The effect of nonresponse on prevalence estimates for a referent population: Insights from a population-based cohort study

Eyal Shahar, Aaron R. Folsom, Rodney Jackson

Research output: Contribution to journalArticle

111 Citations (Scopus)

Abstract

Characterization of nonrespondents, with the aim of detecting nonresponse bias, is a crucial component of prospective studies. This study was undertaken to investigate the demographic and health characteristics of nonrespondents to a population-based cohort study of cardiovascular disease, to determine whether early-stage nonrespondents differ from late-stage nonrespondents, and to estimate the bias in prevalence estimates for the source population. Sixty-seven percent of eligible subjects completed all phases of the cohort recruitment. Compared to respondents, nonrespondents were less likely to be married, less likely to be employed, and less likely to be well educated. Nonrespondents tended to describe their general health in less favorable terms and were more likely to be smokers. Their reported disease profile, however, was not dissimilar to that of respondents. For several demographic and health characteristics, including marital status, education, and smoking, early-stage nonrespondents differed from respondents more than did late-stage nonrespondents. For example, 42% of early nonrespondents were smokers compared to 37% of late nonrespondents and 22% of respondents. Overall, the bias in prevalence estimates related to nonresponse was small (< 5%) for most of the measured characteristics. Although nonresponse to health surveys is associated with typical attributes, early nonrespondents differ from respondents more than do late-stage nonrespondents. With few exceptions, however, a 33% nonresponse rate did not appear to introduce substantial bias into prevalence estimates for the source community.

Original languageEnglish (US)
Pages (from-to)498-506
Number of pages9
JournalAnnals of Epidemiology
Volume6
Issue number6
DOIs
StatePublished - Nov 1996
Externally publishedYes

Fingerprint

Cohort Studies
Population
Surveys and Questionnaires
Health
Demography
Marital Status
Health Surveys
Cardiovascular Diseases
Smoking
Prospective Studies

Keywords

  • Health surveys
  • selection bias
  • survey methods

ASJC Scopus subject areas

  • Medicine(all)
  • Public Health, Environmental and Occupational Health
  • Epidemiology

Cite this

The effect of nonresponse on prevalence estimates for a referent population : Insights from a population-based cohort study. / Shahar, Eyal; Folsom, Aaron R.; Jackson, Rodney.

In: Annals of Epidemiology, Vol. 6, No. 6, 11.1996, p. 498-506.

Research output: Contribution to journalArticle

@article{0a3426310417409cac7467e7a8d01aa1,
title = "The effect of nonresponse on prevalence estimates for a referent population: Insights from a population-based cohort study",
abstract = "Characterization of nonrespondents, with the aim of detecting nonresponse bias, is a crucial component of prospective studies. This study was undertaken to investigate the demographic and health characteristics of nonrespondents to a population-based cohort study of cardiovascular disease, to determine whether early-stage nonrespondents differ from late-stage nonrespondents, and to estimate the bias in prevalence estimates for the source population. Sixty-seven percent of eligible subjects completed all phases of the cohort recruitment. Compared to respondents, nonrespondents were less likely to be married, less likely to be employed, and less likely to be well educated. Nonrespondents tended to describe their general health in less favorable terms and were more likely to be smokers. Their reported disease profile, however, was not dissimilar to that of respondents. For several demographic and health characteristics, including marital status, education, and smoking, early-stage nonrespondents differed from respondents more than did late-stage nonrespondents. For example, 42{\%} of early nonrespondents were smokers compared to 37{\%} of late nonrespondents and 22{\%} of respondents. Overall, the bias in prevalence estimates related to nonresponse was small (< 5{\%}) for most of the measured characteristics. Although nonresponse to health surveys is associated with typical attributes, early nonrespondents differ from respondents more than do late-stage nonrespondents. With few exceptions, however, a 33{\%} nonresponse rate did not appear to introduce substantial bias into prevalence estimates for the source community.",
keywords = "Health surveys, selection bias, survey methods",
author = "Eyal Shahar and Folsom, {Aaron R.} and Rodney Jackson",
year = "1996",
month = "11",
doi = "10.1016/S1047-2797(96)00104-4",
language = "English (US)",
volume = "6",
pages = "498--506",
journal = "Annals of Epidemiology",
issn = "1047-2797",
publisher = "Elsevier Inc.",
number = "6",

}

TY - JOUR

T1 - The effect of nonresponse on prevalence estimates for a referent population

T2 - Insights from a population-based cohort study

AU - Shahar, Eyal

AU - Folsom, Aaron R.

AU - Jackson, Rodney

PY - 1996/11

Y1 - 1996/11

N2 - Characterization of nonrespondents, with the aim of detecting nonresponse bias, is a crucial component of prospective studies. This study was undertaken to investigate the demographic and health characteristics of nonrespondents to a population-based cohort study of cardiovascular disease, to determine whether early-stage nonrespondents differ from late-stage nonrespondents, and to estimate the bias in prevalence estimates for the source population. Sixty-seven percent of eligible subjects completed all phases of the cohort recruitment. Compared to respondents, nonrespondents were less likely to be married, less likely to be employed, and less likely to be well educated. Nonrespondents tended to describe their general health in less favorable terms and were more likely to be smokers. Their reported disease profile, however, was not dissimilar to that of respondents. For several demographic and health characteristics, including marital status, education, and smoking, early-stage nonrespondents differed from respondents more than did late-stage nonrespondents. For example, 42% of early nonrespondents were smokers compared to 37% of late nonrespondents and 22% of respondents. Overall, the bias in prevalence estimates related to nonresponse was small (< 5%) for most of the measured characteristics. Although nonresponse to health surveys is associated with typical attributes, early nonrespondents differ from respondents more than do late-stage nonrespondents. With few exceptions, however, a 33% nonresponse rate did not appear to introduce substantial bias into prevalence estimates for the source community.

AB - Characterization of nonrespondents, with the aim of detecting nonresponse bias, is a crucial component of prospective studies. This study was undertaken to investigate the demographic and health characteristics of nonrespondents to a population-based cohort study of cardiovascular disease, to determine whether early-stage nonrespondents differ from late-stage nonrespondents, and to estimate the bias in prevalence estimates for the source population. Sixty-seven percent of eligible subjects completed all phases of the cohort recruitment. Compared to respondents, nonrespondents were less likely to be married, less likely to be employed, and less likely to be well educated. Nonrespondents tended to describe their general health in less favorable terms and were more likely to be smokers. Their reported disease profile, however, was not dissimilar to that of respondents. For several demographic and health characteristics, including marital status, education, and smoking, early-stage nonrespondents differed from respondents more than did late-stage nonrespondents. For example, 42% of early nonrespondents were smokers compared to 37% of late nonrespondents and 22% of respondents. Overall, the bias in prevalence estimates related to nonresponse was small (< 5%) for most of the measured characteristics. Although nonresponse to health surveys is associated with typical attributes, early nonrespondents differ from respondents more than do late-stage nonrespondents. With few exceptions, however, a 33% nonresponse rate did not appear to introduce substantial bias into prevalence estimates for the source community.

KW - Health surveys

KW - selection bias

KW - survey methods

UR - http://www.scopus.com/inward/record.url?scp=0030294714&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030294714&partnerID=8YFLogxK

U2 - 10.1016/S1047-2797(96)00104-4

DO - 10.1016/S1047-2797(96)00104-4

M3 - Article

C2 - 8978880

AN - SCOPUS:0030294714

VL - 6

SP - 498

EP - 506

JO - Annals of Epidemiology

JF - Annals of Epidemiology

SN - 1047-2797

IS - 6

ER -