Author ORCID Identifier
Date of Graduation
Biostatistics, Bioinformatics and Systems Biology
Doctor of Philosophy (PhD)
Ya-Chen Tina Shih
Projecting the future cancer care cost is critical in health economics research and policy making. An indispensable step is to estimate cost trajectories from an incident cohort of cancer patients using longitudinal medical cost data, accounting for terminal events such as death, and right censoring due to loss of follow-up. Since the cost of cancer care and survival are correlated, a scientifically meaningful quantity for inference in this context is the mean cost trajectory conditional on survival. Many standard approaches for longitudinal and survival analysis are not valid for the problem. The research for my Ph.D. dissertation consists of three aims. In Aim 1, we developed a two-stage semiparametric likelihood-based method to estimate the conditional distribution of longitudinal medical cost trajectory given the time of terminal event. The cost data is assumed normal, which does not reflect the reality. So, for Aim 2, we developed a flexible model to address further challenges such as heteroscedasticity without imposing a cost data distributional assumption. In Aim 3, to conduct flexible and reliable inference on the estimated cost trajectory, we developed a longitudinal varying coefficient single-index model and computational optimization algorithm that is scalable to baseline feature inference with noise. For each of the aims, we provide theoretical and simulation-based justification for the proposed approach and apply the methods to estimate cancer patient cost trajectories from the Surveillance, Epidemiology, and End Results (SEER)-Medicare linked database.
Bivariate penalized spline; Generalized estimating equations; Joint modeling; Semiparametric model; SEER-Medicare