Measurement properties of completely and end labeled unipolar and bipolar scales in Likert-type questions on income (in)equality

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Jan Karem Höhne
  • Dagmar Krebs
  • Steffen M. Kühnel

External Research Organisations

  • University of Mannheim
  • Universität Pompeu Fabra (UPF)
  • Justus Liebig University Giessen
  • University of Göttingen
View graph of relations

Details

Original languageEnglish
Article number102544
JournalSocial science research
Volume97
Early online date2 Mar 2021
Publication statusE-pub ahead of print - 2 Mar 2021
Externally publishedYes

Abstract

The measurement of respondents' attitudes is key in social science research and many adjacent research fields. A common method to measure this information is to use Likert-type questions that consist of a statement that is evaluated with a rating scale. As shown by previous research, the scale design of Likert-type questions can have a profound impact on respondents’ answer behavior. In this study, we therefore investigate the measurement properties of scales that systematically vary with respect to polarity (i.e., unipolar and bipolar) and labeling (i.e., completely and end). We conducted a survey experiment in a probability-based online panel (N = 4851) and used questions on income (in)equality that were adopted from the European Social Survey (ESS). The results reveal considerable differences between the scales under investigation. They show that end labeled unipolar and bipolar scales accomplish the criteria of equidistance best. Completely labeled bipolar scales, in contrast, only show a poor performance in terms of equidistance. Completely labeled unipolar scales are somewhere in between. Overall, our findings suggest that researchers should be careful when using survey data measured with (slightly) different scales because the results might not be comparable.

Keywords

    Latent thresholds, Likert-type questions, Measurement invariance, Online survey, Rating scale design

ASJC Scopus subject areas

Cite this

Measurement properties of completely and end labeled unipolar and bipolar scales in Likert-type questions on income (in)equality. / Höhne, Jan Karem; Krebs, Dagmar; Kühnel, Steffen M.
In: Social science research, Vol. 97, 102544, 02.03.2021.

Research output: Contribution to journalArticleResearchpeer review

Höhne JK, Krebs D, Kühnel SM. Measurement properties of completely and end labeled unipolar and bipolar scales in Likert-type questions on income (in)equality. Social science research. 2021 Mar 2;97:102544. Epub 2021 Mar 2. doi: 10.1016/j.ssresearch.2021.102544
Download
@article{ad6e72504fe14b079aa91e28a445a2ea,
title = "Measurement properties of completely and end labeled unipolar and bipolar scales in Likert-type questions on income (in)equality",
abstract = "The measurement of respondents' attitudes is key in social science research and many adjacent research fields. A common method to measure this information is to use Likert-type questions that consist of a statement that is evaluated with a rating scale. As shown by previous research, the scale design of Likert-type questions can have a profound impact on respondents{\textquoteright} answer behavior. In this study, we therefore investigate the measurement properties of scales that systematically vary with respect to polarity (i.e., unipolar and bipolar) and labeling (i.e., completely and end). We conducted a survey experiment in a probability-based online panel (N = 4851) and used questions on income (in)equality that were adopted from the European Social Survey (ESS). The results reveal considerable differences between the scales under investigation. They show that end labeled unipolar and bipolar scales accomplish the criteria of equidistance best. Completely labeled bipolar scales, in contrast, only show a poor performance in terms of equidistance. Completely labeled unipolar scales are somewhere in between. Overall, our findings suggest that researchers should be careful when using survey data measured with (slightly) different scales because the results might not be comparable.",
keywords = "Latent thresholds, Likert-type questions, Measurement invariance, Online survey, Rating scale design",
author = "H{\"o}hne, {Jan Karem} and Dagmar Krebs and K{\"u}hnel, {Steffen M.}",
note = "Funding Information: We acknowledge funding by German Science Foundation through the Collaborative Research Center 884 “Political Economy of Reforms” (grant number: 139,943,784 ). ",
year = "2021",
month = mar,
day = "2",
doi = "10.1016/j.ssresearch.2021.102544",
language = "English",
volume = "97",
journal = "Social science research",
issn = "0049-089X",
publisher = "Academic Press Inc.",

}

Download

TY - JOUR

T1 - Measurement properties of completely and end labeled unipolar and bipolar scales in Likert-type questions on income (in)equality

AU - Höhne, Jan Karem

AU - Krebs, Dagmar

AU - Kühnel, Steffen M.

N1 - Funding Information: We acknowledge funding by German Science Foundation through the Collaborative Research Center 884 “Political Economy of Reforms” (grant number: 139,943,784 ).

PY - 2021/3/2

Y1 - 2021/3/2

N2 - The measurement of respondents' attitudes is key in social science research and many adjacent research fields. A common method to measure this information is to use Likert-type questions that consist of a statement that is evaluated with a rating scale. As shown by previous research, the scale design of Likert-type questions can have a profound impact on respondents’ answer behavior. In this study, we therefore investigate the measurement properties of scales that systematically vary with respect to polarity (i.e., unipolar and bipolar) and labeling (i.e., completely and end). We conducted a survey experiment in a probability-based online panel (N = 4851) and used questions on income (in)equality that were adopted from the European Social Survey (ESS). The results reveal considerable differences between the scales under investigation. They show that end labeled unipolar and bipolar scales accomplish the criteria of equidistance best. Completely labeled bipolar scales, in contrast, only show a poor performance in terms of equidistance. Completely labeled unipolar scales are somewhere in between. Overall, our findings suggest that researchers should be careful when using survey data measured with (slightly) different scales because the results might not be comparable.

AB - The measurement of respondents' attitudes is key in social science research and many adjacent research fields. A common method to measure this information is to use Likert-type questions that consist of a statement that is evaluated with a rating scale. As shown by previous research, the scale design of Likert-type questions can have a profound impact on respondents’ answer behavior. In this study, we therefore investigate the measurement properties of scales that systematically vary with respect to polarity (i.e., unipolar and bipolar) and labeling (i.e., completely and end). We conducted a survey experiment in a probability-based online panel (N = 4851) and used questions on income (in)equality that were adopted from the European Social Survey (ESS). The results reveal considerable differences between the scales under investigation. They show that end labeled unipolar and bipolar scales accomplish the criteria of equidistance best. Completely labeled bipolar scales, in contrast, only show a poor performance in terms of equidistance. Completely labeled unipolar scales are somewhere in between. Overall, our findings suggest that researchers should be careful when using survey data measured with (slightly) different scales because the results might not be comparable.

KW - Latent thresholds

KW - Likert-type questions

KW - Measurement invariance

KW - Online survey

KW - Rating scale design

UR - http://www.scopus.com/inward/record.url?scp=85101878202&partnerID=8YFLogxK

U2 - 10.1016/j.ssresearch.2021.102544

DO - 10.1016/j.ssresearch.2021.102544

M3 - Article

C2 - 34045005

AN - SCOPUS:85101878202

VL - 97

JO - Social science research

JF - Social science research

SN - 0049-089X

M1 - 102544

ER -