Our published papers are listed here in approximate reverse chronological order (including some unexpected items such as a review of a book on international relations), and our unpublished papers are here. (Many but not all of the unpublished papers will eventually end up in the “published” category.)

No new books this year except for the second edition of my Teaching Statistics book with Deb Nolan. Also relevant for teaching purposes are our recent articles in Slate.

If you like the give-and-take of discussion, you can go back and read the past 400 or so blog entries. Thanks as always for all of you who write the thoughtful comments that make this such a wonderful place to learn.

Finally, a lot of our work has gone into Stan and hasn’t been formulated as research papers, but you can see the Stan forums to get a sense of some of the things that have been going on, or you could do a diff on the Stan manual, or take a look at the Stan case studies. I didn’t write Stan but I’ve been a frequent user.

We get a lot of research funding from many different sources (see here for a partial list), so it’s only fair that we share as much as we can with all of you.

Happy new year, and thanks again for all the thoughtful and lively discussion!

P.S. Here are the articles from 2017:

Published:

- [2018] Review of {\em New Explorations into International Relations: Democracy, Foreign Investment, Terrorism, and Conflict}, by Seung-Whan Choi. {\em Perspectives on Politics}. (Andrew Gelman)
- [2018] Benefits and limitations of randomized controlled trials. Discussion of “Understanding and misunderstanding randomized controlled trials,” by Angus Deaton and Nancy Cartwright. {\em Social Science \& Medicine}. (Andrew Gelman)
- [2018] The failure of null hypothesis significance testing when studying incremental changes, and what to do about it. {\em Personality and Social Psychology Bulletin} {\bf 44}, 16–23. (Andrew Gelman)
- [2018] Bayesian aggregation of average data: An application in drug development. {\em Annals of Applied Statistics}. (Sebastian Weber, Andrew Gelman, Daniel Lee, Michael Betancourt, Aki Vehtari, and Amy Racine-Poon)
- [2018] How to think scientifically about scientists’ proposals for fixing science. {\em Socius}. (Andrew Gelman)
- [2018] Learning from and responding to statistical criticism. {\em Observational Studies}.

(Andrew Gelman) - [2018] Donald Rubin. In {\em Encyclopedia of Social Research Methods}, ed.\ Paul Atkinson, Sara Delamont, Melissa Hardy, and Malcolm Williams. Thousand Oaks, Calif.: Sage Publications.

(Andrew Gelman) - [2017] The prior can often only be understood in the context of the likelihood. {\em Entropy} {\bf 19}, 555. (Andrew Gelman, Daniel Simpson, and Michael Betancourt)
- [2017] Why high-order polynomials should not be used in regression discontinuity designs. {\em Journal of Business and Economic Statistics}. (Andrew Gelman and Guido Imbens)
- [2017] Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC. {\em Statistics and Computing} {\bf 27}, 1413–1432. (Aki Vehtari, Andrew Gelman, and Jonah Gabry)
- [2017] 19 things we learned from the 2016 election (with discussion). {\em Statistics and Public Policy} {\bf 4}. (Andrew Gelman and Julia Azari)

How special was 2016? (rejoinder to discussion). (Julia Azari and Andrew Gelman) - [2017] Exploring the relationships between USMLE performance and disciplinary action in practice: A validity study of score inferences from a licensure examination. {\em Academic Medicine} {\bf 92}, 1780–1785. (Monica M. Cuddy, Aaron Young, Andrew Gelman, David B. Swanson, David A. Johnson, Gerard F. Dillon, and Brian E. Clauser)
- [2017] Some natural solutions to the p-value communication problem—and why they won’t work. {\em Journal of the American Statistical Association} {\bf 112}, 899–901. (Andrew Gelman and John Carlin)
- [2017] Beyond subjective and objective in statistics (with discussion and rejoinder). {\em Journal of the Royal Statistical Society A} {\bf 180}, 967–1033. (Andrew Gelman and Christian Hennig)
- [2017] Measurement error and the replication crisis. {\em Science} {\bf 355}, 584–585. (Eric Loken and Andrew Gelman)
- [2017] Honesty and transparency are not enough. {\em Chance} {\bf 30} (1), 37–39. (Andrew Gelman)
- [2017] Stan: A probabilistic programming language. {\em Journal of Statistical Software} {\bf 76} (1). (Bob Carpenter, Andrew Gelman, Matt Hoffman, Daniel Lee, Ben Goodrich, Michael Betancourt, Marcus Brubaker, Jiqiang Guo, Peter Li, and Allen Riddell)
- [2017] Consensus Monte Carlo using expectation propagation. {\em Brazilian Journal of Probability and Statistics} {\bf 31}, 692–696. (Andrew Gelman and Aki Vehtari)
- [2017] The 2008 election: A preregistered replication analysis. {\em Statistics and Public Policy} {\bf 4}. (Rayleigh Lei, Andrew Gelman, and Yair Ghitza)

