Que sera sera

Statisticians love to develop multiple ways of testing the same thing. If I want to decide whether two groups of people have significantly different IQs, I can run a t-test or a rank sum test or a bootstrap or a regression. You can argue about which of these is most appropriate, but I basically think that if the effect is really statistically significant and large enough to matter, it should emerge regardless of which test you use, as long as the test is reasonable and your sample isn’t tiny. An effect that appears when you use a parametric test but not a nonparametric test is probably not worth writing home about [2].
A similar lesson applies, I think, to first dates. When you’re attracted to someone, you overanalyze everything you say, spend extra time trying to look attractive, etc. But if your mutual attraction is really statistically significant and large enough to matter, it should emerge regardless of the exact circumstances of a single evening. If the shirt you wear can fundamentally alter whether someone is attracted to you, you probably shouldn’t be life partners.

A statistician argues you shouldn't be nervous on a first date. This sounds like math for “if it's meant to be, it will happen.”


Interview with Arthur Chu, famous now for studying Jeopardy carefully and developing a strategy to optimize his chances to win. Some are criticizing his playing style, accusing him of hacking the system, but isn't that how one should try to play every game? Learn the rules and develop the optimal strategy?

I noticed some interesting things. Everyone's talking about my strategy on the show, it seems, but I didn't make anything up—I just read people's observations online. In 1985, the second year of the Alex Trebek version of the show, this guy Chuck Forrest really dominated by bouncing around the categories, and they call it the "Forrest Bounce." There's no logical reason to do what people normally do, which is to take one category at a time from the top down. Your only point of control in the game is your ability, if you get the right answer to a question, to select the next question—and you give that power up if you make yourself predictable. The more unpredictable you are, the more you put your opponents off-balance, the longer you can keep an initial advantage. Multiple people over the years have used [the Forrest Bounce] and yet most people haven't used it. When they programmed the computer Watson to maximize its chances of winning, it did the Forrest Bounce. And it specifically did Daily Double hunting. Watson knew that the bottom two rows of the Jeopardy! board are more likely to contain Daily Doubles, and it knew that whoever gets the most Daily Doubles is the most likely to win the game—that's just statistical analysis. So it was programmed to hunt those Daily Doubles, and I figured I had no reason not to do that.

Another excerpt of interest:

There are a few specific composers they want [you] to know. If they mention "a Norwegian composer"—this happened in a game, I think the Wednesday game—it will be Edvard Grieg. That's the method they use to write the clue. If they mention a "Polish Nobel Prize Winner," it's likely to be Marie Curie. If they mention a "Female Nobel Prize Winner," it's very likely to be Marie Curie. Jeopardy! is aimed at the sort of average TV viewer, so they're not going to ask things that are pointlessly obscure, they're not going to go in-depth on any particular subject, they're going to focus on these cultural touchstones that we all know.And if you watch the show, and you can identify those, you can literally make flashcards.

So I used a program called Anki which uses a method called "spaced repetition." It keeps track of where you're doing well or poorly, and pushes you to study the flashcards you don't know as well, until you develop an even knowledge base about a particular subject, and I just made flashcards for those specific things. I memorized all the world capitals, it wasn't that hard once I had the flashcards and was using them every day. I memorized the US State Nicknames (they're on Wikipedia), memorized the basic important facts about the 44 US Presidents. I really focused on those. But there's a lot more stuff to know. I went onJeopardy! knowing that there was stuff I didn't know. For instance, everyone laughs about sports—but I also knew that [sports clues] were the least likely to come up in Double Jeopardy and Final Jeopardy and be very important. So I decided I shouldn't sweat it too much, I should just recognize that I didn't know them and let that go, as long as I can get the high value clues.


Gamifying world news instruction. Though gamification has some negative connotations thanks to many mobile games and online dark patterns of UI design, so perhaps we should refer to this as some variant of a nudge?


The guy who hacked OkCupid to find love.

But mathematically, McKinlay’s compatibility with women in Los Angeles was abysmal. OkCupid’s algorithms use only the questions that both potential matches decide to answer, and the match questions McKinlay had chosen—more or less at random—had proven unpopular. When he scrolled through his matches, fewer than 100 women would appear above the 90 percent compatibility mark. And that was in a city containing some 2 million women (approximately 80,000 of them on OkCupid). On a site where compatibility equals visibility, he was practically a ghost.

He realized he’d have to boost that number. If, through statistical sampling, McKinlay could ascertain which questions mattered to the kind of women he liked, he could construct a new profile that honestly answered those questions and ignored the rest. He could match every woman in LA who might be right for him, and none that weren’t.

I expected the article to be about how his complex hacking led quickly to the perfect woman, but what's surprising (or depressing, depending on how much faith you put in market efficiency) is how much work he had to go through even after his complex data mining surfaced a candidate list.

Far easier, I suppose, if you are able to nail the three rules mentioned in the old Tom Brady sexual harassment sketch on Saturday Night Live:

  1. Be Handsome.
  2. Be Attractive.
  3. Don't Be Unattractive.

I don't envy the best man at McKinlay's wedding, having to recount the story of how the couple met.