Open Access
September 2008 For objective causal inference, design trumps analysis
Donald B. Rubin
Ann. Appl. Stat. 2(3): 808-840 (September 2008). DOI: 10.1214/08-AOAS187


For obtaining causal inferences that are objective, and therefore have the best chance of revealing scientific truths, carefully designed and executed randomized experiments are generally considered to be the gold standard. Observational studies, in contrast, are generally fraught with problems that compromise any claim for objectivity of the resulting causal inferences. The thesis here is that observational studies have to be carefully designed to approximate randomized experiments, in particular, without examining any final outcome data. Often a candidate data set will have to be rejected as inadequate because of lack of data on key covariates, or because of lack of overlap in the distributions of key covariates between treatment and control groups, often revealed by careful propensity score analyses. Sometimes the template for the approximating randomized experiment will have to be altered, and the use of principal stratification can be helpful in doing this. These issues are discussed and illustrated using the framework of potential outcomes to define causal effects, which greatly clarifies critical issues.


Download Citation

Donald B. Rubin. "For objective causal inference, design trumps analysis." Ann. Appl. Stat. 2 (3) 808 - 840, September 2008.


Published: September 2008
First available in Project Euclid: 13 October 2008

zbMATH: 1149.62089
MathSciNet: MR2516795
Digital Object Identifier: 10.1214/08-AOAS187

Keywords: Average causal effect , causal effects , complier average causal effect , instrumental variables , noncompliance , observational studies , propensity scores , randomized experiments , Rubin Causal Model

Rights: Copyright © 2008 Institute of Mathematical Statistics

Vol.2 • No. 3 • September 2008
Back to Top