|
Activity Number:
|
48
- Academics Industry Perspectives on Cancer Data Innovations: Simultaneous Inference, Inconsistency, and Clinical Response
|
|
Type:
|
Topic-Contributed
|
|
Date/Time:
|
Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #317477
|
|
|
Title:
|
Inconsistency of Model Specifications in Generalized Linear Models
|
|
Author(s):
|
Changyong Feng* and Hongyue Wang and Laurent Glance and Xin Tu
|
|
Companies:
|
University of Rochester and University of Rochester and University of Rochester and University of California, San Diego
|
|
Keywords:
|
Conditional expectation;
linear regression;
logistic regression
|
|
Abstract:
|
Given a data set, depending on the purpose of the study, we may specify many regression models. The properties of conditional expectation put a natural consistency constraint on the specifications of these models. In this manuscript we show that inconsistent specifications can easily occur in linear and logistic regression models even under some most favorable assumptions of the structure of the covariates. Same problem will happen to other generalized linear models with nonlinear link functions.
|
Authors who are presenting talks have a * after their name.
