Logistic regression models with missing covariate values for complex survey data

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Maximum likelihood methods are used to incorporate partially observed covariate values in fitting logistic regression models. We extend these methods to data collected through complex surveys using the pseudo-likelihood approach. One can obtain parameter estimates of the logistic regression model using standard statistical software and their standard errors by Taylor series expansion or the jackknife method. We apply the approach to data from a two-phase survey screening for dementia in a community sample of African Americans age 65 and older living in Indianapolis. The binary response variable is dementia and the covariate with missing values is a daily functioning score collected from interviews with a relative of the study subject.

Original languageEnglish
Pages (from-to)2419-2428
Number of pages10
JournalStatistics in Medicine
Volume16
Issue number21
DOIs
StatePublished - Nov 15 1997

Fingerprint

Missing Covariates
Dementia
Logistic Regression Model
Survey Data
Covariates
Logistic Models
Pseudo-likelihood
Statistical Software
Binary Response
Jackknife
Taylor Series Expansion
Missing Values
Maximum Likelihood Method
Standard error
Screening
African Americans
Estimate
Software
Interviews
Surveys and Questionnaires

ASJC Scopus subject areas

  • Epidemiology

Cite this

Logistic regression models with missing covariate values for complex survey data. / Gao, Sujuan; Hui, Siu.

In: Statistics in Medicine, Vol. 16, No. 21, 15.11.1997, p. 2419-2428.

Research output: Contribution to journalArticle

@article{cd41c4dafeac408f8badfa4b83857705,
title = "Logistic regression models with missing covariate values for complex survey data",
abstract = "Maximum likelihood methods are used to incorporate partially observed covariate values in fitting logistic regression models. We extend these methods to data collected through complex surveys using the pseudo-likelihood approach. One can obtain parameter estimates of the logistic regression model using standard statistical software and their standard errors by Taylor series expansion or the jackknife method. We apply the approach to data from a two-phase survey screening for dementia in a community sample of African Americans age 65 and older living in Indianapolis. The binary response variable is dementia and the covariate with missing values is a daily functioning score collected from interviews with a relative of the study subject.",
author = "Sujuan Gao and Siu Hui",
year = "1997",
month = "11",
day = "15",
doi = "10.1002/(SICI)1097-0258(19971115)16:21<2419::AID-SIM686>3.0.CO;2-E",
language = "English",
volume = "16",
pages = "2419--2428",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "21",

}

TY - JOUR

T1 - Logistic regression models with missing covariate values for complex survey data

AU - Gao, Sujuan

AU - Hui, Siu

PY - 1997/11/15

Y1 - 1997/11/15

N2 - Maximum likelihood methods are used to incorporate partially observed covariate values in fitting logistic regression models. We extend these methods to data collected through complex surveys using the pseudo-likelihood approach. One can obtain parameter estimates of the logistic regression model using standard statistical software and their standard errors by Taylor series expansion or the jackknife method. We apply the approach to data from a two-phase survey screening for dementia in a community sample of African Americans age 65 and older living in Indianapolis. The binary response variable is dementia and the covariate with missing values is a daily functioning score collected from interviews with a relative of the study subject.

AB - Maximum likelihood methods are used to incorporate partially observed covariate values in fitting logistic regression models. We extend these methods to data collected through complex surveys using the pseudo-likelihood approach. One can obtain parameter estimates of the logistic regression model using standard statistical software and their standard errors by Taylor series expansion or the jackknife method. We apply the approach to data from a two-phase survey screening for dementia in a community sample of African Americans age 65 and older living in Indianapolis. The binary response variable is dementia and the covariate with missing values is a daily functioning score collected from interviews with a relative of the study subject.

UR - http://www.scopus.com/inward/record.url?scp=0030785266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030785266&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-0258(19971115)16:21<2419::AID-SIM686>3.0.CO;2-E

DO - 10.1002/(SICI)1097-0258(19971115)16:21<2419::AID-SIM686>3.0.CO;2-E

M3 - Article

C2 - 9364651

AN - SCOPUS:0030785266

VL - 16

SP - 2419

EP - 2428

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 21

ER -