For objective causal inference, design trumps analysis
Top Cited Papers
Open Access
- 1 September 2008
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Applied Statistics
- Vol. 2 (3), 808-840
- https://doi.org/10.1214/08-aoas187
Abstract
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.Keywords
This publication has 39 references indexed in Scilit:
- Estimating Treatment Effects Using Observational DataJAMA, 2007
- Heart failure, chronic diuretic use, and increase in mortality and hospitalization: an observational study using propensity score methodsEuropean Heart Journal, 2006
- Combining Propensity Score Matching with Additional Adjustments for Prognostic CovariatesJournal of the American Statistical Association, 2000
- Formal mode of statistical inference for causal effectsJournal of Statistical Planning and Inference, 1990
- Statistics and Causal InferenceJournal of the American Statistical Association, 1986
- Constructing a Control Group Using Multivariate Matched Sampling Methods That Incorporate the Propensity ScoreThe American Statistician, 1985
- The central role of the propensity score in observational studies for causal effectsBiometrika, 1983
- Randomization Analysis of Experimental Data: The Fisher Randomization TestJournal of the American Statistical Association, 1980
- Using Multivariate Matched Sampling and Regression Adjustment to Control Bias in Observational StudiesJournal of the American Statistical Association, 1979
- The Probability Approach in EconometricsEconometrica, 1944