Heterogeneity and Causality
Before R.A. Fisher introduced randomized experimentation, the literature on causal inference emphasized reduction of heterogeneity of experimental units. To what extent is heterogeneity relevant to causal claims in observational studies when random assignment of treatments is unethical or infeasible?
KeywordsStatist Assoc Seat Belt Moderate Bias Design Sensitivity Causal Claim
Unable to display preview. Download preview PDF.
- Card, D., Krueger, A.: Minimum wages and employment: A case study of the fast-food industry in New Jersey and Pennsylvania. Am Econ Rev 84, 772–793 (1994)Google Scholar
- Fisher, R.A.: Design of Experiments. Edinburgh: Oliver and Boyd (1935)Google Scholar
- Greenland, S.: A unified approach to the analysis of case-distribution (case-only) studies. Statist Med 18, 1–15 (1999)Google Scholar
- Hammond, E.C.: Smoking in relation to mortality and morbidity. J Natl Cancer Inst 32, 1161–1188 (1964)Google Scholar
- Heller, R., Rosenbaum, P.R., Small, D.: Split samples and design sensitivity in observational studies. J Am Statist Assoc 104, to appear (2009)Google Scholar
- Lehmann, E.L.: Nonparametrics, San Francisco: Holden Day (1975) Reprinted New York: Springer (2006)Google Scholar
- Maclure, M.: The case-crossover design: A method for studying transient effects on the risk of acute events. Am J Epidemiol 133, 144–152 (1991)Google Scholar
- Mill, J.S.: A System of Logic: The Principles of Evidence and the Methods of Scientific Investigation. Indianapolis: Liberty Fund (1867)Google Scholar
- Rosenbaum, P.R.: What aspects of the design of an observational study affect its sensitivity to bias from covariates that were not observed? In: Festshrift for Paul W. Holland. Princeton, NJ: ETS (2009)Google Scholar
- Wright, P.H., Robertson, L.S.: Priorities for roadside hazard modification. Traffic Eng 46, 24–30 (1976)Google Scholar