Bias correction in group sequential analysis with correlated data

This paper focuses on the bias of the group sequential estimate of treatmen t effect for correlated data using the generalized estimating equation (GEE ) method and the Lan and DeMets alpha-spending function. Linear and logisti c regressions are used to examine (a) the magnitude of the bias of a sequen tial estimate with correlated data; (b) the influence of the true correlati on structure on bias. A bias-corrected sequential estimate is proposed usin g a Brownian motion approximation and numerical simulation. Logistic regres sion is used to illustrate and to assess the performance of the proposed me thod.