Activity Number:
|
72
- Recent Advances in Nonparametric Statistical Methods II
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract #327181
|
Presentation
|
Title:
|
Adjustments of Mann-Whitney U-Statistics for Comparing Sojourn Time Distributions in Observational Studies When Transition Time Are Right Censored
|
Author(s):
|
Yichen Chen* and Somnath Datta
|
Companies:
|
University of Florida and University of Florida
|
Keywords:
|
censored data;
observational studies;
Mann-Whitney;
Wilcoxon rank sum test;
U-statistics;
sojourn time
|
Abstract:
|
We propose adjustments to the classical two-sample Mann-Whitney U-statistics when distributions of sojourn time are compared in an observational study on a multistate system. Our adjustments are geared towards removing potential bias come from right censoring of transition times (state entry or exist times) and presence of confounding covariates. The Mann-Whitney U-statistics are re-weighted and normalized based on a combination of inverse probability of censoring weights and propensity score based weights. Two types of the adjustments are proposed corresponding to two different selection methods. The dependence of censoring time on state entry time, group membership and/or observed covariates is considered. Simulation results are used to illustrate the performance of the adjusted Mann-Whitney U-statistics under different censoring mechanisms and selection approaches. A real data set on recovery process following bone marrow transplant for acute leukemia was applied to exemplify its usefulness.
|
Authors who are presenting talks have a * after their name.