Blog · corpus.blog/blogs/statmodeling.stat.columbia.edu/posts
Andrew Gelman
statmodeling.stat.columbia.edu
2023
Physics educators do great work with innovative teaching. They should do better in evaluating evidence of effectiveness and be more open to criticism.original ↗
10 May 2023
7 May 2023
6 May 2023
These corruption statistics are literally incredible! (Every political science student should read this article.)original ↗
5 May 2023
When did the use of stylized data examples become standard practice in statistical research and teaching?original ↗
4 May 2023
3 May 2023
30 Apr 2023
29 Apr 2023
Straining on the gnat of the prior distribution while swallowing the camel that is the likelihood. (Econometrics edition)original ↗
27 Apr 2023
Estimated effects of pre-K over the decades: From Cold War optimism to modern-day pessimismoriginal ↗
26 Apr 2023
Open problem: How to make residual plots for multilevel models (or for regularized Bayesian and machine-learning predictions more generally)?original ↗
25 Apr 2023
24 Apr 2023
How large is the underlying coefficient? An application of the Edlin factor to that claim that “Cash Aid to Poor Mothers Increases Brain Activity in Babies”original ↗
24 Apr 2023
Hey—here’s some ridiculous evolutionary psychology for you, along with some really bad data analysis.original ↗
23 Apr 2023
22 Apr 2023
21 Apr 2023
20 Apr 2023
“While we absolutely acknowledge that we’re moving to a more accurate and appropriate way to count deaths, it doesn’t change our understanding, it does not alter our understanding . . .”original ↗
19 Apr 2023
Why it doesn’t make sense to say, “X people are dying every year from Y.” Use life-years instead.original ↗
18 Apr 2023
Ghostwriting by federal judges (a way to violate disclosure rules) as the opposite of plagiarism.original ↗
17 Apr 2023
15 Apr 2023
The “percentogram”—a histogram binned by percentages of the cumulative distribution, rather than using fixed bin widthsoriginal ↗
13 Apr 2023
12 Apr 2023
11 Apr 2023
“Assault Deaths in the OECD 1960-2020”: These graphs are good, and here’s how we can make them better:original ↗
10 Apr 2023
Does the scientific literature contradict itself? Very well, then it contradicts itself, it is large, it contains multitudes.original ↗
8 Apr 2023
8 Apr 2023
7 Apr 2023
Mystery resolved! How did an article with apparently zero Jewish content end up in a “magazine of Jewish news, ideas, and culture”?original ↗
5 Apr 2023
3 Apr 2023
2 Apr 2023
1 Apr 2023
30 Mar 2023
29 Mar 2023
An epidemiologist and a psychologist come down from the ivory tower to lecture us on “concrete values like freedom and equality” . . . What does that even mean?? The challenge of criticizing policies without considering their political and social contexts:original ↗
28 Mar 2023
Multilevel modeling to make better decisions using data from schools: How can we do better?original ↗
27 Mar 2023
Someone has a plea to teach real-world math and statistics instead of “derivatives, quadratic equations, and the interior angles of rhombuses”original ↗
26 Mar 2023
It’s the finals! Time to choose the ultimate seminar speaker: Beverly Cleary vs. Laura Ingalls Wilderoriginal ↗
25 Mar 2023
24 Mar 2023
Bad stuff going down in biostat-land: Declaring null effect just cos p-value is more than 0.05, assuming proportional hazards where it makes no senseoriginal ↗
23 Mar 2023
What does it take, or should it take, for an empirical social science study to be convincing?original ↗
22 Mar 2023
They did a graphical permutation test to see if students could reliably distinguish the observed data from permuted replications. Now the question is, how do we interpret the results?original ↗
21 Mar 2023
Parallelization for Markov chain Monte Carlo with heterogeneous runtimes: a case-study on ODE-based modelsoriginal ↗
20 Mar 2023
“On March 14th at 7pm ET, thought leader and Harvard professor Steven Pinker will release digital collectibles of his famous idea that ‘Free speech is fundamental.'”original ↗
20 Mar 2023
17 Mar 2023
Problems with a CDC report: Challenges of comparing estimates from different surveys. Also a problem with rounding error.original ↗
16 Mar 2023
15 Mar 2023
Don’t trust people selling their methods: The importance of external validation. (Sepsis edition)original ↗
15 Mar 2023
Should drug companies be required to release data right away, not holding data secret until after regulatory approval?original ↗
12 Mar 2023
10 Mar 2023
“The butterfly and the piranha: Understanding the generalizability and reproducibility crisis from statistical and political perspectives” (my talk at the University of Minnesota political science department on Monday)original ↗
9 Mar 2023
8 Mar 2023