Case–Control Analysis with Partial Knowledge of Exposure Misclassification Probabilities

Authors

  • Paul Gustafson,

    Corresponding author
    1. Department of Statistics, University of British Columbia, Vancouver, British Columbia V6T 1Z2, Canada
    Search for more papers by this author
  • Nhu D. Le,

    1. Department of Statistics, University of British Columbia, Vancouver, British Columbia V6T 1Z2, Canada
    2. BC Cancer Agency, 600 West 10th Avenue, Vancouver, British Columbia V5Z 4E6, Canada
    Search for more papers by this author
  • Refik Saskin

    1. Department of Statistics, University of British Columbia, Vancouver, British Columbia V6T 1Z2, Canada
    2. Department of Microbiology, Mount Sinai Hospital, 600 University Avenue, Toronto, Ontario M5G 1X5, Canada
    Search for more papers by this author

*email:gustaf@stat.ubc.ca

Abstract

Summary. Consider case-control analysis with a dichotomous exposure variable that is subject to misclassification. If the classification probabilities are known, then methods are available to adjust odds-ratio estimates in light of the misclassification. We study the realistic scenario where reasonable guesses, but not exact values, are available for the classification probabilities. If the analysis proceeds by simply treating the guesses as exact, then even small discrepancies between the guesses and the actual probabilities can seriously degrade odds-ratio estimates. We show that this problem is mitigated by a Bayes analysis that incorporates uncertainty about the classification probabilities as prior information.

Ancillary