|
Activity Number:
|
206
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305480 |
|
Title:
|
Parametric Inference from Window-Censored Renewal Processes and Applications
|
|
Author(s):
|
Yanxing Zhao*+ and H. N. Nagaraja
|
|
Companies:
|
The Ohio State University and The Ohio State University
|
|
Address:
|
632 Trumbull Court, Columbus, OH, 43210,
|
|
Keywords:
|
renewal process ; window censoring ; maximum likelihood estimate ; Fisher information ; simulation
|
|
Abstract:
|
Suppose we have m independent, identical renewal processes observed over a fixed length of time. Only the renewals that occur within an observation window are recorded. Assuming a parametric model for the renewal time distribution, we obtain the maximum likelihood estimates (MLE) and study their properties. We consider the exponential, gamma distributions in our study. We compute the Fisher information matrix using simulation. We use it to study the large sample properties of the MLE and to determine optimal window length when the total time of observation is fixed. Our results are applied to a longitudinal dataset of lupus relapses.
|
