Comparison Of Interval Estimation For Relative Risk Ratio With Rare Events

  • Published : 2004.04.01


One of objectives in epidemiologic studies is to detect the amount of change caused by a specific risk factor. Risk ratio is one of the most useful measurements in epidemiology. When we perform the inference for this measurement with rare events, the standard approach based on the normal approximation may fail, in particular when there are no disease cases observed. In this paper, we discuss and evaluate several existing methods for constructing a confidence interval of risk ratio through simulation when the disease of interest is a rare event. The results in this paper provide guidance with how to construct interval estimates for risk difference and risk ratio when there are no disease cases observed.


  1. The American Statistician v.35 Bayesian Risk Ratio Analysis Aitchison,J.;Bason-Shone,J.
  2. Statistics in Medicine v.15 Comparison Methods for Calculating Confidence intervals for Vaccine Efficiency Ewell,M.<2379::AID-SIM457>3.0.CO;2-L
  3. Biometrics v.44 Approximate interval estimation of the ratio of binomial parameters : A review and corrections for skewness Gart,J.J.;Nam,J.M.
  4. Biometrics v.34 Obtaining Confidence Intervals for the Risk Ratio in Cohort Studies Katz,D.;Baptista,J.;Azen,S.P.;Pikel,M.C.
  5. Biometrics v.40 Confidence limits for the ratio of two biomial proportions Koopman,P.A.R.
  6. Biometrics v.40 Confidence bounds for the difference between two probabilities Mee,R.W.
  7. Statist. Med. v.4 Comparative analysis of two rates Miettinen,O.S.;M.Nurminen
  8. Journal of the American Statistics Association v.52 Two confidence intervals for the ratio of two probabilities and some measures of effectiveness Neother,G.E.
  9. Biometrika v.62 The distribution of Levin's measure of attributable risk Walter,S.D.