A bias-corrected covariance estimator for improved inference when using an unstructured correlation with quadratic inference functions

Philip M. Westgate

doi:10.1016/j.spl.2013.02.021

A bias-corrected covariance estimator for improved inference when using an unstructured correlation with quadratic inference functions

Philip M. Westgate

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Notable bias can exist in the empirical covariance matrix of parameter estimates obtained from the quadratic inference function method that incorporates an unstructured working correlation. We therefore derive a bias correction. Via simulation, we show that the proposed correction leads to appropriate standard error estimation.

Original language	English
Pages (from-to)	1553-1558
Number of pages	6
Journal	Statistics and Probability Letters
Volume	83
Issue number	6
DOIs	https://doi.org/10.1016/j.spl.2013.02.021
State	Published - Jun 2013

Keywords

Correlated data
Efficiency
Generalized estimating equations
Marginal model
Working correlation structure

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1016/j.spl.2013.02.021

Cite this

@article{a1855cc1091c473e9da17aa6536ed120,

title = "A bias-corrected covariance estimator for improved inference when using an unstructured correlation with quadratic inference functions",

abstract = "Notable bias can exist in the empirical covariance matrix of parameter estimates obtained from the quadratic inference function method that incorporates an unstructured working correlation. We therefore derive a bias correction. Via simulation, we show that the proposed correction leads to appropriate standard error estimation.",

keywords = "Correlated data, Efficiency, Generalized estimating equations, Marginal model, Working correlation structure",

author = "Westgate, {Philip M.}",

year = "2013",

month = jun,

doi = "10.1016/j.spl.2013.02.021",

language = "English",

volume = "83",

pages = "1553--1558",

number = "6",

}

TY - JOUR

T1 - A bias-corrected covariance estimator for improved inference when using an unstructured correlation with quadratic inference functions

AU - Westgate, Philip M.

PY - 2013/6

Y1 - 2013/6

N2 - Notable bias can exist in the empirical covariance matrix of parameter estimates obtained from the quadratic inference function method that incorporates an unstructured working correlation. We therefore derive a bias correction. Via simulation, we show that the proposed correction leads to appropriate standard error estimation.

AB - Notable bias can exist in the empirical covariance matrix of parameter estimates obtained from the quadratic inference function method that incorporates an unstructured working correlation. We therefore derive a bias correction. Via simulation, we show that the proposed correction leads to appropriate standard error estimation.

KW - Correlated data

KW - Efficiency

KW - Generalized estimating equations

KW - Marginal model

KW - Working correlation structure

UR - http://www.scopus.com/inward/record.url?scp=84875778338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875778338&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2013.02.021

DO - 10.1016/j.spl.2013.02.021

M3 - Article

AN - SCOPUS:84875778338

SN - 0167-7152

VL - 83

SP - 1553

EP - 1558

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

IS - 6

ER -

A bias-corrected covariance estimator for improved inference when using an unstructured correlation with quadratic inference functions

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this