Events

Naghmeh Daneshi PhD in Mathematical Sciences Dissertation Defense
Friday, May 31, 2019 - 11:00am

Ph.D. in Mathematical Sciences Dissertation Defense

Naghmeh Daneshi 

Estimation of association between a longitudinal marker and interval censored progression times.

MS Statistics, Portland State University, 2013        
BS Statistics, Azad University Tehran, 2008

Defense date:      Friday, May 31, 2019
Time:                  11:00AM 
Location:             Cramer Hall room 325
                           1721 SW Broadway, Portland

Committee chair:                          Jong Sung Kim, PhD
Committee members:                   Robert Fountain, PhD
                                                    Subhash Kochar, PhD 
                                                    Alexis Dinno, PhD 
Graduate Office representative:    Wayne Wakeland, PhD

Abstract

In longitudinal data analysis, we are studying subjects over time for occurrence of an event. Often in longitudinal studies, some subjects complete their follow-up visits but others miss their visits due to various reasons. For those who miss follow-up visits, they learn that the event of interest has already happened, when they come back. In this case, not only are their event times interval-censored, but also their time-dependent measurements are incomplete. This problem was motivated by a national longitudinal survey of youth data. We study such events under various conditions. The event of interest could have a single progression state or multiple progression stages. Maximum likelihood estimation (MLE) method, based on EM algorithm, is used for parameter estimation; and missing information principle (Louis (1982)) is applied to estimate the variance-covariance matrix of the MLEs. Simulation studies demonstrate that the proposed methods work well in terms of bias, standard error, and power for samples of moderate size. Furthermore, variable selection techniques and multicollinearity between the covariates has been studied. The national longitudinal survey of youth (NLSY97) data is analyzed for illustration.