Complexity in Simple Regression Models with Binary Disease Outcome

• Activity Number: 222 - New Advances in Statistical Methods for Complex Data
• Type: Invited
• Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
• Sponsor: Section on Risk Analysis
• Author(s): Mei-Cheng Wang*
• Companies: Johns Hopkins University
• Keywords: Current status data; Birth-illness-death process; Logistic model; Sampling bias; Stationary process

Abstract

Cross-sectionally sampled data with binary disease outcome are commonly collected and analyzed in observational studies for identifying how covariates correlate with disease occurrence. As the progression of a disease typically involves both disease status and duration, this paper considers how the binary disease outcome is connected to the progression of disease through the birth-illness-death process. In general, the distribution of the cross-sectional binary outcome could be very different from the population risk distribution. The cross-sectional risk probability is determined jointly by the population risk probability together with the ratio of duration of diseased state to the duration of disease-free state. Using the logistic model as an illustrating example, we examine the bias from cross-sectional data and argue that the bias can almost never be avoided. We present an approach which treats the binary outcome as a specific type of current status data and offers a compromised model on the basis of an age-specific risk probability. An analysis based on Alzheimer's disease data is presented to illustrate the proposed model approach.