Skip to content
Archive of entries posted by

Rosenbaum (1999): Choice as an Alternative to Control in Observational Studies

Winston Lin wrote in a blog comment earlier this year: Paul Rosenbaum’s 1999 paper “Choice as an Alternative to Control in Observational Studies” is really thoughtful and well-written. The comments and rejoinder include an interesting exchange between Manski and Rosenbaum on external validity and the role of theories. And here it is. Rosenbaum begins: In […]

Iterative importance sampling

Aki points us to some papers: Langevin Incremental Mixture Importance Sampling Parallel Adaptive Importance Sampling Iterative importance sampling algorithms for parameter estimation problems Next one is not iterative, but interesting in other way Black-box Importance Sampling Importance sampling is what you call it when you’d like to have draws of theta from some target distribution […]

All cause and breast cancer specific mortality, by assignment to mammography or control

Paul Alper writes: You might be interested in the robocall my wife received today from our Medicare Advantage organization (UCARE Minnesota). The robocall informed us that mammograms saved lives and was available free of charge as part of her health insurance. No mention of recent studies criticizing mammography regarding false positives, harms of biopsies, etc. […]

SCANDAL: Florida State University football players held to the same low standards as George Mason University statistics faculty

Paul Alper points us to this news report: As the Florida State University football team was marching to a national title in the fall of 2013, the school was investigating allegations of academic favoritism involving a half-dozen of its leading players . . . The inquiry, previously unreported, stemmed from a complaint by a teaching […]

Causal identification + observational study + multilevel model

Sam Portnow writes: I am attempting to model the impact of tax benefits on children’s school readiness skills. Obviously, benefits themselves are biased, so I am trying to use the doubling of the maximum allowable additional child tax credit in 2003 to get an unbiased estimate of benefits. I was initially planning to attack this […]

The Groseclose endgame: Getting from here to there.

A few years ago, I wrote the following regarding political scientist Tim Groseclose’s book on media bias: Groseclose’s big conclusion is that in the absence of media bias, the average American voter would be positioned at around 25 on a 0-100 scale, where 0 is a right-wing Republican and 100 is a left-wing Democrat. . […]

What are best practices for observational studies?

Mark Samuel Tuttle writes: Just returned from the annual meeting of the American Medical Informatics Association (AMIA); in attendance were many from Columbia. One subtext of conversations I had with the powers that be in the field is the LACK of Best Practices for Observational Studies. They all agree that however difficult they are that […]

Robert Gelman, 1923-2017

Bob Gelman, beloved husband of Jane for 67 years, proud father of Alan, Nancy, Susan, and Andy, and adoring grandparent of Stephanie, Noah, Adam, Jamie, Ben, Zacky, Jakey, and Sophie, passed away peacefully on the morning of 27 Aug 2017 at the age of 94. A child of immigrants, Bob grew up playing stickball in […]

“Mainstream medicine has its own share of unnecessary and unhelpful treatments”

I have a story and then a question. The story Susan Perry (link sent by Paul Alper) writes: Earlier this week, I [Perry] highlighted two articles that exposed the dubious history, medical ineffectiveness and potential health dangers of popular alternative “therapies.” Well, the same can be said of many mainstream conventional medical practices, as investigative […]

Using statistical prediction (also called “machine learning”) to potentially save lots of resources in criminal justice

John Snow writes: Just came across this paper [Human Decisions and Machine Predictions, by Jon Kleinberg, Himabindu Lakkaraju, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan] and I’m wondering if you’ve been following the debate/discussion around these criminal justice risk assessment tools. I haven’t read it carefully or fully digested the details. On the surface, their […]

Chris Moore, Guy Molyneux, Etan Green, and David Daniels on Bayesian umpires

Kevin Lewis points us to a paper by Etan Green and David Daniels, who conclude that “decisions of [baseball] umpires reflect an accurate, probabilistic, and state-specific understanding of their rational expectations—as well as an ability to integrate those prior beliefs in a manner that approximates Bayes rule.” This is similar to what was found in […]

Fake polls. Not new.

Mark Palko points me to this article by Harry Enten about a possibly nonexistent poll that was promoted by an organization or group or website called Delphi Analytica. Enten conjectures that the reported data were not fabricated but they’re not a serious poll either but rather some raw undigested output from a Google poll. This […]

“From that perspective, power pose lies outside science entirely, and to criticize power pose would be a sort of category error, like criticizing The Lord of the Rings on the grounds that there’s no such thing as an invisibility ring, or criticizing The Rotter’s Club on the grounds that Jonathan Coe was just making it all up.”

From last year: One could make the argument that power pose is innocuous, maybe beneficial in that it is a way of encouraging people to take charge of their lives. And this may be so. Even if power pose itself is meaningless, the larger “power pose” story could be a plus. Of course, if power […]

Nice interface, poor content

Jim Windle writes: This might interest you if you haven’t seen it, and I don’t think you’ve blogged about it. I’ve only checked out a bit of the content but it seems a pretty good explanation of basic statistical concepts using some nice graphics. My reply: Nice interface, but their 3 topics of Statistical Inference […]

Sucker MC’s keep falling for patterns in noise

Mike Spagat writes: Apologies if forty people just sent this to you but maybe it’s obscure enough that I’m the first. It’s a news article by Irina Ivanova entitled, “‘Very unattractive’ workers can out-earn pretty people, study finds.” Spagat continues: You may be able to recognize a pattern here: Tiny, noisy sample Surprise result Journal […]

Cumulative residual plots seem like they could be useful

Peter Vanney, a statistician at Texas Highway Patrol, writes: I’m wondering if you could comment on CURE (CUmulative REsidual) plots that I’m seeing quite a bit in vehicle crash modeling. Ezra Hauer and Joseph Bamfo champion them as a way to determine model fit for their hierarchical Bayesian generalized linear mixed models. I had not […]

Don’t always give ’em what they want: Practicing scientists want certainty, but I don’t want to offer it to them!

Stephen Senn writes: What the practicing scientist wants to know is what is a good test in practice. I agree with Stephen Senn on most things—even where it seems we disagree, I think we agree on the fundamentals—but in this case I think you have to be careful about giving the practicing scientist what he […]

Two papers and one presentation by Ron Kennett related to workflow

Ron Kennett sent along these two papers: Statistics: A Life Cycle View Aspects of statistical consulting not taught by academia Also this presentation. They’re somewhat relevant to our current project on statistical workflow, so I’m posting them here for convenience. P.S. I used to think it was a good idea to teach statistical consulting, and […]

He wants some readings on the replication crisis that are accessible to college freshmen in economics

Harvey Rosen writes: My query is similar to the one from André Ariew that you posted on August 7, in which he asked if you could suggest readings for his graduate course in philosophy. I occasionally teach an undergraduate course on introductory microeconomics. I like to devote some time to discussing challenges to economists’ conventional […]

Mixture models in Stan: you can use log_mix()

From the Stan manual: log_mix() . . . I like it. Super-clean.