Editing 2370: Prediction

This comic is about misunderstanding {{w|probability}}. Sometimes people will incorrectly assume that if two events are possible, and one of them is more likely than the other to occur, then the first event WILL occur; or, that if one names two or more outcomes they are equally likely to occur when in fact they might have different probabilities.

Saying that one event is more likely to happen than another is not the same as saying that the first event is definitely going to happen. A statement like "event A has a 70% probability of happening" sometimes misleads people into believing that event A is inevitable, while in fact 3 times out of 10 event A will not happen.

Some don't like probability statements because they are not definite and therefore cannot be proven wrong. For example, if a probability statement says "event A has a 1% probability of happening" and event A actually happens, that does not prove the statement wrong, because the statement admits of the possibility of event A happening.

For example, FiveThirtyEight [https://projects.fivethirtyeight.com/2016-election-forecast/ famously gave Trump a higher odds, 28.6%] of winning the 2016 U.S. presidential election than most other models did just before the election, but still not more likely than his opponent. However, many readers at the time interpreted that as "Trump is definitely going to lose", and after he won that election, blasted FiveThirtyEight for getting its prediction "wrong". However, that interpretation is mistaken. 28.6% means Trump had a real chance at winning: if you could put election results in a hat and draw them at random, he would win two out of every seven tries. For another example, in tabletop gaming terms, Trump's likelihood of winning was slightly lower than that of passing a flat check with a DC of 15 (6/20 or 30%).

The correct interpretation of a probability statement like "event A has a 70% probability to happen" is that in the long run, about 70% of events with this probability end up happening. If, for example, 99% of those events ended up happening, the 70% probabilities you gave those events may likely be wrong (you should've given probabilities closer to 99%), even though you "called" almost all events correctly (in the sense that 70% means the events are more likely to happen than not to happen, and almost all of them happened). Looking back at your predictions and seeing if the results are what you should expect is called {{w|Calibration (statistics)|calibration}} ([https://projects.fivethirtyeight.com/checking-our-work/ example]).

The title text says that these people are gullible enough to the point that they would accept a disadvantageous bet. However, it also says that the probability that they might not actually go through with paying the bet if they lose brings into question whether to propose the bet is actually worth it. Randall has previously made allusions to betting on fallaciously claimed probabilities in comics such as [[1132: Frequentists vs. Bayesians]] and [[955: Neutrinos]].

 

The comic doesn't rule out the possibility that event A and event B aren't directly related. For example, it is more likely to flip a coin and get a head than to roll a 6-sided die and get a 6. This is a fairly pointless observation in most cases, except perhaps if one is trying to explain the probability of an unfamiliar event by comparison with something very familiar.

At the time of writing, the 2020 United States presidential and congressional elections are less than a month away. This is a time when polls showing one or the other candidate leading are common, and may be misinterpreted to mean that the candidate is certain to win. Additionally, after the 2016 election saw Donald Trump, the trailing candidate in the polls, winning, many also interpreted this to mean that the polls were useless and/or wrong, or even go beyond this and take an adverse poll prediction as a perversely authoritative indication that the exact opposite result (which they would favour) is now a certainty. Cueball has previously shown an interest in U.S. election polling, for example in [[500: Election]].

In early October, famous statistician [[Nate Silver]] explained on his podcast "Model Talk" that, according to his model, Donald Trump had a 17% chance of winning reelection in 2020. That seems low, but it's a one in six chance, the odds of Russian roulette, the practice of shooting oneself in the head with a six-bullet barreled pistol with only one chamber loaded: it only has one chance in six to kill the person doing it. Would anyone in their right mind play Russian roulette? The answer he was implying was no. This illustrates how one chance in six is very real. While 17% seems low, it can absolutely happen.