Online appendix. - [2017] The statistical crisis in science: How is it relevant to clinical neuropsychology? {\em Clinical Neuropsychologist} {\bf 31}, 1000–1014. (Andrew Gelman and Hilde Geurts)
- [2017] Automatic differentiation variational inference {\em Journal of Machine Learning Research} {\bf 18}, 1–45. (Alp Kucukelbir, Dustin Tran, Rajesh Ranganath, Andrew Gelman, and David M. Blei)
- [2017] Type M error might explain Weisburd’s Paradox. {\em Journal of Quantitative Criminology}. (Andrew Gelman, Torbjørn Skardhamar, and Mikko Aaltonen)
- [2017] Learning about networks using sampling. {\em Journal of Survey Statistics and Methodology} {\bf 5}, 22–28 (Andrew Gelman)
- [2017] Fitting Bayesian item response models in Stata and Stan. {\em Stata Journal} {\bf 17}, 343–357. (Robert Grant, Daniel Furr, Bob Carpenter, and Andrew Gelman)

- Stents: An exploration of design, measurement, analysis, and reporting in clinical research. (Andrew Gelman and Brahmajee Nallamothu)
- The fallacy of objective measurement: the case of gaydar. (Andrew Gelman)
- Statistical learning and scientific decisions. (Andrew Gelman and Blakeley B. McShane)
- Bayesian inference under cluster sampling with probability proportional to size. (Susanna Makela, Yajuan Si, and Andrew Gelman)
- Abandon statistical significance. (Blakeley B. McShane, David Gal, Andrew Gelman, Christian Robert, and Jennifer L. Tackett)
- Visualization in Bayesian workflow. (Jonah Gabry, Daniel Simpson, Aki Vehtari, Michael Betancourt, and Andrew Gelman)
- R-squared for Bayesian regression models. (Andrew Gelman, Ben Goodrich, Jonah Gabry, and Imad Ali)
- The political impact of social penumbras. (Andrew Gelman and Yotam Margalit)
- Bayesian hierarchical weighting adjustment and survey inference. (Yajuan Si, Rob Trangucci, Jonah Gabry, and Andrew Gelman)
- Using stacking to average Bayesian predictive distributions. (Yuling Yao, Aki Vehtari, Daniel Simpson, and Andrew Gelman)
- Pareto smoothed importance sampling. (Aki Vehtari, Andrew Gelman, and Jonah Gabry)
- The statistical significance filter leads to overconfident expectations of replicability. (Shravan Vasishth and Andrew Gelman)

Andrew:

“Also relevant for teaching purposes are our recent articles in Slate.”

In one of your Slate articles you write:

“When the election came around, Trump ended up with nearly 50 percent of the two-party vote—according to the latest count, he lost to Hillary Clinton by only 200,000 votes.”

Actually, Clinton won by well over 2 million votes so you are off by at least a factor of ten. Is this par for the course in the (Trump) polling game?

From https://splinternews.com/here-is-the-final-popular-vote-count-of-the-2016-electi-1793864349

“Clinton received 65,844,610 votes, or 48.2% of the total vote.

Trump received 62,979,636 votes, or 46.1% of the total vote. (That’s a difference of 2.86 million votes.)”

Consequently, make that a factor of 14.3.

Paul:

Sure, it’s fine for teaching purposes for students to see that it takes awhile for all the votes to be counted.

When dealing with the 2016 election I am reminded of the following which appeared in

https://andrewgelman.com/2017/04/06/dear-cornell-university-public-relations-office/

“these [Wansink] numbers don’t add up. None of them add up! The numbers violate the Law of Conservation of Carrots.”

Likewise, Trump’s triumph and his continuing hold on his followers remain essentially inexplicable to a rational mind.

Paul:

Not inexplicable from the standpoint of political polarization. A Trump supporter can consider him and his policies, on the whole, to be superior to the Democratic alternative.

Thanks for sharing and facilitating the blog (along with your other co-authors). We would be much worse off if you did not do so.

Yes thanks for sharing. Happy New Year

Thanks for sharing this. Any news on when the new the new “Data Analysis Using Regression and Multilevel/Hierarchical Models” will be released? I’m assuming everything (or most majority) will be in Stan, so I’m looking forward!

+1 on looking forward to the 2nd edition of ARM. Will literally jump for joy when it’s released!

Jorge:

We’re almost finished Regression and Other Stories (the update of the first half of ARM), then we’ll do Advanced Regression and Multilevel Models (the update of the second half). The code is mostly in R and rstanarm.

Eddie:

I too will jump for joy when this is done!

There is a problem with the direct links to the different papers, where you get an page not found error, if you try to click on any of them.

Links fixed; thanks.