Multiple auxiliary variables in nonresponse adjustment

Frauke Kreuter, Kristen Olson

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Prior work has shown that effective survey nonresponse adjustment variables should be highly correlated with both the propensity to respond to a survey and the survey variables of interest. In practice, propensity models are often used for nonresponse adjustment with multiple auxiliary variables as predictors. These auxiliary variables may be positively or negatively associated with survey participation, they may be correlated with each other, and can have positive or negative relationships with the survey variables. Yet the consequences for nonresponse adjustment of these conditions are not known to survey practitioners. Simulations are used here to examine the effects of multiple auxiliary variables with opposite relationships with survey participation and the survey variables. The results show that bias and mean square error of adjusted respondent means are substantially different when the predictors have relationships of the same directions compared to when they have opposite directions with either propensity or the survey variables. Implications for nonresponse adjustment and responsive designs will be discussed.

Original languageEnglish (US)
Pages (from-to)311-332
Number of pages22
JournalSociological Methods and Research
Volume40
Issue number2
DOIs
StatePublished - May 1 2011

Fingerprint

response behavior
participation
simulation

Keywords

  • mean square error
  • nonresponse bias adjustment
  • response propensity models
  • survey participation

ASJC Scopus subject areas

  • Social Sciences (miscellaneous)
  • Sociology and Political Science

Cite this

Multiple auxiliary variables in nonresponse adjustment. / Kreuter, Frauke; Olson, Kristen.

In: Sociological Methods and Research, Vol. 40, No. 2, 01.05.2011, p. 311-332.

Research output: Contribution to journalArticle

@article{ca81c4d1eda94625afc4208d1857ff1d,
title = "Multiple auxiliary variables in nonresponse adjustment",
abstract = "Prior work has shown that effective survey nonresponse adjustment variables should be highly correlated with both the propensity to respond to a survey and the survey variables of interest. In practice, propensity models are often used for nonresponse adjustment with multiple auxiliary variables as predictors. These auxiliary variables may be positively or negatively associated with survey participation, they may be correlated with each other, and can have positive or negative relationships with the survey variables. Yet the consequences for nonresponse adjustment of these conditions are not known to survey practitioners. Simulations are used here to examine the effects of multiple auxiliary variables with opposite relationships with survey participation and the survey variables. The results show that bias and mean square error of adjusted respondent means are substantially different when the predictors have relationships of the same directions compared to when they have opposite directions with either propensity or the survey variables. Implications for nonresponse adjustment and responsive designs will be discussed.",
keywords = "mean square error, nonresponse bias adjustment, response propensity models, survey participation",
author = "Frauke Kreuter and Kristen Olson",
year = "2011",
month = "5",
day = "1",
doi = "10.1177/0049124111400042",
language = "English (US)",
volume = "40",
pages = "311--332",
journal = "Sociological Methods and Research",
issn = "0049-1241",
publisher = "SAGE Publications Inc.",
number = "2",

}

TY - JOUR

T1 - Multiple auxiliary variables in nonresponse adjustment

AU - Kreuter, Frauke

AU - Olson, Kristen

PY - 2011/5/1

Y1 - 2011/5/1

N2 - Prior work has shown that effective survey nonresponse adjustment variables should be highly correlated with both the propensity to respond to a survey and the survey variables of interest. In practice, propensity models are often used for nonresponse adjustment with multiple auxiliary variables as predictors. These auxiliary variables may be positively or negatively associated with survey participation, they may be correlated with each other, and can have positive or negative relationships with the survey variables. Yet the consequences for nonresponse adjustment of these conditions are not known to survey practitioners. Simulations are used here to examine the effects of multiple auxiliary variables with opposite relationships with survey participation and the survey variables. The results show that bias and mean square error of adjusted respondent means are substantially different when the predictors have relationships of the same directions compared to when they have opposite directions with either propensity or the survey variables. Implications for nonresponse adjustment and responsive designs will be discussed.

AB - Prior work has shown that effective survey nonresponse adjustment variables should be highly correlated with both the propensity to respond to a survey and the survey variables of interest. In practice, propensity models are often used for nonresponse adjustment with multiple auxiliary variables as predictors. These auxiliary variables may be positively or negatively associated with survey participation, they may be correlated with each other, and can have positive or negative relationships with the survey variables. Yet the consequences for nonresponse adjustment of these conditions are not known to survey practitioners. Simulations are used here to examine the effects of multiple auxiliary variables with opposite relationships with survey participation and the survey variables. The results show that bias and mean square error of adjusted respondent means are substantially different when the predictors have relationships of the same directions compared to when they have opposite directions with either propensity or the survey variables. Implications for nonresponse adjustment and responsive designs will be discussed.

KW - mean square error

KW - nonresponse bias adjustment

KW - response propensity models

KW - survey participation

UR - http://www.scopus.com/inward/record.url?scp=79956128893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956128893&partnerID=8YFLogxK

U2 - 10.1177/0049124111400042

DO - 10.1177/0049124111400042

M3 - Article

AN - SCOPUS:79956128893

VL - 40

SP - 311

EP - 332

JO - Sociological Methods and Research

JF - Sociological Methods and Research

SN - 0049-1241

IS - 2

ER -