Advertisement

Overt Bias in Observational Studies

  • Paul R. Rosenbaum
Part of the Springer Series in Statistics book series (SSS)

Abstract

An observational study is biased if the treated and control groups differ prior to treatment in ways that matter for the outcomes under study. An overt bias is one that can be seen in the data at hand-for instance, prior to treatment, treated subjects are observed to have lower incomes than controls. A hidden bias is similar but cannot be seen because the required information was not observed or recorded. Overt biases are controlled using adjustments, such as matching or stratification. In other words, treated and control subjects may be seen to differ in terms of certain observed covariates, but these visible differences may be removed by comparing treated and control subjects with the same values of the observed covariates, that is, subjects in the same matched set or stratum defined by the observed covariates. It is natural to ask when the standard methods for randomized experiments may be applied to matched or stratified data from an observational study. This chapter discusses a model for an observational study in which there is overt bias but no hidden bias. The model is, at best, one of many plausible models, but it does clarify when methods for randomized experiments may be used in observational studies, and so it becomes the starting point for thinking about hidden biases. Dealing with hidden bias is the focus of most of the later chapters.

Keywords

Propensity Score Matched Pair Treatment Assignment Bibliographic Note Hide Bias 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Becker, H. S. (1996) The epistemology of qualitative research. In: Ethnography and Human Development, R. Jessor, A. Colby, and R. Shweder, eds., Chicago: University of Chicago Press, pp. 53–72.Google Scholar
  2. Bishop, Y., Fienberg, S., and Holland, P. (1975) Discrete Multivariate Analysis. Cambridge, MA: MIT Press.zbMATHGoogle Scholar
  3. Blumer, H. (1969) The methodological position of symbolic interactionism. In: H. Blumer, Symbolic Interactionism: Perspective and Method. Berkeley: University of California Press.Google Scholar
  4. Breslow, N. and Day, N. (1980) The Analysis of Case-Control Studies. Volume I of Statistical Methods in Cancer Research. Lyon, France: International Agency for Research on Cancer of the World Health Organization.Google Scholar
  5. Canner, P. (1984) How much data should be collected in a clinical trial? Statistics in Medicine, 3, 423–432.CrossRefGoogle Scholar
  6. Canner, P. (1991) Covariate adjustment of treatment effects in clinical trials. Controlled Clinical Trials, 12, 359–366.CrossRefGoogle Scholar
  7. Cochran, W. G. (1957) The analysis of covariance. Biometrics, 13, 261–281.MathSciNetCrossRefGoogle Scholar
  8. Cochran, W. G. (1965) The planning of observational studies of human populations (with Discussion). Journal of the Royal Statistical Society, Series A,128, 134–155.Google Scholar
  9. Cochran, W. G. (1968) The effectiveness of adjustment by subclassification in removing bias in observational studies. Biometrics, 24, 205–213.MathSciNetCrossRefGoogle Scholar
  10. Cochran, W. G. and Rubin, D. B. (1973) Controlling bias in observational studies: A review. Sankya, Series A, 35, 417–446.zbMATHGoogle Scholar
  11. Cole, P. (1979) The evolving case-control study. Journal of Chronic Diseases, 32, 15–27.CrossRefGoogle Scholar
  12. Coleman, J., Hoffer, T., and Kilgore, S. (1982) Cognitive outcomes in public and private schools. Sociology of Education, 55, 65–76.CrossRefGoogle Scholar
  13. Cornfield, J. (1951) A method of estimating comparative rates from clinical data: Applications to cancer of the lung, breast and cervix. Journal of the National Cancer Institute, 11, 1269–1275.Google Scholar
