Considerable recent interest has focused on doubly robust estimatorsfor a population mean response in the presence of incomplete data,which involve models for both the propensity score and the regressionof outcome on covariates. The ``usual" doubly robust estimator mayyield severely biased...

In many longitudinal studies, it is of interest to characterize the relationship between a time-to-event (e.g. survival) and time-dependent and time-independent covariates. Time-dependent covariates are generally observed intermittently and with error.For a single time-dependent covariate, a...

We propose a method of simultaneous model selection and estimation in additive regression models (ARMs) forindependent normal data. We use the mixed model representation of the smoothing spline estimators of thenonparametric functions in ARMs, where the importance of these functions is...

A variety of complications arise when imperfect measurements, W, are observed in place of a true variable of interest, X. In the context of linear and non-linear regression models where X is a covariate, regression parameter estimators obtained when W is substituted for X may be substantially...

There are two topics in this dissertation. The first topic is 'Smoothing Parameter Selection in Nonparametric Generalized Linear Models via Sixth-order Laplace Approximation' and the second topic is 'Smoothing Spline-based Score Tests for Proportional Hazards Models'.We present a new approach...

In many studies, a primary endpoint and longitudinal measures of a continuous response are collected for each participant along with other covariates, and the association between the primary endpoint and features of the longitudinal profiles is of interest. One challenge is that the features of...

Model selection is important for longitudinal data analysis. But up to date little work has been done on variable selection for generalized linear mixed models (GLMM). In this paper we propose and study a class of variable selection methods. Full likelihood (FL) approach is proposed for...

Conventionally, values of nuisance parameters given in a statistical design are often erroneous, thus may result in overpowering or underpowering a test using traditional sample size calculations. In this thesis, we propose to use Fisher Information data monitoring in group sequential studies to...