it did approach a horizontal asymptote, then one of the other models subtracted from a constant would probably be better, e.g. <math>f(x) = a - \frac{b}{x}</math> or <math>f(x) = a - b^{-cx}</math>.) If the experimenter wants to find confirmation of this fact, they may try to fit a logarithmic curve.</p><br />
<p>Comment: either you use a or you use the base b of the logarithm, but not both. They are redundant. The model has only two parameters</p><br />
<br />
===Exponential===<br />
<math>f(x) = a*b^x + c</math> <p>An exponential curve, on the contrary, is typical of a phenomenon whose growth gets rapidly faster and faster - a common case is a process that generates stuff that contributes to the process itself, think bacteria growth or compound interest.</p><br />
*The logarithmic and exponential interpretations could very easily be fudged or engineered by a researcher with an agenda (such as by taking a misleading subset or even outright lying about the regression), which the comic mocks by juxtaposing them side-by-side on the same set of data.<br />
===LOESS===<br />
<math>w(x) = (1-|d|^3)^3</math> (notice: this is just the function used for the weights, not the actually fitted curve formula, as it's a piecewise polynomial) <p>A {{w|Local regression|LOESS fit}} doesn't use a single formula to fit all the data, but approximates data points locally using different polynomials for each "zone" (weighting differently data points as they get further from it) and patching them together</p><p>As it has much more degrees of freedom compared to a single polynomial, it generally "fits better" to any data set, although it is generally impossible to derive any strong, "clean" mathematical correlation from it - it is just a nice smooth line that approximates well the data points, with a good degree of rejection from outliers.</p><br />
<br />
===Linear, No Slope===<br />
<math>f(x) = c</math> <p>Apparently, the person making this line figured out pretty early on that their data analysis was turning into a scatter plot, and wanted to escape their personal stigma of scatter plots by drawing an obviously false regression line on top of it. Alternatively, they were hoping the data would be flat, and are trying to pretend that there's no real trend to the data by drawing a horizontal trend line.</p><br />
===Logistic===<br />
<math>f(x) = L / (1 + e^{-k(x-b)})</math> <p>A logistic curve provides a smooth, S-shaped transition curve between two flat intervals; indeed the caption says that the experimenter just wants to find a mathematically-respectable way to link two flat lines.</p><br />
===Confidence Interval===<br />
Not a type of curve fitting, but a method of depicting the predictive power of a curve. <p>Providing a confidence interval over the graph shows the uncertainty of the acquired data, thus acknowledging the uncertain results of the experiment, and showing the will not to "cheat" with "easy" regression curves.</p><br />
===Piecewise===<br />
Mapping different curves to different segments of the data. This is a legitimate strategy, but the different segments should be meaningful, such as if they were pulled from different populations.<br />
<br />
This kind of fit would arise naturally in a study based on a regression discontinuity design. For instance, if students who score below a certain cutoff must take remedial classes, the line for outcomes of those below the cutoff would reasonably be separate from the one for outcomes above the cutoff; the distance between the end of the two lines could be considered the effect of the treatment, under certain assumptions. This kind of study design is used to investigate causal theories, where mere correlation in observational data is not enough to prove anything. Thus, the associated text would be appropriate; �there is a theory, and data that might prove the theory is hard to find.<br />
===Connecting lines===<br />
Not useful whatsoever, but it looks nice!<br />
It can be caused by overfitting to the data set or not using curve-fitting tools correctly.<br />
===Ad-Hoc Filter===<br />
Drawing a bunch of different lines by hand, keeping in only the data points perceived as "good". Also not useful.<br />
===House of Cards===<br />
Not a real method, but a common consequence of mis-application of statistical methods: a curve can be generated that fits the data extremely well, but immediately becomes absurd as soon as one glances outside the training data sample range, and your analysis comes crashing down "like a house of cards". This is a type of ''overfitting''. In other words, the model may do quite well for (approximately) {{w|Interpolation|interpolating}} between values in the sample range, but not extend at all well to {{w|Extrapolation|extrapolating}} values outside that range.<br />
