Explicit formulas are provided for estimating the attributable risk ratio among the exposed and the entire target population utilizing matched-pairs data. Large-sample standard errors and corresponding confidence intervals are provided. These estimates can be obtained from the cross-classification frequencies of matched pairs by disease and exposure status in the usual 2 X 2 table. The key to the development of these formulas lies in recognizing that attributable risk among the exposed is a direct function of the odds ratio, and population attributable risk is a direct function of the odds ratio and exposure prevalence among only the cases (assuming a rare disease). The formulas presented in this paper require only a calculator for computation. The methodology is illustrated with data from a matched-pairs case-control study of oral conjugated estrogens and endometrial cancer.
PIP: A methodology is presented for estimating attributable risk ratio along with their large-sample standard errors, and corresponding confidence intervals from a matched-pairs case-control study design. The methodology is illustrated with an example from a matched-pairs case-control study of endometrial cancer and oral conjugated estrogens. The complete methods and study results are provided by antunes et al.; the portions of the data used in this example is reproduced by Schlesselman. Each case in this study was matched to a hospital control on the basis of hospital, data of admission (within 6 months), age (within 5 years), and race. These 183 matched pairs then were classified according to their exposure status (ever versus never) with regard to the use of estrogens. The sample odds ratio of 6.14 indicates that the risk for endometrial cancer was over 6 times as great among women who used estrogens compared with women who never used oral conjugated estrogens. The sample attributable risk of 0.837 among the exposed suggests that among women who have taken oral conjugated estrogens, 83.7% of endometrial cancers were associated with such use, reflecting the sizable strength of the exposure-disease association as measured by the odds ratio. Because less than 1/3 of the cases were so exposed, it is estimated that only 25% of the disease in the general population can be attributed to taking oral conjugated estrogens. This highlights the appeal of population attributable risk in incorporating both the strength of the association and the prevalence of exposure to the risk factor.