Abstract
dc:description.abstractThis thesis analyzes censored data in recurrent event, longitudinal, and survival settings. In Chapter 2, a straightforward, flexible methodology is proposed to estimate parameters indexing the conditional means and variances of the interevent times in a recurrent event process. In Chapter 3, we analyze discretely and informatively observed multivariate continuous longitudinal data; missingness and terminal events are introduced in Chapter 4. In Chapters 3 and 4, the inter-event times are considered a nuisance and the goal is to estimate parameters driving the longitudinal process. To do this, we propose an innovative conditional estimating equation that can model individual trajectories. Finally, Chapter 5 uses these subject-specific trajectories to estimate parameters indexing the terminal event process and predict future survival for arbitrary subjects.
Degree
thesis:*- Name thesis:degree_name
- Ph. D., Statistics
- Level thesis:degree_level
- Doctor of Philosophy
- Discipline thesis:degree_discipline
- Statistics
- Grantor
- Cornell University
- Year dc:date.issued
- 2011
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Clement, David
- Chair dc:contributor.chair
-
- Strawderman, Robert Lee
- Committee members dc:contributor.committeemember
-
- Hooker, Giles J.
- Wells, Martin Timothy
Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Dc Identifier Bibid
- 8213809