explain xkcd - User contributions [en]

1347: t Distribution

2014-04-02T17:23:15Z

Idrhtsft: /* Explanation */ uncap

{{comic
| number = 1347
| date = March 26, 2014
| title = t Distribution
| image = t_distribution.png
| titletext = If data fails the Teacher's t test, you can just force it to take the test again until it passes.
}}

==Explanation==
{{incomplete|Please don't remove this tag until language issues are solved. This is international, not only U.S.}}
The {{w|Student's t-distribution}} is a class of {{w|probability distribution}} used in statistics to model small sample sizes. "Student" was the pseudonym of {{w|William Gosset}}, an employee of Guinness Brewery who discovered it.

A Student's t distribution is similar to a normal symmetric bell curve distribution, but has "fatter tails"; thus, the one shown in the comic is roughly the right shape. A "Teacher's" t-distribution is a joke (pun) made up by Randall.

The comic is a play on the name "Student", the pseudonym of the creator versus the "Teacher". The idea is that a "teacher's" distribution would be more complex, and that it would be used for fitting data when the student's distribution wasn't sophisticated enough. Of course, in actuality, such a complex distribution as the one shown in the comic would have many parameters, and in practice would probably lead to overfitting and/or bias. Thus, the comic (and the title text) can be seen as making fun of the idea that more complex is always better, or perhaps of the idea that a statistician's job is to use more and more sophisticated tools to force the data to yield a "publishable" result, rather than to use the simplest appropriate tool and let the chips fall where they may.

[[Cueball]] tries to "fit" a distribution to the data on the paper. This is the usual jargon for when a statistician is trying to model his/her data as coming from some underlying probability distribution, and the comic makes a pun with the physical meaning of "fit". In the second panel, Cueball decides that the Student's T distribution does not fit his data well (the data failed the Student t-test), and decides to pull out the more complex Teachers t-distribution instead (the teachers t-test - which the data is not allowed to continue to fail). Note that "test" is what statisticians do to data to see if it fits some distribution, but it is also, in American English, another word for "examination."

The Students t distribution relates the average of a small sample to the "true" population average (under the assumptions, unobjectionable in many contexts, that there is such a "true" value, and that the samples are independent and normally distributed with equal variance). As such, unless the data on Cueball's paper contain many small groups which radically violate these assumptions somehow, there is no way Cueball's data could falsify the t distribution. In particular, a single number (for the average of one group) or a small set of numbers (for the averages of several numbers) will never make a nice smooth curve, but an average statistician would see that as normal statistical noise that would even out over time, not as a reason to prefer a complex, spiky curve such as the supposed "teacher's" distribution. But of course, Cueball's access to a secret, cooler-looking distribution makes them more badass than a mere average statistician... or does it?

Ironically, the Teacher's T Distribution shows equal variance, itself proving the appropriateness of the Student's T Distribution.

The title text plays on the word "test". The first part of the sentence refers to a potential "Teacher t-test" which would be used in a statistical context to test for the significance of some observation, as opposed to the real "Student's t-test" which is used to determine if two sets of data differ by a statistically significant amount. On the other hand, the second part of the sentence refers to the possibility for students to take tests (or exams) until they pass - or to teachers who forces students to take the test again and again until they pass. The resulting sentence may refer to statistical fallacy, or the (conscious or unconscious) action of manipulating observations or misconducting experiments to give statistical significance to a false fact.

==Transcript==
:[A physical bell-curve-shaped object labeled "Student's t distribution" is resting on a table. Cueball is working with it and a piece of paper.]
:Cueball: hmm
:[Cueball looks at the piece of paper.]
:Cueball: ...nope.
:[Cueball picks up the object and begins to walk off the panel with it.]
:[Cueball comes back onto the panel, now carrying an object shaped like a much more complex curve, with many symmetric spikes and dips, labeled "Teacher's t distribution".]

{{comic discussion}}

[[Category:Comics featuring Cueball]]

1347: t Distribution

2014-04-02T17:22:27Z

Idrhtsft: /* Explanation */ cap

{{comic
| number = 1347
| date = March 26, 2014
| title = t Distribution
| image = t_distribution.png
| titletext = If data fails the Teacher's t test, you can just force it to take the test again until it passes.
}}

==Explanation==
{{incomplete|Please don't remove this tag until language issues are solved. This is international, not only U.S.}}
The {{w|Student's t-distribution}} is a class of {{w|probability distribution}} used in statistics to model small sample sizes. "Student" was the pseudonym of {{w|William Gosset}}, an employee of Guinness Brewery who discovered it.

A Student's t distribution is similar to a normal symmetric bell curve distribution, but has "fatter tails"; thus, the one shown in the comic is roughly the right shape. A "Teacher's" t-distribution is a joke (pun) made up by Randall.

