One of the world’s best statisticians, who has literally written the book on how to teach statistics, had an interesting twitter post the other day
As an interesting note, Andrew Gelman’s twitter feed has 2300 followers…but yet Gelman himself is not following anyone. That’s a pretty solid ratio!
While I’m not ready to give the top 5 papers across all of statistics, I figured it’d be worth a shot at the top 5 causal inference papers from the 2000’s. Only rules: the paper had to be published between 2001 and 2010 in a statistics journal, and our primary interest is not just the application, but the method itself.
My favorites, in no particular order.
Frangakis, Constantine E., and Donald B. Rubin. “Principal stratification in causal inference.” Biometrics 58.1 (2002): 21-29. ML: This one pretty much introduced the idea of principal stratification, and did so in a strait-forward manner.
Stuart, Elizabeth A. “Matching methods for causal inference: A review and a look forward.” Statistical science: a review journal of the Institute of Mathematical Statistics 25.1 (2010): 1. ML: My favorite review paper on matching methods, this paper is only three years old and has been cited almost 300 times on google scholar. I still learn something each time I go back to it. If you are starting causal inference, start with this paper! Don’t start with the next one.
Imai, Kosuke, and David A. Van Dyk. “Causal inference with general treatment regimes.” Journal of the American Statistical Association 99.467 (2004). ML: Since I’m focused on causal inference methods with multiple exposures, this paper is always a must read (albeit, a difficult one!)
Bang, Heejung, and James M. Robins. “Doubly robust estimation in missing data and causal inference models.” Biometrics 61.4 (2005): 962-973. ML: Some would argue that doubly robust estimation is the only way to go. Bang and Robins are two of those people.
Kang, Joseph DY, and Joseph L. Schafer. “Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data.” Statistical science 22.4 (2007): 523-539. ML: I thought a paper on missing data would nicely round up this list, and I think I’ve read this one as much as any.
Hogan, Joseph W., Jason Roy, and Christina Korkontzelou. “Handling drop out in longitudinal studies.” Statistics in medicine 23.9 (2004): 1455-1497. ML: A must read for anyone conducting longitudinal studies, where there is always drop out.
Hirano, Keisuke, and Guido W. Imbens. “The propensity score with continuous treatments.” Applied Bayesian modeling and causal inference from incomplete-data perspectives 226164 (2004): 73-84. ML: Imbens’ similar 2000 paper missed out on this list by one year.
Austin, Peter C., et al. “Conditioning on the propensity score can result in biased estimation of common measures of treatment effect: a Monte Carlo study.” Statistics in medicine 26.4 (2007): 754-768. ML: Austin wrote about 9 papers in 3 years. The title of this one is all people needed to read.
Lunceford, Jared K., and Marie Davidian. “Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study.” Statistics in medicine 23.19 (2004): 2937-2960. ML: This is one of the first papers to compare a bunch of causal methods through simulations.