Abstract #301118

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #301118
Activity Number: 215
Type: Contributed
Date/Time: Tuesday, August 5, 2003 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract - #301118
Title: A Semiparametric Model for the Analysis of Multivariate Time-to-event Data with Interval Censoring
Author(s): Kenichi Yoshimura*+ and Hiroshi Nishiyama and Yasuo Ohashi
Companies: University of Tokyo and Tokyo University of Science and University of Tokyo
Address: Dept. of Biostatistics/Epidemiology, Tokyo 113-0033, , , Japan
Keywords: Gibbs sampling ; interval censoring ; multivariate data ; proportional hazards model ; regression ; survival analysis
Abstract:

This presentation proposes a marginal approach to fitting the proportional hazards model to multivariate interval-censored or grouped time-to-event data. Interval censoring of multiple events can be observed when the events are not directly discernable but are diagnosed only by periodical laboratory tests or clinical examination. For each event, this approach maximizes a marginal likelihood that is the sum over all possible rankings that are consistent with the observed censored data. These possible rankings are generated from the proportional hazards family of the distribution of rankings by the Gibbs sampling scheme. As in the Cox proportional hazards model, the specification of the baseline hazard function is not required. A robust and consistent estimator for the covariance matrix of the parameters is developed that accounts for the correlations between events and the incomplete nature of the data. A simulation study is performed to compare the performance of our approach and others, including the one based on discrete analogue of the proportional hazards model and the one based on several imputation methods, e.g. midpoint, left- and right-endpoint imputation.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003