  14. Cox, D. R. (1970) The Analysis of Binary Data. London: Methuen.zbMATHGoogle Scholar
  15. Cox, D. R. (1958) The Planning of Experiments. New York: Wiley.Google Scholar
  16. Dehejia, R. H. and Wahba, S. (1999) Causal effects in nonexperimental studies: Reevaluating the evaluation of training programs. Journal of the American Statistical Association, 94, 1053–1062.CrossRefGoogle Scholar
  17. Emerson, R. M. (1981) Observational field work. Annual Review of Sociology, 7, 351–378.CrossRefGoogle Scholar
  18. Fleiss, J. (1981) Statistical Methods for Rates and Proportions. New York: Wiley.zbMATHGoogle Scholar
  19. Gastwirth, J. (1988) Statistical Reasoning in Law and Public Policy. New York: Academic.zbMATHGoogle Scholar
  20. Goldberger, A. and Cain, G. (1982) The causal analysis of cognitive outcomes in the Coleman, Hoffer, and Kilgore report. Sociology of Education, 55, 103–122.CrossRefGoogle Scholar
  21. Greenhouse, S. (1982) Cornfield’s contributions to epidemiology. Biometrics, 38S, 33 46.Google Scholar
  22. Hamilton, M. (1979) Choosing a parameter for 2 × 2 table or 2 × 2 × 2 table analysis. American Journal of Epidemiology, 109, 362–375.Google Scholar
  23. Heckman, J. J., Ichimura, H., and Todd, P. (1998) Matching as an econometric evaluation estimator. Review of Economic Studies, 65, 261–294.MathSciNetzbMATHCrossRefGoogle Scholar
  24. Hirano, K., Imbens, G. W., and Ridder, G. (2000) Efficient estimation of average treatment effects using the estimated propensity score. National Bureau of Economic Research, Working Paper T0251.Google Scholar
  25. Holland, P. and Rubin, D. (1988) Causal inference in retrospective studies. Evaluation Review, 12, 203–231.CrossRefGoogle Scholar
  26. Imbens, G. W. (2000) The role of the propensity score in estimating doseresponse functions. Biometrika, 87, 706 – 710.MathSciNetzbMATHCrossRefGoogle Scholar
  27. Joffe, M. M. and Rosenbaum, P. R. (1999) Propensity scores. American Journal of Epidemiology, 150, 327–333.CrossRefGoogle Scholar
  28. Katz, J. (2001) Analytic induction. In: International Encyclopedia of Social and Behavioral Sciences, Oxford: Elsevier Science Limited, to appear.Google Scholar
  29. Kitagawa, E. (1964) Standardized comparisons in population research. Demography, 1, 296–315.Google Scholar
  30. Kleinbaum, D., Kupper, L., and Morgenstern, H. (1982) Epidemiologic Research. Belmont, CA: Wadsworth.Google Scholar
  31. Mantel, N. (1973) Synthetic retrospective studies. Biometrics, 29, 479486.Google Scholar
  32. Mantel, N. and Haenszel, W. (1959) Statistical aspects of retrospective studies of disease. Journal of the National Cancer Institute, 22, 719 – 748.Google Scholar
  33. Ming, K. and Rosenbaum, P. R. (2000) Substantial gains in bias reduction from matching with a variable number of controls. Biometrics, 56, 118–124.zbMATHCrossRefGoogle Scholar
  34. Morton, D., Saah, A., Silberg, S., Owens, W., Roberts, M., and Saah, M. (1982) Lead absorption in children of employees in a lead related industry. American Journal of Epidemiology, 115, 549–555.Google Scholar
  35. Mosteller, F. and Tukey, J. (1977) Data Analysis and Regression. Reading, MA: Addison-Wesley.Google Scholar
  36. Petersen, L. A., Normand, S., Daley, J., and McNeil, B. (2000) Outcome of myocardial infarction in Veterans Health Administration patients as compared with Medicare patients. New England Journal of Medicine, 343, December 28, 1934–1941.CrossRefGoogle Scholar
  37. Robins, J. M. and Ritov, Y. (1997) Toward a curse of dimensionality appropriate asymptotic theory for semi-parametric models. Statistics in Medicine, 16, 285–319.CrossRefGoogle Scholar