The comic is a play on the name "Student", the pseudonym of the creator versus the "Teacher". The idea is that a "teacher's" distribution would be more complex, and that it would be used for fitting data when the student's distribution wasn't sophisticated enough. Of course, in actuality, such a complex distribution as the one shown in the comic would have many parameters, and in practice would probably lead to overfitting and/or bias. Thus, the comic (and the title text) can be seen as making fun of the idea that more complex is always better, or perhaps of the idea that a statistician's job is to use more and more sophisticated tools to force the data to yield a "publishable" result, rather than to use the simplest appropriate tool and let the chips fall where they may.

[[Cueball]] tries to "fit" a distribution to the data on the paper. This is the usual jargon for when a statistician is trying to model his/her data as coming from some underlying probability distribution, and the comic makes a pun with the physical meaning of "fit". In the second panel, Cueball decides that the Student's T distribution does not fit his data well (the data failed the Student t-test), and decides to pull out the more complex Teachers t-distribution instead (the teachers t-test - which the data is not allowed to continue to fail). Note that "test" is what statisticians do to data to see if it fits some distribution, but it is also, in American English, another word for "examination."

The Students T distribution relates the average of a small sample to the "true" population average (under the assumptions, unobjectionable in many contexts, that there is such a "true" value, and that the samples are independent and normally distributed with equal variance). As such, unless the data on Cueball's paper contain many small groups which radically violate these assumptions somehow, there is no way Cueball's data could falsify the t distribution. In particular, a single number (for the average of one group) or a small set of numbers (for the averages of several numbers) will never make a nice smooth curve, but an average statistician would see that as normal statistical noise that would even out over time, not as a reason to prefer a complex, spiky curve such as the supposed "teacher's" distribution. But of course, Cueball's access to a secret, cooler-looking distribution makes them more badass than a mere average statistician... or does it?

Ironically, the Teacher's T Distribution shows equal variance, itself proving the appropriateness of the Student's T Distribution.

The title text plays on the word "test". The first part of the sentence refers to a potential "Teacher t-test" which would be used in a statistical context to test for the significance of some observation, as opposed to the real "Student's t-test" which is used to determine if two sets of data differ by a statistically significant amount. On the other hand, the second part of the sentence refers to the possibility for students to take tests (or exams) until they pass - or to teachers who forces students to take the test again and again until they pass. The resulting sentence may refer to statistical fallacy, or the (conscious or unconscious) action of manipulating observations or misconducting experiments to give statistical significance to a false fact.

==Transcript==
:[A physical bell-curve-shaped object labeled "Student's t distribution" is resting on a table. Cueball is working with it and a piece of paper.]
:Cueball: hmm
:[Cueball looks at the piece of paper.]
:Cueball: ...nope.
:[Cueball picks up the object and begins to walk off the panel with it.]
:[Cueball comes back onto the panel, now carrying an object shaped like a much more complex curve, with many symmetric spikes and dips, labeled "Teacher's t distribution".]

{{comic discussion}}

[[Category:Comics featuring Cueball]]

1337: Hack

2014-03-06T14:14:51Z

Idrhtsft: /* Truth & Fiction Explained */ minor copyedit

{{comic
| number = 1337
| date = March 3, 2014
| title = Hack
| image = hack.png
| titletext = HACK THE STARS
}}
<noinclude>:''"1337", this comic's number, redirects here. For the 2007 storyline of the same name, starting with [[341|comic 341]], see [[:Category:1337]].''</noinclude>

==Explanation==
The probe {{w|International Cometary Explorer|ISEE-3/ICE}} is a spacecraft launched on August 12, 1978. The original mission was to study the interaction between the Earth's magnetic field and the solar wind. It was later sent to visit Comet {{w|21P/Giacobini–Zinner|Giacobini-Zinner}} and became the first spacecraft to do so by flying through a comet's tail.

Its trajectory will bring it close to Earth on August 2014. A status check of the spacecraft has revealed that many of its instruments are still working and that it contains plenty of fuel. But the hardware to communicate with ISEE-3/ICE has been decommissioned, and it will be expensive to reestablish the communication needed to use the spacecraft for another mission.

The characters Crash and Burn (and the catchphrase, "Mess with the best, die like the rest") are an allusion to the 1995 movie [[wikipedia:Hackers (film)|Hackers]]. Since the movie predates the shutdown-signal (1997), the characters should both possess the skills and 'outdated' equipment to understand and hack the signal to the probe.

In the comic, Burn has hacked into the satellite and left the catchphrase to be shown to those who would log into the satellite regularly. She has also rerouted its path to enter the atmosphere at a certain time. She then uses this knowledge to tell Crash in advance at just the right time that a "falling star" will appear in the sky.

The title text "Hack the stars" is also an allusion to the movie [[wikipedia:Hackers (film)|Hackers]] where the Phrase "Hack the Planet!" is used on multiple occasions.

In the Hackers movie, the rivalry between the characters Crash and Burn was to "one up" the other by means of hacking as a measure of how good their skills were. The "falling star" could be the ultimate measure of hacking "leet-ness".

