Maximum likelihood estimation has been extensively used in the joint analysisof repeated measurements and survival time. However, there is a lack oftheoretical justification of the asymptotic properties for the maximumlikelihood estimators. This paper intends to fill this gap. Specifically, weprove the consistency of the maximum likelihood estimators and derive theirasymptotic distributions. The maximum likelihood estimators are shown to besemiparametrically efficient.
展开▼
