A mixture model for middle category inflation in ordered survey responses

Benjamin E. Bagozzi; Bumba Mukherjee

doi:10.1093/pan/mps020

A mixture model for middle category inflation in ordered survey responses

Benjamin E. Bagozzi, Bumba Mukherjee

Political Science

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

23 Scopus citations

Abstract

Recent research finds that, for social desirability reasons, uninformed individuals disproportionately give " neither agree nor disagree" type responses to survey attitude questions, even when a " do not know" option is available. Such " face-saving" responses inflate the indifference (i.e., middle) categories of ordered attitude variables with nonordered responses. When such inflation occurs within the middle category of one's ordered dependent variable, estimates from ordered probit (and ordered logit) models are likely to be unreliable and inefficient. This article develops a set of mixture models that estimate and account for the presence of " face-saving" responses in middle categories of ordered survey response variables, and applies these models to (1) simulated data and (2) a commonly studied survey question measuring attitudes toward European Union (EU) membership among individuals in EU-candidate countries. Results from the survey data set and the Monte Carlo experiments suggest that, when middle category inflation is present in one's ordered dependent variable, the estimates obtained from middle category mixture models are less biased than-and in some cases substantively distinct from-the estimates obtained from " naive" ordered probit models.

Original language	English (US)
Pages (from-to)	369-386
Number of pages	18
Journal	Political Analysis
Volume	20
Issue number	3
DOIs	https://doi.org/10.1093/pan/mps020
State	Published - Jul 2012

All Science Journal Classification (ASJC) codes

Sociology and Political Science
Political Science and International Relations

Access to Document

10.1093/pan/mps020

Cite this

@article{577afa34830f4a5fac2aa81c98c964de,

title = "A mixture model for middle category inflation in ordered survey responses",

abstract = "Recent research finds that, for social desirability reasons, uninformed individuals disproportionately give {"} neither agree nor disagree{"} type responses to survey attitude questions, even when a {"} do not know{"} option is available. Such {"} face-saving{"} responses inflate the indifference (i.e., middle) categories of ordered attitude variables with nonordered responses. When such inflation occurs within the middle category of one's ordered dependent variable, estimates from ordered probit (and ordered logit) models are likely to be unreliable and inefficient. This article develops a set of mixture models that estimate and account for the presence of {"} face-saving{"} responses in middle categories of ordered survey response variables, and applies these models to (1) simulated data and (2) a commonly studied survey question measuring attitudes toward European Union (EU) membership among individuals in EU-candidate countries. Results from the survey data set and the Monte Carlo experiments suggest that, when middle category inflation is present in one's ordered dependent variable, the estimates obtained from middle category mixture models are less biased than-and in some cases substantively distinct from-the estimates obtained from {"} naive{"} ordered probit models.",

author = "Bagozzi, {Benjamin E.} and Bumba Mukherjee",

note = "Funding Information: Authors{\textquoteright} note: An earlier version of this article was presented as a poster at the 2011 Political Methodology Meeting. The authors wish to acknowledge the valuable suggestions that they received from the editor and reviewers of Political Analysis, Chris Zorn, Phil Schrodt, Will H. Moore, Daniel W. Hill, Eric Plutzer, John Freeman, Robert J. Franzese Jr., and the 2011 Political Methodology meeting attendees. This work was supported by the Pennsylvania State University{\textquoteright}s College of Liberal Arts under the Forrest Crawford Graduate Scholarship. Replication materials can be found at Bagozzi and Mukherjee (2012). Supplementary Materials for this article are available on the Political Analysis Web site. 1Middle category responses include, e.g., “neither agree nor disagree” or “neither good nor bad.” 2Studies also show that respondents who are more uncertain about their position on certain policy issues are more likely to opt for the middle category response on survey questions that track their perception about their senator{\textquoteright}s position on such issues (Bradey and Sniderman 1991; Alvarez and Franklin 1994a,b). 3Zaller (1992); Mondak (2000); Burden (2000); Berinsky (2002).",

year = "2012",

month = jul,

doi = "10.1093/pan/mps020",

language = "English (US)",

volume = "20",

pages = "369--386",

journal = "Political Analysis",

issn = "1047-1987",

publisher = "Cambridge University Press",

number = "3",

}

TY - JOUR

T1 - A mixture model for middle category inflation in ordered survey responses

AU - Bagozzi, Benjamin E.

