Chen, Xiaotian
(2015)
Association Analysis of Successive Events and Diagnostic Accuracy Analysis for Competing Risks Data.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
Abstract
In this dissertation there are two overarching objectives to address the challenges in analyzing data from the Bipolar Disorder Center for Pennsylvanians (BDCP) study.
First, we aim to close a methodological gap in analyzing durations of successive events that are subject to induced dependent censoring as well as competing-risk censoring. In the BDCP study, some patients who managed to recover from their symptomatic entry later developed a new depressive or manic episode. It is of clinical interest to quantify the association between time to recovery and time to recurrence in patients with bipolar disorder. The estimation of the bivariate distribution of the gap times with independent censoring has been well studied. However, the existing methods cannot be applied to failure times censored by competing causes. Bivariate cumulative incidence function (CIF) has been used to describe the joint distribution of parallel event times that involve multiple causes. However, there is no method available for successive events with competing-risk censoring. Therefore, we extend the bivariate CIF to successive events data, and propose nonparametric estimators. Moreover, an odds ratio measure is proposed to describe the cause-specific dependence, leading to the development of a formal test for independence of successive events. The method is evaluated through simulations and also applied to the real dataset.
Next, motivated by another subgroup of subjects in the BDCP study who entered the study in a euthymic state, we investigate the Receiver Operating Characteristic (ROC) approach for a competing-risk censored outcome, when the diagnostic marker of interest, number of previous episodes, can be treated as censored observations. We propose two methods to estimate the discrimination measures such as sensitivity, specificity, positive and negative predictive values and the Area Under the Curve (AUC). We also develop cause-specific tests to compare two markers' discriminatory abilities in separating those subjects who will experience the cause-specific event by some time point from those who will not. The proposed estimators and tests have satisfactory performance in simulation studies. We also illustrate these methods through the analysis of the BDCP subsample.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
11 September 2015 |
| Date Type: |
Publication |
| Defense Date: |
25 June 2015 |
| Approval Date: |
11 September 2015 |
| Submission Date: |
22 June 2015 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
68 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Dietrich School of Arts and Sciences > Statistics |
| Degree: |
PhD - Doctor of Philosophy |
| Thesis Type: |
Doctoral Dissertation |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
Bipolar disorder; Competing risks; Cumulative incidence function; Inverse probability weighting; Odds ratio; Successive events; AUC; Discrimination; ROC |
| Date Deposited: |
11 Sep 2015 19:48 |
| Last Modified: |
15 Nov 2016 14:28 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/25447 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[img]](http://d-scholarship.pitt.edu/style/images/fileicons/application_pdf.png)
![[feed]](/images/feed-icon-32x32.png){kind=icon}