Variance estimation for the instrumental variables approach to measurement error in generalized linear models
James W. Hardin
Arnold School of Public Health
University of South Carolina
Columbia, SC 29208
|
Raymond J. Carroll
Department of Statistics MS-3143
Texas A&M University
College Station, TX 77843-3143
|
Abstract. This paper derives and gives explicit formulas for a derived sandwich
variance estimate. This variance estimate is appropriate for generalized
linear additive measurement error models fitted using instrumental
variables. We also generalize the known results for linear regression. As
such, this article explains the theoretical justification for the sandwich
estimate of variance utilized in the software for measurement error
developed under the Small Business Innovation Research Grant (SBIR) by
StataCorp. The results admit estimation of variance matrices for measurement
error models where there is an instrument for the unknown covariate.
View all articles by these authors:
James W. Hardin, Raymond J. Carroll
View all articles with these keywords:
sandwich estimate of variance, measurement error, White's estimator, robust variance, generalized linear models, instrumental variables
Download citation: BibTeX RIS
Download citation and abstract: BibTeX RIS
|
