Blog · corpus.blog/blogs/statmodeling.stat.columbia.edu/posts
Andrew Gelman
statmodeling.stat.columbia.edu
2018
“The following needs to be an immutable law of journalism: when someone with no track record comes into a field claiming to be able to do a job many times better for a fraction of the cost, the burden of proof needs to shift quickly and decisively onto the one making the claim. The reporter simply has to assume the claim is false until substantial evidence is presented to the contrary.”original ↗
17 Jan 2018
Static sensitivity analysis: Computing robustness of Bayesian inferences to the choice of hyperparametersoriginal ↗
16 Jan 2018
Statistical behavior at the end of the world: the effect of the publication crisis on U.S. research productivityoriginal ↗
16 Jan 2018
Hey, here’s a new reason for a journal to reject a paper: it’s “annoying” that it’s already on a preprint serveroriginal ↗
15 Jan 2018
14 Jan 2018
The puzzle: Why do scientists typically respond to legitimate scientific criticism in an angry, defensive, closed, non-scientific way? The answer: We’re trained to do this during the process of responding to peer review.original ↗
13 Jan 2018
The retraction paradox: Once you retract, you implicitly have to defend all the many things you haven’t yet retractedoriginal ↗
12 Jan 2018
11 Jan 2018
10 Jan 2018
Benefits and limitations of randomized controlled trials: I agree with Deaton and Cartwrightoriginal ↗
8 Jan 2018
8 Jan 2018
“However noble the goal, research findings should be reported accurately. Distortion of results often occurs not in the data presented but . . . in the abstract, discussion, secondary literature and press releases. Such distortion can lead to unsupported beliefs about what works for obesity treatment and prevention. Such unsupported beliefs may in turn adversely affect future research efforts and the decisions of lawmakers, clinicians and public health leaders.”original ↗
7 Jan 2018
“Each computer run would last 1,000-2,000 hours, and, because we didn’t really trust a program that ran so long, we ran it twice, and it verified that the results matched. I’m not sure I ever was present when a run finished.”original ↗
6 Jan 2018
6 Jan 2018
4 Jan 2018
2017
30 Dec 2017
“Handling Multiplicity in Neuroimaging through Bayesian Lenses with Hierarchical Modeling”original ↗
28 Dec 2017
The failure of null hypothesis significance testing when studying incremental changes, and what to do about itoriginal ↗
26 Dec 2017
25 Dec 2017
24 Dec 2017
20 Dec 2017
The problem of media concentration/deregulation “is usually treated as a series of unrelated problems, much like a cocaine addict who complains about his drug problem, bankruptcy, divorce, and encounters with loan sharks, but who never makes a causal connection between the items on the list”original ↗
20 Dec 2017
18 Dec 2017
17 Dec 2017
16 Dec 2017
The piranha problem in social psychology / behavioral economics: The “take a pill” model of science eats itselforiginal ↗
15 Dec 2017
14 Dec 2017
14 Dec 2017
13 Dec 2017
Yes, you can do statistical inference from nonrandom samples. Which is a good thing, considering that nonrandom samples are pretty much all we’ve got.original ↗
13 Dec 2017
12 Dec 2017
11 Dec 2017
StanCon2018: one month to go, schedule finalized, over 20 talks, 6 tutorials… and flights are cheaporiginal ↗
10 Dec 2017
9 Dec 2017
8 Dec 2017
7 Dec 2017
“There was this prevalent, incestuous, backslapping research culture. The idea that their work should be criticized at all was anathema to them. Let alone that some punk should do it.”original ↗
6 Dec 2017
5 Dec 2017
Orphan drugs and forking paths: I’d prefer a multilevel model but to be honest I’ve never fit such a model for this sort of problemoriginal ↗
3 Dec 2017
2 Dec 2017
1 Dec 2017
29 Nov 2017
Asymptotically we are all dead (Thoughts about the Bernstein-von Mises theorem before and after a Diamanda Galás concert)original ↗
27 Nov 2017
“Dear Professor Gelman, I thought you would be interested in these awful graphs I found in the paper today.”original ↗
26 Nov 2017
Using output from a fitted machine learning algorithm as a predictor in a statistical modeloriginal ↗
24 Nov 2017
22 Nov 2017
22 Nov 2017
21 Nov 2017
21 Nov 2017
“A Bias in the Evaluation of Bias Comparing Randomized Trials with Nonexperimental Studies”original ↗
20 Nov 2017
20 Nov 2017
Graphics software is not a tool that makes your graphs for you. Graphics software is a tool that allows you to make your graphs.original ↗
18 Nov 2017
17 Nov 2017