Blog · corpus.blog/blogs/statmodeling.stat.columbia.edu/posts
Andrew Gelman
statmodeling.stat.columbia.edu
2022
11 Apr 2022
Hey—check out this post from 2006 when I was mellow . . . actually too mellow, too nice, and too understandingoriginal ↗
9 Apr 2022
Some discussion of “how to get confident with statistics”: Reading, practicing, talking, and questioningoriginal ↗
8 Apr 2022
Different effect sizes used in statistics/psychometrics or machine learning; what should this researcher do?original ↗
8 Apr 2022
Continuing uncertainty regarding what was going on in Santa Clara county, California, in April 2020original ↗
7 Apr 2022
6 Apr 2022
(Further ranting on Public Choice’s terrible decision:) If Uri Geller submits a paper claiming to have photographs of the Loch Ness monster, you don’t just say, Hey, the photos look real, let’s go publish!original ↗
5 Apr 2022
“Two truths and a lie” as a class-participation activity (and some more general comments on integrating active learning into a statistics class)original ↗
4 Apr 2022
The journal Public Choice goes the way of Lancet and publishes a paper that is “riddled with errors” but comes to a political conclusion that they want to support.original ↗
3 Apr 2022
“Why the New Pollution Literature is Credible” . . . but I’m still guessing that the effects are being overestimated:original ↗
2 Apr 2022
The epidemiologists and the Kardashians, and the difficulty of introducing satire in scientific discourseoriginal ↗
1 Apr 2022
31 Mar 2022
29 Mar 2022
Open AI gets GPT-3 to work by hiring an army of humans to fix GPT’s bad answers. Interesting questions involving the mix of humans and computer algorithms in Open AI’s GPT-3 programoriginal ↗
28 Mar 2022
The examples you see in the textbooks are not representative of the sorts of problems you see in the real worldoriginal ↗
27 Mar 2022
25 Mar 2022
He’s a devops engineer and he wants to set some thresholds. Where should he go to figure out what to do?original ↗
24 Mar 2022
Teddy, don’t be a hero, don’t fall in love with your story / Teddy, don’t be a hero, there’s more to science than gloryoriginal ↗
24 Mar 2022
Could the so-called “fragility index” be useful as a conceptual tool even though it would be a bad idea to actually use it?original ↗
23 Mar 2022
Sleep, cats, and statistical significance: This one hits the Statistical Modeling, Causal Inference, and Social Science sweet spot!original ↗
20 Mar 2022
20 Mar 2022
19 Mar 2022
17 Mar 2022
15 Mar 2022
Talks from our mini-conference, MRI Together: A global workshop on Open Science and Reproducible MR Researchoriginal ↗
15 Mar 2022
14 Mar 2022
13 Mar 2022
13 Mar 2022
10 Mar 2022
How to think about the large estimated effects from taking an ethnic studies class in high school?original ↗
9 Mar 2022
PhD student position in Stuttgart . . . to work on Stan! Latent variable models in psychology and the social sciences. With Paul “brms” Buerkner!original ↗
9 Mar 2022
Own your design choices: We should express findings in paper titles by referring to what was measured rather than the general construct that was being aimed for.original ↗
7 Mar 2022
5 Mar 2022
Yuling’s talk, “From mixture model to continuous model extension to operator-based probabilistic inference”original ↗
4 Mar 2022
3 Mar 2022
3 Mar 2022
Duality between multilevel models and multiple comparisons adjustments, and the relevance of this to some discussions of replication failuresoriginal ↗
2 Mar 2022
1 Mar 2022
Exploring some questions about meta-analysis (using ivermectin as an example), with R and Stan codeoriginal ↗
28 Feb 2022
Did Chinese laborers on the Yangtze pay someone to whip them? Why can’t political scientists and economists resist telling this evidence-free story? And why do they keep embellishing it?original ↗
27 Feb 2022
26 Feb 2022
“Masks block some fraction of viral particles from dispersing from those who are infected and from infecting those who are susceptible . . . studies that did not find masks to be effective had limited statistical power and therefore do not imply that masks are ineffective . . . The studies that did not find statistically significant effects prove only that masks cannot offer protection if they are not worn.”original ↗
24 Feb 2022
Former editor of British Medical Journal says we should “assume that the research is fraudulent until there is some evidence to support it having happened and been honestly reported”original ↗
22 Feb 2022
21 Feb 2022
20 Feb 2022
The important “It exists, and it’s not going away” argument, as it applies to economics, political science, sabermetrics, and many aspects of statisticsoriginal ↗
19 Feb 2022
“Efficacy of Ivermectin Treatment on Disease Progression Among Adults With Mild to Moderate COVID-19 and Comorbidities The I-TECH Randomized Clinical Trial”original ↗
19 Feb 2022
Some Bayesian Methods for Causal Inference (my remote talk next Monday at the University of Wisconsin Population Health Sciences Seminar)original ↗
17 Feb 2022
Understanding Spatial Models in Context (my talk this Friday at the Getis-Ord Lecture in Spatial Analysis)original ↗
16 Feb 2022
Hey! I got an exclusive invitation to this off-the-record conference . . . but I think I’ll take 3515 Jamaican beef patties instead.original ↗
16 Feb 2022
15 Feb 2022
He’s attempting to overhaul his company’s model of retail demand. Which makes me think of multilevel models . . .original ↗
15 Feb 2022
“Driving about 85 m.p.h. in a 45 m.p.h. zone on the winding Southern California road when he lost control of his SUV. . . . He was not charged with any legal violation.”original ↗
13 Feb 2022