Activity Number:
|
417
- Contributed Poster Presentations: Section on Statistics in Epidemiology
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistics in Epidemiology
|
Abstract #323483
|
|
Title:
|
Correlating a Right Censored Risk Factor with a Neuropathology Finding
|
Author(s):
|
Richard Kryscio* and Qiwen Kang and Erin L Abner and Peter T Nelson and David Fardo and Frederick A Schmitt
|
Companies:
|
Univ of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky and University of Kentucky
|
Keywords:
|
right censored risk ;
logistic regression ;
Weibull ;
mild cognitive impairment
|
Abstract:
|
We propose a maximum likelihood procedure for measuring the association between a risk factor subject to right censoring and the presence/absence of a neuropathology outcome. The methodology, based on a logistic regression model, assumes the probability that the risk factor which is right censored may depend on the neuropathology outcome and other covariates in the model but does not depend on the censored value itself. The special case when the risk factor is Weibull distributed will be discussed. Data on 343 mild cognitive impairment (MCI) cases derived from the Statistical Modeling of Aging and Risk of Transition (SMART) project who died and came to autopsy will illustrate the novel method and results. The SMART project combines autopsy data from five centers conducting longitudinal studies on dementia. The application will focus on correlating length of time in the MCI state with the presence of brain arteriolosclerosis pathology at the moderate to severe stage with adjustment for other risks including gender and age at death. The time in MCI is subject to right censoring since some study participants are cognitively impaired when they were recruited to the study.
|
Authors who are presenting talks have a * after their name.