  38. Robins, J. M., Mark, S. D. and Newey, W. K. (1992) Estimating exposure effects by modeling the expectation of exposure conditional on confounders. Biometrics, 48, 479–495.MathSciNetzbMATHCrossRefGoogle Scholar
  39. Rosenbaum, P. R. (1984a) The consequences of adjustment for a concomitant variable that has been affected by the treatment. Journal of the Royal Statistical Society, Series A, 147, 656–666.CrossRefGoogle Scholar
  40. Rosenbaum, P. R. (1984b) Conditional permutation tests and the propensity score in observational studies. Journal of the American Statistical Association, 79, 565–574.MathSciNetCrossRefGoogle Scholar
  41. Rosenbaum, P. R. (1986) Dropping out of high school in the United States: An observational study. Journal of Educational Statistics, 11, 207 – 224.CrossRefGoogle Scholar
  42. Rosenbaum, P. R. (1987a) Model-based direct adjustment. Journal of the American Statistical Association, 82, 387–394.zbMATHCrossRefGoogle Scholar
  43. Rosenbaum, P. R. (1987b) The role of a second control group in an observational study (with Discussion) . Statistical Science, 2, 292–316.CrossRefGoogle Scholar
  44. Rosenbaum, P. R. (1988) Permutation tests for matched pairs with adjustments for covariates. Applied Statistics, 37, 401–411.MathSciNetCrossRefGoogle Scholar
  45. Rosenbaum, P. R. and Rubin, D. B. (1983) The central role of the propensity score in observational studies for causal effects. Biometrika, 70, 41–55.MathSciNetzbMATHCrossRefGoogle Scholar
  46. Rosenbaum, P. and Rubin, D. (1984) Reducing bias in observational studies using subclassification on the propensity score. Journal of the American Statistical Association, 79, 516–524.CrossRefGoogle Scholar
  47. Rosenbaum, P. R. and Silber, J. H. (2001) Matching and thick description in an observational study of mortality after surgery. Biostatistics, 2, 217–232.zbMATHCrossRefGoogle Scholar
  48. Rubin, D.B. (1977) Assignment to treatment group on the basis of a covariate. Journal of Educational Statistics, 2, 1–26.CrossRefGoogle Scholar
  49. Rubin, D.B. (1978) Bayesian inference for causal effects: The role of randomization. Annals of Statistics, 6, 34–58.MathSciNetzbMATHCrossRefGoogle Scholar
  50. Silber, J. H., Rosenbaum, P. R., Trudeau, M. E., Even-Shoshan, O., Chen, W., Zhang, X., and Mosher, R. E. (2001) Multivariate matching and bias reduction in the surgical outcomes study. Medical Care, to appear.Google Scholar
  51. Smith, H. L. (1997) Matching with multiple controls to estimate treatment effects in observational studies. Sociological Methodology, 27, 325–353.CrossRefGoogle Scholar
  52. Tunca, B. T. and Egeli, U. (1996) Cytogenetic findings on shoe workers exposed long-term to benzene. Environmental Health Perspectives, 104, supplement 6, 1313–1317.Google Scholar
  53. Ury, H. (1975) Efficiency of case-control studies with multiple controls per case: Continuous or dichotomous data. Biometrics, 31, 643–649.zbMATHCrossRefGoogle Scholar
  54. Walker, A. (1982) Efficient assessment of confounder effects in matched follow-up studies. Applied Statistics, 31, 293–297.CrossRefGoogle Scholar
  55. Walker, A., Jick, H., Hunter, J., Danford, A., Watkins, R., Alhadeff, L., and Rothman, K. (1981) Vasectomy and non-fatal myocardial infarction. Lancet, 13–15.Google Scholar
  56. Whitehead, R., Rosenbaum, P., and Carbone, P. (1984) Cisplatin, doxorubicin, cyclophosphamide, lomustine, and vincristine (PACCO) in the treatment of nonsmall cell bronchogenic carcinoma. Cancer Treatment Reports, 68, 771–773.Google Scholar

Copyright information

© Springer Science+Business Media New York 2002

Authors and Affiliations

  • Paul R. Rosenbaum
    • 1
  1. 1.Department of Statistics, The Wharton SchoolUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations