How much of interviewer variance is really nonresponse error variance?

Brady T. West, Kristen Olson

Research output: Contribution to journalArticle

44 Citations (Scopus)

Abstract

Kish's (1962) classical intra-interviewer correlation (ρint) provides survey researchers with an estimate of the effect of interviewers on variation in measurements of a survey variable of interest. This correlation is an undesirable product of the data collection process that can arise when answers from respondents interviewed by the same interviewer are more similar to each other than answers from other respondents, decreasing the precision of survey estimates. Estimation of this parameter, however, uses only respondent data. The potential contribution of variance in nonresponse errors between interviewers to the estimation of ρint has been largely ignored. Responses within interviewers may appear correlated because the interviewers successfully obtain cooperation from different pools of respondents, not because of systematic response deviations. This study takes a first step in filling this gap in the literature on interviewer effects by analyzing a unique survey data set, collected using computer-assisted telephone interviewing (CATI) from a sample of divorce records. This data set, which includes both true values and reported values for respondents and a CATI sample assignment that approximates interpenetrated assignment of subsamples to interviewers, enables the decomposition of interviewer variance in means of respondent reports into nonresponse error variance and measurement error variance across interviewers. We show that in cases where there is substantial interviewer variance in reported values, the interviewer variance may arise from nonresponse error variance across interviewers.

Original languageEnglish (US)
Pages (from-to)1004-1026
Number of pages23
JournalPublic Opinion Quarterly
Volume74
Issue number5
DOIs
StatePublished - Dec 1 2010

Fingerprint

response behavior
interview
Telephone
Measurement errors
Decomposition
telephone
reactivity effect
Values
divorce

ASJC Scopus subject areas

  • Communication
  • History
  • Sociology and Political Science
  • Social Sciences(all)
  • History and Philosophy of Science

Cite this

How much of interviewer variance is really nonresponse error variance? / West, Brady T.; Olson, Kristen.

In: Public Opinion Quarterly, Vol. 74, No. 5, 01.12.2010, p. 1004-1026.

Research output: Contribution to journalArticle

@article{ba9d730aa0c1466bbecf3b5be772d71e,
title = "How much of interviewer variance is really nonresponse error variance?",
abstract = "Kish's (1962) classical intra-interviewer correlation (ρint) provides survey researchers with an estimate of the effect of interviewers on variation in measurements of a survey variable of interest. This correlation is an undesirable product of the data collection process that can arise when answers from respondents interviewed by the same interviewer are more similar to each other than answers from other respondents, decreasing the precision of survey estimates. Estimation of this parameter, however, uses only respondent data. The potential contribution of variance in nonresponse errors between interviewers to the estimation of ρint has been largely ignored. Responses within interviewers may appear correlated because the interviewers successfully obtain cooperation from different pools of respondents, not because of systematic response deviations. This study takes a first step in filling this gap in the literature on interviewer effects by analyzing a unique survey data set, collected using computer-assisted telephone interviewing (CATI) from a sample of divorce records. This data set, which includes both true values and reported values for respondents and a CATI sample assignment that approximates interpenetrated assignment of subsamples to interviewers, enables the decomposition of interviewer variance in means of respondent reports into nonresponse error variance and measurement error variance across interviewers. We show that in cases where there is substantial interviewer variance in reported values, the interviewer variance may arise from nonresponse error variance across interviewers.",
author = "West, {Brady T.} and Kristen Olson",
year = "2010",
month = "12",
day = "1",
doi = "10.1093/poq/nfq061",
language = "English (US)",
volume = "74",
pages = "1004--1026",
journal = "Public Opinion Quarterly",
issn = "0033-362X",
publisher = "Oxford University Press",
number = "5",

}

TY - JOUR

T1 - How much of interviewer variance is really nonresponse error variance?

AU - West, Brady T.

AU - Olson, Kristen

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Kish's (1962) classical intra-interviewer correlation (ρint) provides survey researchers with an estimate of the effect of interviewers on variation in measurements of a survey variable of interest. This correlation is an undesirable product of the data collection process that can arise when answers from respondents interviewed by the same interviewer are more similar to each other than answers from other respondents, decreasing the precision of survey estimates. Estimation of this parameter, however, uses only respondent data. The potential contribution of variance in nonresponse errors between interviewers to the estimation of ρint has been largely ignored. Responses within interviewers may appear correlated because the interviewers successfully obtain cooperation from different pools of respondents, not because of systematic response deviations. This study takes a first step in filling this gap in the literature on interviewer effects by analyzing a unique survey data set, collected using computer-assisted telephone interviewing (CATI) from a sample of divorce records. This data set, which includes both true values and reported values for respondents and a CATI sample assignment that approximates interpenetrated assignment of subsamples to interviewers, enables the decomposition of interviewer variance in means of respondent reports into nonresponse error variance and measurement error variance across interviewers. We show that in cases where there is substantial interviewer variance in reported values, the interviewer variance may arise from nonresponse error variance across interviewers.

AB - Kish's (1962) classical intra-interviewer correlation (ρint) provides survey researchers with an estimate of the effect of interviewers on variation in measurements of a survey variable of interest. This correlation is an undesirable product of the data collection process that can arise when answers from respondents interviewed by the same interviewer are more similar to each other than answers from other respondents, decreasing the precision of survey estimates. Estimation of this parameter, however, uses only respondent data. The potential contribution of variance in nonresponse errors between interviewers to the estimation of ρint has been largely ignored. Responses within interviewers may appear correlated because the interviewers successfully obtain cooperation from different pools of respondents, not because of systematic response deviations. This study takes a first step in filling this gap in the literature on interviewer effects by analyzing a unique survey data set, collected using computer-assisted telephone interviewing (CATI) from a sample of divorce records. This data set, which includes both true values and reported values for respondents and a CATI sample assignment that approximates interpenetrated assignment of subsamples to interviewers, enables the decomposition of interviewer variance in means of respondent reports into nonresponse error variance and measurement error variance across interviewers. We show that in cases where there is substantial interviewer variance in reported values, the interviewer variance may arise from nonresponse error variance across interviewers.

UR - http://www.scopus.com/inward/record.url?scp=79951651495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951651495&partnerID=8YFLogxK

U2 - 10.1093/poq/nfq061

DO - 10.1093/poq/nfq061

M3 - Article

AN - SCOPUS:79951651495

VL - 74

SP - 1004

EP - 1026

JO - Public Opinion Quarterly

JF - Public Opinion Quarterly

SN - 0033-362X

IS - 5

ER -