Not coincidentally, this is comic number 1337, which in {{w|leet speak}} means ''elite'' (elite hacking, in this case).

===Truth & Fiction Explained===
This comic involves some truth and some fiction. There is an {{w|International Cometary Explorer|ISEE-3/ICE}} probe. According to the Wikipedia article, it was launched in August 12, 1978 and tasked to study Earth's magnetic field and the solar wind. After completing its original mission the probe was repurposed on June 10, 1982 to study the interaction between the solar wind and a cometary atmosphere. This put it in a {{w|heliocentric orbit}}. According to an article by [http://www.planetary.org/blogs/emily-lakdawalla/2014/02070836-isee-3.html Emily Lakdawalla] at Planetary.org, the Deep Space Network (DSN) detected the probe again in 2008 because NASA mistakenly left its transmitters on. The probe is now catching up to Earth, and people on earth can hear its transmissions (and presumably decode them), but the technology that would allow NASA to send commands back to the probe no longer exists, and would be prohibitively expensive to build. The DSN is required because "no other network of antennas in the US has the sensitivity to detect and transmit signals to the spacecraft at such a distance".

From this [http://deepspace.jpl.nasa.gov/dsndocs/810-005/101/101E.pdf this NASA JPL paper], the Madrid DSS complex still has the special filter required to communicate with the ICE satellite, but because of frequency conflicts S-band uplink is not supported.

It is unknown if any other person or organisation possesses the transmitter technology required to send commands to the spacecraft at this time. If someone were able to hack into the Madrid facility, it's still unlikely that a clear signal would be able to reach the satellite due to interference from other S-band signals.

(With some help from a page at [http://www.unmannedspaceflight.com/lofiversion/index.php/t3800.html UnmannedSpaceFlight.com].)

==Transcript==
:[Panel 1 shows an image of the ISEE-3/ICE spacecraft]
:Narration: The ISEE-3/ICE probe was launched in 1978. Its mission ended in 1997 and it was sent a shutdown signal.
:Narration: In 2008, we learned-to our surprise-that the probe didn't shut down. It's still running and it has plenty of fuel. ...and in 2014, its orbit brings it near earth.
:[Panel 3 shows Megan and Ponytail talking to each other.]
:Megan: We could send it on a new mission... Except we no longer have the equipment to send commands to it.
:Ponytail: Can't we...
:Megan: NASA won't rebuild it. "Too Expensive"
:Ponytail: Seriously?
:Megan: I know, right? So the Internet found the specs and we went to work.
:[Panel 5 shows Megan and Ponytail have walking into an area where a girl and Cueball both are sitting at desks looking at laptops.]
:Narration: We've convinced them to give us time on the Madrid DSN transmitter and hacked the maser to support the uplink. And today's the big day.
:Cueball: Transmitting... We have a signal! We have control!
:Megan: OK, transmit the new comet rendezvous maneuver sequen-
:[Cueball, off panel]: What the hell?
:Megan: What?
:Cueball: My console went dead!
:Girl: Mine too!
:Megan: What's happening?!
:Cueball: There's a new signal going out over the transmitter!
:[Megan, off panel]: A bug?
:Cueball: Someone else is in the system!
:Girl: Kill the connection!
:[Cueball, off panel]: I can't find it!
:Girl: They're firing the probe's engines!
:[Cueball, off panel]: NO!
:[Megan, off panel]: Who's doing this?? Stop them!
:[Girl, off panel]: I'm trying!
:Cueball, pointing to his screen: Look! My screen!
:[Text, on Cueball's laptop screen]: M-E-S-S-W-I-T-H-T-H-E-B-E-S-T D-I-E-L-I-K-E-T-H-E-R-E-S-T
:[Panel 13 shows two people in a pool at night.]
:[Panel 14 zooms out to reveal the pool is on top of a skyscraper in a vertically developed, downtown setting.]
:Burn: Crash?
:Crash: Yeah, Burn?
:Burn: Make a wish.
:[Panel 16 shows the spacecraft streaking across the sky, indistinguishable from a meteoroid.]

==Trivia==
*There are several pools in the movie as well. There is a subplot involving a mythical pool on the roof of the high school where several of the characters are students. Additionally, a scene in the movie [http://www.youtube.com/watch?v=dcHBsB0igrg Hackers ending] shows Crash and Burn swimming in a rooftop pool, while several buildings light up with the words "CRASH AND BURN", the result of their friends' latest hack. This scene is similar to the last four panels of the comic.
*The number of the comic is also significant, in that [[:Category:1337|1337]] is a common numeric form of {{w|leet}}, again referring to hackers.

{{comic discussion}}

[[Category:Comics with color]]
[[Category:Comics featuring Ponytail]]
[[Category:Comics featuring Megan]]
[[Category:Comics featuring Cueball]]