|
Activity Number:
|
561
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #305372 |
|
Title:
|
Covariate Bias Induced by Length-Biased Sampling of Failure Times
|
|
Author(s):
|
Pierre-Jerome Bergeron*+ and Masoud Asgharian and David B. Wolfson
|
|
Companies:
|
University of Ottawa and McGill University and McGill University
|
|
Address:
|
585 King Edward, Ottawa, ON, K1N 6N5, Canada
|
|
Keywords:
|
length-biased sampling ; left truncation ; right censoring ; prevalent cohort
|
|
Abstract:
|
In standard regression, though one samples from the joint distribution of the variable of interest and covariates, the analysis is carried out conditionally because the covariate distribution is considered ancillary to the parameters of interest. Length-biased sampling with respect to the response variable, as can be the case with survival data from prevalent cohorts, results in biased sampling of the covariates. Their marginal distribution holds information about the parameters, thus one should adapt the usual methods of analysis to account for it. We present an adjusted (joint) likelihood approach for length-biased left-truncated right-censored data. It is shown that taking the covariates into consideration can yield more efficient estimates. The methods are applied to data on survival with dementia from the Canadian Study on Health and Aging (CSHA).
|
