摘要：We derive three likelihood-based con dence intervals for the riskratio of two proportion parameters using a double sampling scheme for mis-classi ed binomial data. The risk ratio is also known as the relative risk.We obtain closed-form maximum likelihood estimators of the model param-eters by maximizing the full-likelihood function. Moreover, we develop threecon dence intervals: a naive Wald interval, a modi ed Wald interval, anda Fieller-type interval. We apply the three con dence intervals to cervi-cal cancer data. Finally, we perform two Monte Carlo simulation studiesto assess and compare the coverage probabilities and average lengths of thethree interval estimators. Unlike the other two interval estimators, the mod-i ed Wald interval always produces close-to-nominal con dence intervals forthe various simulation scenarios examined here. Hence, the modi ed Waldcon dence interval is preferred in practice.
