|
Abstract:
|
In longitudinal data analysis, to assess a predictor impact on a time-varying response, it is important to account for heterogeneity in its trajectory shape among subjects, while allowing the predictor impact to vary for different sub-groups. To address this problem, we propose a flexible semiparametric Bayes approach relying on a local partition process prior, allowing flexible local borrowing of information across subjects and sub-groups. Methods are developed for local hypothesis testing, allowing for identifying the significant time windows of the predictor impact, while inducing a multiplicity adjustment in identifying sub-group specific effects. Posterior computation proceeds via an efficient MCMC algorithm relying on the exact block Gibbs sampler to avoid finite approximations to the nonparametric model. The methods are assessed using simulation studies.
|
