Tests for Comparing the Progression of an Epidemic in Two Groups

Abstract

The severity of an epidemic is quantied by measures like the death rate, the cure rate, the case fatality rate (CFR) and the real-time fatality rate. In an outbreak of a completely new infectious disease, estimation of the fatality over the course of the epidemic is of clinical and epidemiological importance. The fatality rates may differ in different populations due to some factors like the etiological characteristics, geographical conditions or the treatment and intervention procedures. In this article, we suggest some measures related to the real-time fatality rate for this comparison. We propose two-sample tests for equality of these measures and a test for the proportionality of the crude transition death rates and derive the asymptotic properties of the test statistics. We propose sequential tests that can be carried out as the epidemic progresses. We apply the tests to real data in Beijing and Taiwan.