AU - Mukherjee, Bumba

N1 - Funding Information: Authors’ note: An earlier version of this article was presented as a poster at the 2011 Political Methodology Meeting. The authors wish to acknowledge the valuable suggestions that they received from the editor and reviewers of Political Analysis, Chris Zorn, Phil Schrodt, Will H. Moore, Daniel W. Hill, Eric Plutzer, John Freeman, Robert J. Franzese Jr., and the 2011 Political Methodology meeting attendees. This work was supported by the Pennsylvania State University’s College of Liberal Arts under the Forrest Crawford Graduate Scholarship. Replication materials can be found at Bagozzi and Mukherjee (2012). Supplementary Materials for this article are available on the Political Analysis Web site. 1Middle category responses include, e.g., “neither agree nor disagree” or “neither good nor bad.” 2Studies also show that respondents who are more uncertain about their position on certain policy issues are more likely to opt for the middle category response on survey questions that track their perception about their senator’s position on such issues (Bradey and Sniderman 1991; Alvarez and Franklin 1994a,b). 3Zaller (1992); Mondak (2000); Burden (2000); Berinsky (2002).

PY - 2012/7

Y1 - 2012/7

N2 - Recent research finds that, for social desirability reasons, uninformed individuals disproportionately give " neither agree nor disagree" type responses to survey attitude questions, even when a " do not know" option is available. Such " face-saving" responses inflate the indifference (i.e., middle) categories of ordered attitude variables with nonordered responses. When such inflation occurs within the middle category of one's ordered dependent variable, estimates from ordered probit (and ordered logit) models are likely to be unreliable and inefficient. This article develops a set of mixture models that estimate and account for the presence of " face-saving" responses in middle categories of ordered survey response variables, and applies these models to (1) simulated data and (2) a commonly studied survey question measuring attitudes toward European Union (EU) membership among individuals in EU-candidate countries. Results from the survey data set and the Monte Carlo experiments suggest that, when middle category inflation is present in one's ordered dependent variable, the estimates obtained from middle category mixture models are less biased than-and in some cases substantively distinct from-the estimates obtained from " naive" ordered probit models.

AB - Recent research finds that, for social desirability reasons, uninformed individuals disproportionately give " neither agree nor disagree" type responses to survey attitude questions, even when a " do not know" option is available. Such " face-saving" responses inflate the indifference (i.e., middle) categories of ordered attitude variables with nonordered responses. When such inflation occurs within the middle category of one's ordered dependent variable, estimates from ordered probit (and ordered logit) models are likely to be unreliable and inefficient. This article develops a set of mixture models that estimate and account for the presence of " face-saving" responses in middle categories of ordered survey response variables, and applies these models to (1) simulated data and (2) a commonly studied survey question measuring attitudes toward European Union (EU) membership among individuals in EU-candidate countries. Results from the survey data set and the Monte Carlo experiments suggest that, when middle category inflation is present in one's ordered dependent variable, the estimates obtained from middle category mixture models are less biased than-and in some cases substantively distinct from-the estimates obtained from " naive" ordered probit models.

UR - http://www.scopus.com/inward/record.url?scp=84864497684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864497684&partnerID=8YFLogxK

U2 - 10.1093/pan/mps020

DO - 10.1093/pan/mps020

M3 - Article

AN - SCOPUS:84864497684

SN - 1047-1987

VL - 20

SP - 369

EP - 386

JO - Political Analysis

JF - Political Analysis

IS - 3

ER -

A mixture model for middle category inflation in ordered survey responses

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this