Monday, October 19, 2015

A Statistical Argument for Not Being Nervous on First Dates


A few months ago I became single for the first time in four years. I went from studying online dating to being a datapoint myself [1]. This has made me think more urgently about questions I once considered only abstractly. Today I write about the connection between testing statistical hypotheses and testing romantic attraction.


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.


You can argue against this by pointing out cases where a tiny detail does matter because it prevents you from having any future interactions: for example, you foolishly wear your XL Chess Team sweatshirt to the bar and your would be Lothario never bothers to approach you and thereby discover that you look much better with it off.


This is a risk. In statistical terms, a glance at across a bar doesn’t give you a lot of data and increases the probability you’ll make an incorrect decision. As a statistician, I prefer not to work with small datasets, and similarly, I’ve never liked romantic environments that give me very little data about a person. (Don’t get me started on Tinder. The only thing I can think when I see some stranger staring at me out of a phone is, “My errorbars are huge!” which makes it very hard to assess attraction.)

Even on a longer date, there’s some risk that a disaster at the beginning will ruin your subsequent interactions. If you start by asking “how’s your relationship with your mother?”, you’ve torpedoed your chance to have a truly intimate conversation about how she ran off to train monkeys.


Still, I’m sticking to the principle that if your romance-to-be is statistically robust, whether you wear makeup or the moon is full should make no more difference than whether you compute the Spearman or Pearson correlation. (And if your date asks you if you want to bootstrap, the answer is always, of course, yes.)


I think there’s even an argument for being deliberately unattractive to your date, on the grounds that if they still like you, they must really like you. Imagine a cliched rom-com disaster [3]: you vomit on your date. This isn’t sexy. On the other hand, someone who finds you attractive after that is much more likely to still find you attractive when you’re puking during pregnancy or chemotherapy [4]. This is somewhat analogous to using a statistical test that makes very weak assumptions (here's one example): if the test yields positive results, you can have high confidence they're real.


Please don’t send me angry emails when you take this post too seriously and the love of your life spurns you because you didn’t shower for a week before your date. But I’d welcome your thoughts in the comments or via email. (Also hit me up if you have ideas for statistical projects that I can only conduct while single.)


Notes:
[1] I recently received an email from a Stanford professor in a similar situation: his marriage broke up after 20 years, and he responded by writing a book about the connections between economics and dating.
[2] An economics friend points out a corollary to this principle: be suspicious of analyses that use really convoluted tests when it seems like simple ones should do, because that might indicate that the simple ones didn’t produce the results they’re reporting.
[3] 10 Things I Hate About You, 50 Shades of Grey, Mean Girls. What’s with this trope, and why are the pukers always female?
[4] You’re calling me crazy and I’m kind of kidding, but I’d also argue that the idea of testing one’s partner is a socially accepted one. (My scholarly attempt to do a lit review on this question -- I Googled “make them work for it” -- yielded this text. You’re welcome.) There are many bad reasons people are told to defer sleeping with someone, but a not-so-bad-one, from a probabilistic standpoint, is that someone who will wait might be more likely to really like you.



16 comments:

  1. My philosophy in my 20s was similar to Bertrand Russell's advice on happiness which is to be open to as many pleasures (people) as possible. (1) Not exactly knowing what kind of guy I wanted to be with, I covered all my bases. I exercised to have a nice body and good posture, drank lots of water and ate well for a nice complexion, varied my interests from literature to science to athletics to travel, increased my social skills, made sure I was employable and saved a lot of money. I won the lottery finding my spouse so it is hard to separate my luck from the implementation of my philosophy. In my 20s I met a lot of interesting people but also gained a lot of great habits that make my life healthy, interesting, and with low-stress in my 30s. Finding the ideal life partner is so impactful on the quality of ones life, I really recommend doing everything one can to increase the probability of finding a good mate. Dating a lot (and hearing about the dating experiences of your friends) will give one enough intuition so that one can shower as much as they want!

    (1) "Suppose one man likes strawberries and another does not; in what respect is the latter superior? There is no abstract and impersonal proof either that strawberries are good or that they are not good. To the man who likes them they are good, to the man who dislikes them they are not. But the man who likes them has a pleasure which the other does not have; to that extent his life is more enjoyable and he is better adapted to the world in which both must live."

    ReplyDelete
    Replies
    1. Great quote, and great advice (probably considerably more sensible than anything in my original post).

      Delete
  2. Very nice ! I won't advice puking or farting on any first dates .😂😂😂. I must add to be ones self on a first date.. I would rather we don't get along or don't earlier .. Than to pretend and break up weeks later

    ReplyDelete
    Replies
    1. Agreed. I think that "be oneself" is probably better advice than "deliberately be unattractive". It's one thing to dress as you normally would. It's another thing to deliberately dress sloppily.

