ABSTRACT
In clinical studies, different types of outcomes (multivariate responses) can be observed from the same subject. This chapter presents data analysis for multivariate responses where at least one response is time-to-event. The R package jointdhglm supports a joint modeling framework based on the h-likelihood for analyzing jointly the repeated-measures data and event-time data including competing-risks events. The models for repeated-measure response and time-to-event time with censoring indicator status are defined by the jointmodeling() function by specifying their link functions, linear predictors, and distributions of random effects. In clinical trials, various response variables of interest are measured repeatedly over time on the same subject, which can be analyzed by using the mdhglm package. Both longitudinal and survival data were collected in a recent clinical trial to compare the efficacy and safety of two antiretroviral drugs in treating patients who had failed or were intolerant of zidovudine (AZT) therapy.
