Generalized information matrix tests for detecting model misspecification

Generalized Information Matrix Tests (GIMTs) have recently been used for detecting the presence of misspecification in regression models in both randomized controlled trials and observational studies. In this paper, a unified GIMT framework is developed for the purpose of identifying, classifying, a...

Full description

Saved in:
Bibliographic Details
Published in:Econometrics 2016-12, Vol.4 (4), p.1-24
Main Authors: Golden, Richard M, Henley, Steven S, White, Halbert, Kashner, T. Michael
Format: Article
Language:English
Subjects:
asymptotic theory
Econometrics
Economic models
Economic statistics
Economic theory
Equality
Hypotheses
Information Matrix Test
information ratio
logistic regression
Medical research
misspecification
Observational studies
Probability
Random variables
Regression analysis
Residuals
Simulation
simulation study
specification analysis
Statistics
Studies
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Generalized Information Matrix Tests (GIMTs) have recently been used for detecting the presence of misspecification in regression models in both randomized controlled trials and observational studies. In this paper, a unified GIMT framework is developed for the purpose of identifying, classifying, and deriving novel model misspecification tests for finite-dimensional smooth probability models. These GIMTs include previously published as well as newly developed information matrix tests. To illustrate the application of the GIMT framework, we derived and assessed the performance of new GIMTs for binary logistic regression. Although all GIMTs exhibited good level and power performance for the larger sample sizes, GIMT statistics with fewer degrees of freedom and derived using log-likelihood third derivatives exhibited improved level and power performance.
ISSN:2225-1146
2225-1146
DOI:10.3390/econometrics4040046