      Delete
  3. Who pukes is statistically insignificant to the importance of how a date reacts: was on a first date at a restaurant I frequented, holding the restaurant owner's small daughter on my lap, when without warning said daughter puked all over my pants. Fortunately - weirdly - I happened to have a change of clothes in the car. My date was super impressed that I didn't get mad at the little girl and generally handled the situation with aplomb. However, I'd also note that there is a fine like between dating as you are and dating like you don't care how things work out. Perhaps it is the unspoken definition of how to manage that line that the more come-as-you-are approach has in its favor.

    ReplyDelete
    Replies
    1. Hahaha, that's great. And I agree that dating "like you don't care how things work out" runs the risk of signaling a lack of interest -- see my response to the commenter below.

      Delete
  4. Dear Emma,

    It's all about power.

    A first date is a *mutual* test. Your excellent tests lower the probability of your committing a type-II error (H0: The guy is a douchebag), but you don't know his statistical skills.

    Suppose you go on a first date with a high-quality Muggle. You're into him. But unlike high-power statisticians like youself, Muggles' type-II errors are huge. Your frumpy t-shirt might produce a low t-stat, and thus dissuade him from going on a second date, despite being attracted to you if only he could see through, ahem, your bad t-shirt. His low-power testing strategy is getting in the way of a happy relationship.

    Maybe that's the whole point. Maybe you would never date a person with a poor filter. But unless you have Leontief preferences, I bet you'd be willing to date a guy with poor statistical skills, but who is excellent in many other ways.

    And this, I think, is one reason why we conform to certain norms, whether on a first date or a job interview: Because *they* might use a *low-power* test.

    ReplyDelete
    Replies
    1. I'm sorry, you lost me at "I'd bet you'd be willing to date a guy with poor statistical skills".

      Delete
    2. More seriously, your point is well-taken. It's also not even clear that a person who infers from a frumpy t-shirt that you're not worth dating is making a poor statistical decision. Your decision to wear that t-shirt may indicate a lack of interest in him. As the commenter above points out, "dating like you don't care how things work out" may send the wrong signal even to people who you might be interested in.

      Delete
  5. The strength of one's relationships with all the nodes of the ego net is often claimed to be hierarchical in nature, and certainly obeys a radical inequality (fat tail). Dunbar claims that his hierarchical model of relation (where theory-of-mind can hold for 150 people, going down to a group of ~25 friends and 5 friends who you can really confide in, from the linear regression on brain volume) is modified so that one significant other replaces 2 friends for confiding in.

    I think Lekovec goes over this in cs224w? I never paid attention in that class very much.

    Anyhow, fat tails on a distribution are a possible hint of strange dynamical shenanigans that can go on (a hint, mind you: many claimed power law processes might just be, say, an exponential process with uneven sampling or lognormal or whatever, which might have perfectly normal explanations and things), which bring the importance of contingency into them, because lots of spectra of interest from signals of interest from chaotic (not speaking of chaos in a mushy way here: I mean SDIC, Lyapunov exponent >0, etc etc) systems are power law spectra. Sufficient but not necessary. Moreover, it hints of worlds where central limit theorems and suchlike get drowned in correlational structure.

    You can tell a lot of the same stories in the info theory of dynamical systems as many people tell in love: this was what drew the Losada group et al. into thinking about it. They were really not good enough at math to do anything with it, but it's interesting to think about.

    Also of interest are the paradox of enrichment and the paradox of the pesticides, which are both statements on the _reactive_ nature of ecological systems, and compare them to what R. Cialdini the influence man calls the "romeo and juliet effect", where parental pressure to avoid a relationship in a teenage couple induces a stronger relationship.

    ReplyDelete
  6. This article is great, thanks! I really enjoyed it :)

    ReplyDelete
  7. You can't smell a potential partner on your phone. Meet first. Then, because you inhaled, you'll be able to be attracted. The pic only lets you intellectualize yourself into a non-evolutionary situation.

    Love at first sight was always love at first smell.

    ReplyDelete
  8. I'm not a stats type of guy but I do enjoy the discussions they often spawn and this is an interesting one for me. I'm a counselor/therapist and have always been interested in dating statistics. The only one I've use is a simple one...the more you date the closer you get to finding the right one. The less you date the further from finding the right one.

    ReplyDelete
  9. I'm not a stats type of guy but I do enjoy the discussions they often spawn and this is an interesting one for me. I'm a counselor/therapist and have always been interested in dating statistics. The only one I've use is a simple one...the more you date the closer you get to finding the right one. The less you date the further from finding the right one.

    ReplyDelete