Skip to content

Valentine’s Day statistical love poems

Elissa Brown sends these in. They’re actually pretty good, with a quite reasonable Ogden-Nash-style rhythm and a certain amount of statistical content. It’s good to know that the kids today are learning useful skills in their graduate programs.

You are perfect; I’d make no substitutions
You remind me of my favorite distributions
With a shape and a scale that I find reliable
You’re as comforting as a two parameter Weibull
When I ask you a question and hope you answer truly
You speak as clearly as a draw from a Bernoulli
Your love of adventure is most influential
Just like the constant hazard of an exponential.
With so many moments, all full of fun,
You always integrate perfectly to one.

And here are a bunch more:

A frequentist would say the chances of love are small,
using 1 in a million as an close approximation.
But I’d rather let a Bayseian make the call,
who would conclude it’s certain based on observed


I’m aiming for a p-value less than .01
That you and me together could have lots of fun
The R2 of those before you were really quite poor
But the multiple comparisons problem we’ll just ignore


I used to think you were a little proc mean
But now I see that I was wrong
Your data is much more classy than I’d seen
So how ’bout we get our proc freq on?


Some hypothesize all love turns sour
And that even the hottest flame will grow dull
That’s why you and I should combine our power
And once and for all reject the null


You’re the apple of my pi
You’re the square to my chi
You’re the source of my love, shining and nu
And that is why I love mu


They say that Y equals m-x plus b
(well, when you remove the uncertainty).
So let me reveal a secret confession:
You’re the solution to my least squares obsession.


In this world, I seek a fellow actuary;
but I am careful to avoid those who are ancillary.
When I need some help estimating my coefficient,
you, my dear, are minimal and sufficient.


I may know all things statistical
But how to win your love is far more mystical
I could derive and integrate with great flair
And we could make a perfectly correlated pair


#2 in the homework? I’ll show you what I got:
My heart’s the confounder in Y-dot-dot
Just check out the box and spaghetti plots
Now let’s get to rejecting H sub naught!


H0: All is lost, our love is not mean to be
Ha: Oh happy day, you really like me
Our favorite test statistic says p=0.053
That’s a little high but it’s good enough for me


The highest rank of love is in group You
Distributions lead to models that aren’t very true
Because parameters our love most readily eschews


Help! My heart’s survival is approaching zero
There’s been no recurrence of love to observe
So do me a favor and be my hero
And flatten the shape of my survival curve


You could say my love life was missing
And my crushes so dismissing
But then I had an idea most astute:
A new lover I could impute!
And now how I’m enjoying lots of kissing.


I’ve suffered through dates that were very extreme
When all I was hoping for was closer to the mean
Their knowledge of boring facts was encyclopedian
When it would have been better to be on the other side of the median
And eventually even their manners did erode
With scores for politeness nowhere near the mode
So I apologize for being so informal
But I’m so glad I finally found someone normal

I don’t know what “WSR, WRS, MWU” are, but the other poems pretty much make sense to me.


  1. Jason says:

    Non-parametric tests, I believe. WSR = Wilcoxon Signed Ranks; WRS = Wilcoxon Rank Sum; and MWU = Mann-Whitney U.

  2. Cristian says:

    I think "WSR, WRS, MWU" stands for the following non-parametric test based on ranks…

    WSR: Wilcoxon Signed-Rank test
    WRS: Wilcoxon Rank-Sum test (or Wilcoxon–Mann–Whitney test)
    MWU: Mann–Whitney U test

    Nice blog!

  3. Andrew Gelman says:

    For my take on Wilcoxon, see p.252 of BDA.

  4. elissa says:

    Even us hard-working grad students need a break now and then; one can apply the delta method only so many times before needing to write a poem.

    I should note that Matthew Flickinger, a very talented doctoral student, wrote a good half of these.

    Love the "Literature" tag. Ha! Cheers Andrew.

  5. Scott Schulz says:

    Here's a poem along the same lines I wrote fresh off of my Ph.D. in OR back in 1990 or so:

  6. Xiaoyu says:

    @Scott: like your poems! they are very beautiful!