시간-종속적 공변량이 포함된 이분형 반복측정자료의 GEE를 이용한 분석에서 결측 체계에 따른 회귀계수 추정방법 비교

Abstract

Abstract When analyzing repeated binary data, the generalized estimating equations(GEE) approach produces con-sistent estimates for regression parameters even if an incorrect working correlation matrix is used. However,time-varying covariates experience larger changes in coefficients than time-invariant covariates across var-ious working correlation structures for finite samples. In addition, the GEE approach may give biasedestimates under missing at random(MAR). Weighted estimating equations and multiple imputation meth-ods have been proposed to reduce biases in parameter estimates under MAR. This article studies if thetwo methods produce robust estimates across various working correlation structures for longitudinal binarydata with time-varying covariates under different missing mechanisms. Through simulation, we observe thattime-varying covariates have greater differences in parameter estimates across different working correlationstructures than time-invariant covariates. The multiple imputation method produces more robust estimatesunder any working correlation structure and smaller biases compared to the other two methods.Keywords: Generalized estimating equations, multiple imputation, weighted estimating equations, MCAR,MAR.