Uncertainty analysis of multiple epidemiological studies using frequency distributions of relative risks

A new format for presenting uncertainty in the results of multiple epidemiologic studies of the same outcome is suggested. A set of 95% confidence intervals for relative risk, RR, is transformed to a frequency distribution of the normalized deviations, ln(RR)/SE(ln(RR)), from the null value In(RR)=0 (RR=1). It is assumed that deviations from RR=1 are due to unaccounted residual biases and we compare the distribution of these deviations with the distributions of the actual errors in physical measurements where the true values have subsequently become known, and the incidence of large errors can be estimated. Comparison of these distributions can, by analogy, help to understand how convincing is the evidence of elevated risk in observational studies.

[1]  A. I. Shlyakhter,et al.  An improved framework for uncertainty analysis: Accounting for unsuspected errors , 1994 .

[2]  A. I. Shlyakhter,et al.  Monte Carlo simulation of uncertainties in epidemiological studies: an example of false-positive findings due to misclassification , 1995, Proceedings of 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society.

[3]  Policy Coordination,et al.  Health effects of low-frequency electric and magnetic fields , 1992 .

[4]  E. Fontham,et al.  Lung cancer in nonsmoking women: a multicenter case-control study. , 1991, Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology.

[5]  A. I. Shlyakhter,et al.  Estimating uncertainty in physical measurements, observational and environmental studies: lessons from trends in nuclear data , 1993, 1993 (2nd) International Symposium on Uncertainty Modeling and Analysis.

[6]  A R Feinstein,et al.  Scientific standards in epidemiologic studies of the menace of daily life. , 1988, Science.

[7]  E. Seymann,et al.  Neutron scattering lengths: A survey of experimental data and methods , 1991 .

[8]  Oar,et al.  Respiratory health effects of passive smoking: lung cancer and other disorders , 1993 .

[9]  A. Gross.  The risk of lung cancer in nonsmokers in the United States and its reported association with environmental tobacco smoke , 1995 .

[10]  E. Fontham.  Lung cancer in nonsmoking women , 1991 .

[11]  A R Feinstein,et al.  A collection of 56 topics with contradictory results in case-control research. , 1988, International journal of epidemiology.