|
Activity Number:
|
409
- Survival Analysis I
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #329948
|
Presentation
|
|
Title:
|
A General Class of Weighted Semiparametric Models for Recurrent Event Data
|
|
Author(s):
|
Russell Stocker* and Akim Adekpedjou
|
|
Companies:
|
Indiana University of Pennsylvania and Missouri University of Science and Technology
|
|
Keywords:
|
Recurrent Events;
Biased Samples;
Survey Samples;
Emipircal Processes;
Survival Analysis;
Right Censoring
|
|
Abstract:
|
We propose a general class of weighted semiparametric models for recurrent event data. The weights represent the reciprocals of selection probabilities for units in a study. These can be known quantities that are used in situations such as survey sampling. Alternatively, they are unknown quantities that are estimated via logistic regression in studies that have a biased sample. Estimators are constructed and their associated asymptotic properties are established. Finite sample properties are investigated via a computer simulation study. A real data set is analyzed to illustrate the class of models.
|
Authors who are presenting talks have a * after their name.
