Statistical Science

Covariance Adjustment in Randomized Experiments and Observational Studies

Paul R. Rosenbaum

Full-text: Open access

Abstract

By slightly reframing the concept of covariance adjustment in randomized experiments, a method of exact permutation inference is derived that is entirely free of distributional assumptions and uses the random assignment of treatments as the "reasoned basis for inference.'' This method of exact permutation inference may be used with many forms of covariance adjustment, including robust regression and locally weighted smoothers. The method is then generalized to observational studies where treatments were not randomly assigned, so that sensitivity to hidden biases must be examined. Adjustments using an instrumental variable are also discussed. The methods are illustrated using data from two observational studies.

Article information

Source
Statist. Sci., Volume 17, Issue 3 (2002), 286-327.

Dates
First available in Project Euclid: 16 January 2003

Permanent link to this document
https://projecteuclid.org/euclid.ss/1042727942

Digital Object Identifier
doi:10.1214/ss/1042727942

Mathematical Reviews number (MathSciNet)
MR1962487

Zentralblatt MATH identifier
1013.62117

Keywords
Covariance adjustment matching observational studies permutation inference propensity score randomization inference sensitivity analysis

Citation

Rosenbaum, Paul R. Covariance Adjustment in Randomized Experiments and Observational Studies. Statist. Sci. 17 (2002), no. 3, 286--327. doi:10.1214/ss/1042727942. https://projecteuclid.org/euclid.ss/1042727942


Export citation

See also

  • Includes: J. Angrist, G. Imbens. Comment.
  • Includes: Jennifer Hill. Comment.
  • Includes: James M. Robins. Comment.
  • Includes: Paul R. Rosenbaum. Rejoinder.