''Note:'' Exact polynomial fitting, a fit which gives the unique (n-1)-th degree polynomial through n points, often display this kind of behaviour. Also a potential reference to the TV show, House of Cards ("WAIT NO, NO, DON'T EXTEND IT!").<br />
<br />
===Cauchy-Lorentz===<br />
{{w|Cauchy_distribution|Cauchy-Lorentz}} is a continuous probability distribution which does not have an expected value or a defined variance. This means that the law of large numbers does not hold and that estimating e.g. the sample mean will diverge (be all over the place) the more data points you have. Hence very troublesome (mathematically alarming). <br />
<br />
Since so many different models can fit this data set at first glance, Randall may be making a point about how if a data set is sufficiently messy, you can read any trend you want into it, and the trend that is chosen may say more about the researcher than about the data. This is a similar sentiment to [[1725: Linear Regression]], which also pokes fun at dubious trend lines on scatterplots.<br />
<br />
==Transcript==<br />
{{incomplete transcript|Do NOT delete this tag too soon.}}<br />
:'''Curve-Fitting Methods'''<br />
:and the messages they send<br />
<br />
:[In a single frame twelve scatter plots with unlabeled x- and y-axes are shown. Each plot consists of the same data-set of approximately thirty points located all over the plot but slightly more distributed around the diagonal. Every plot shows in red a different fitting method which is labeled on top in gray.]<br />
<br />
:[The first plot shows a line starting at the left bottom above the x-axis rising towards the points to the right.]<br />
:Linear<br />
:"Hey, I did a regression."<br />
<br />
:[The second plot shows a curve falling slightly down and then rising up to the right.]<br />
:Quadratic<br />
:"I wanted a curved line, so I made one with Math."<br />
<br />
:[At the third plot the curve starts near the left bottom and increases more and more less to the right.]<br />
:Logarithmic<br />
:"Look, it's tapering off!"<br />
<br />
:[The fourth plot shows a curve starting near the left bottom and increases more and more steeper towards the right.]<br />
:Exponential<br />
:"Look, it's growing uncontrollably!"<br />
<br />
:[The fifth plot uses a fitting to match many points. It starts at the left bottom, increases, then decreases, then rapidly increasing again, and finally reaching a plateau.]<br />
:LOESS<br />
:"I'm sophisticated, not like those bumbling polynomial people."<br />
<br />
:[The sixth plot simply shows a line above but parallel to the x-axis.]<br />
:Linear, no slope<br />
:"I'm making a scatter plot but I don't want to."<br />
<br />
:[At plot #7 starts at a plateau above the x-axis, then increases, and finally reaches a higher plateau.]<br />
:Logistic<br />
:"I need to connect these two lines, but my first idea didn't have enough Math."<br />
<br />
:[Plot #8 shows two red lines embedding most points and the area between is painted as a red shadow.]<br />
:Confidence interval<br />
:"Listen, science is hard. But I'm a serious person doing my best."<br />
<br />
:[Plot #9 shows two not connected lines, one at the lower left half, and one higher at the right. Both have smaller curved lines in light red above and below.]<br />
:Piecewise<br />
:"I have a theory, and this is the only data I could find."<br />
<br />
:[The plot at the left bottom shows a line connecting all points from left to right, resulting in a curve going many times up and down.]<br />
:Connecting lines<br />
:"I clicked 'Smooth Lines' in Excel."<br />
<br />
:[The next to last plot shows a echelon form, connecting a few real and some imaginary points.]<br />
:Ad-Hoc filter<br />
:"I had an idea for how to clean up the data. What do you think?"<br />
<br />
:[The last plot shows a wave with increasing peak values.]<br />
:House of Cards<br />
:"As you can see, this model smoothly fits the- ''wait no no don't extend it AAAAAA!!''"<br />
<br />
<br />
==Trivia==<br />
This is the comic 2048, or 2^11. In addition to being the name of a popular app referenced in [[1344: Digits]], this is an extremely round number in binary (100,000,000,000). [[1000: 1000 Comics]] pointed out that comic 1024 would be a round number, but there were not any comics noting 2048.<br />
<br />
<br />
{{comic discussion}}<br />
<br />
[[Category:Comics with color]]<br />
[[Category:Scatter plots]]<br />
[[Category:Math]]<br />
[[Category:Science]]</div>162.158.186.192