Confidence Intervals for an Exposure-Adjusted Incidence Rate Difference with Applications to Clinical Trials

• Activity Number: 674
• Type: Topic Contributed
• Date/Time: Thursday, August 8, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Junyuan Wang*+ and G. Frank Liu and Ken Liu and Snavely Duane
• Companies: BMS and Merck Res Labs and Merck & Co., Inc. and Merck & Co., Inc.
• Keywords: Poisson distribution ; exposure adjusted incidence rate ; confidence interval ; adverse experiences ; clinical trials

Abstract

To summarize safety data such as clinical adverse experiences in clinical trials with a moderate to long-term follow-up, we may use a measurement which accounts for the follow-up duration. The incidence rate, which uses the total person-time follow-up in a treatment group as the denominator, is one of these measures. When treatment comparisons are based on the difference of the incidence rates, it is of interest to construct confidence intervals (CI)for the rate differences. We first discuss the assumptions and scenarios in which the exposure adjusted incidence rate may be appropriate. Then we review several methods of calculating CIs for the difference of incidence rates assuming that the number of events come from a Poisson distribution. The methods considered include Wald's method, the two-by-two table method, the conditional Miettinen and Nurminen (MN) method, and the MN method. For the first three methods, explicit CIs can be obtained. For the MN method, numerical solution process is required. The simulation results show that the MN method outperforms the other three in terms of the coverage of the CI, especially when the rates or the number of events are small.