health non-sense [xkcd]

red state – blue state – vaccinated state – unvaccinated state

The New York Times published an article demonstrating the partisan separation between US Democrats and Republicans by regression lines. As the one above, regressing the proportion of vaccinated on the proportion of Trump voters but no scale on the first axis. But no correction for age composition or population density. And the one below, plotted at the county level, which seems quite meaningless given the spread of red dots in Wyoming.

Still, there is a clear opposition between places (counties) that voted more than 70% Trump (representing 33M people) and those that voted more than 70% Biden (more than 58M people), even though county density, age composition, and earlier deaths from COVID should also be accounted for. But the vaccination rate also exhibits this opposition, with a 1.65 ratio between the first and last decile of the blue counties.

gender gaps

Two of my colleagues [and co-authors] at Dauphine, Elyès Jouini and Clotilde Napp, published a paper in Science last week (and an associated tribune in Le Monde which I spotted first) about explaining differences in national gender inequalities in maths (as measured by PISA) in terms of the degree of overall inequality in the respective countries. Gaps in the highest maths performer sex ratio. While I have no qualm about the dependency or the overall statistical cum machine learning analysis (supported by our common co-author Jean-Michel Marin), and while I obviously know nothing about the topic!, I leisurely wonder at the cultural factor (which may also partly explain for the degree of inequality) when considering that the countries at the bottom of the above graphs are rather religious (and mostly catholic). I also find it most intriguing that the gender gap is consistently reversed when considering higher performer sex ratio for reading, because mastering the language should be a strong factor in power structures and hence differences therein should also lead to inequalities…

weapons of math destruction [book review]

As I had read many comments and reviews about this book, including one by Arthur Charpentier, on Freakonometrics, I eventually decided to buy it from my Amazon Associate savings (!). With a strong a priori bias, I am afraid, gathered from reading some excerpts, comments, and the overall advertising about it. And also because the book reminded me of another quantic swan. Not to mention the title. After reading it, I am afraid I cannot tell my ascertainment has changed much.

“Models are opinions embedded in mathematics.” (p.21)

The core message of this book is that the use of algorithms and AI methods to evaluate and rank people is unsatisfactory and unfair. From predicting recidivism to fire high school teachers, from rejecting loan applications to enticing the most challenged categories to enlist for for-profit colleges. Which is indeed unsatisfactory and unfair. Just like using the h index and citation ranking for promotion or hiring. (The book mentions the controversial hiring of many adjunct faculty by KAU to boost its ranking.) But this conclusion is not enough of an argument to write a whole book. Or even to blame mathematics for the unfairness: as far as I can tell, mathematics has nothing to do with unfairness. Some analysts crunch numbers, produce a score, and then managers make poor decisions. The use of mathematics throughout the book is thus completely inappropriate, when the author means statistics, machine learning, data mining, predictive algorithms, neural networks, &tc. (OK, there is a small section on Operations Research on p.127, but I figure deep learning can bypass the maths.)

reading classics (#3)

Following in the reading classics series, my Master students in the Reading Classics Seminar course, listened today to Kaniav Kamary analysis of Denis Lindley’s and Adrian Smith’s 1972 linear Bayes paper Bayes Estimates for the Linear Model in JRSS Series B. Here are her (Beamer) slides

At a first (mathematical) level this is an easier paper in the list, because it relies on linear algebra and normal conditioning. Of course, this is not the reason why Bayes Estimates for the Linear Model is in the list and how it impacted the field. It is indeed one of the first expositions on hierarchical Bayes programming, with some bits of empirical Bayes shortcuts when computation got a wee in the way. (Remember, this is 1972, when shrinkage estimation and its empirical Bayes motivations is in full blast…and—despite Hstings’ 1970 Biometrika paper—MCMC is yet to be imagined, except maybe by Julian Besag!) So, at secondary and tertiary levels, it is again hard to discuss, esp. with Kaniav’s low fluency in English. For instance, a major concept in the paper is exchangeability, not such a surprise given Adrian Smith’s translation of de Finetti into English. But this is a hard concept if only looking at the algebra within the paper, as a motivation for exchangeability and partial exchangeability (and hierarchical models) comes from applied fields like animal breeding (as in Sørensen and Gianola’s book). Otherwise, piling normal priors on top of normal priors is lost on the students. An objection from a 2012 reader is also that the assumption of exchangeability on the parameters of a regression model does not really make sense when the regressors are not normalised (this is linked to yesterday’s nefarious post!): I much prefer the presentation we make of the linear model in Chapter 3 of our Bayesian Core. Based on Arnold Zellner‘s g-prior. An interesting question from one student was whether or not this paper still had any relevance, other than historical. I was a bit at a loss on how to answer as, again, at a first level, the algebra was somehow natural and, at a statistical level, less informative priors could be used. However, the idea of grouping parameters together in partial exchangeability clusters remained quite appealing and bound to provide gains in precision….