|
Activity Number:
|
76
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 6, 2006 : 8:00 PM to 9:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #305588 |
|
Title:
|
Survival Instantaneous Log-Odds Ratio from Empirical Functions
|
|
Author(s):
|
JungAh Jung*+ and J. Wanzer Drane
|
|
Companies:
|
Novartis Pharmaceuticals Corporation and University of South Carolina
|
|
Address:
|
Oncology Biostatistics and Statistical Reporting, East Hanover, NJ, 07936,
|
|
Keywords:
|
odds ratio ; log-or ; instantaneous LOR ; survival ILOR ; copula
|
|
Abstract:
|
The objective of this work is to introduce and derive the survival instantaneous log-odds ratio (SILOR) and its standard error and compare it to logistic regression. Hip fracture on white women, AGE and BMI from NHANES III, were used to calculate empirical survival functions (SF) for the adverse health outcome (AHO) and non-AHO. A stable copula was used to create a parametric bivariate SF that was fitted to the empirical bivariate SF. PROC NLIN in SAS was used to estimate the parameters of the copula models. Variations were observed that could not be anticipated and that were poorly, if at all, modeled by logistic regression. The bivariate SF had SILOR contours the nonconstancy of SILOR. The proposed method out-performed logistic regression. The present method is straightforward, and it captures all but random variability of the data.
|
