One size doesn't fit all: Selecting response scales for BES attitude items

Robert A. Johns

Research output: Contribution to journalArticle

Abstract

The simple 5-point Likert format is ubiquitous in British public opinion research. Yet recent thinking on survey response questions the validity of even the simplest measures. Respondents seek satisficing strategies to cope with the cognitive demands of answering, and the Likert midpoint provides such a strategy. This suggests that 4-point scales might be more appropriate. Evidence is presented on who chooses the midpoint, and what they do when denied it. Omitting the midpoint may impair validity, because some respondents opt for it when they have no basis for choosing between agreement and disagreement. Yet omission may improve validity, because the midpoint is also used as a safe haven by a 'silent minority', taking refuge in that option rather than confessing to an unpopular viewpoint. The implication is that the midpoint should be offered on obscure topics, where many respondents will have no basis for choice, but omitted on controversial topics, where social desirability is uppermost in respondents' minds. Applying these principles to the 2001 BES demonstrates that varying format by topic thus is not only advisable but also straightforward in practical terms.
LanguageEnglish
Pages237-264
Number of pages27
JournalJournal of Elections, Public Opinion and Parties
Volume15
Issue number2
DOIs
Publication statusPublished - Sep 2005

Fingerprint

social desirability
opinion research
public opinion
minority
evidence

Keywords

  • response scales
  • BES attitude items
  • Likert format
  • survey responses

Cite this

@article{5ae09a2a965d4cefbc2cbfce09f084d9,
title = "One size doesn't fit all: Selecting response scales for BES attitude items",
abstract = "The simple 5-point Likert format is ubiquitous in British public opinion research. Yet recent thinking on survey response questions the validity of even the simplest measures. Respondents seek satisficing strategies to cope with the cognitive demands of answering, and the Likert midpoint provides such a strategy. This suggests that 4-point scales might be more appropriate. Evidence is presented on who chooses the midpoint, and what they do when denied it. Omitting the midpoint may impair validity, because some respondents opt for it when they have no basis for choosing between agreement and disagreement. Yet omission may improve validity, because the midpoint is also used as a safe haven by a 'silent minority', taking refuge in that option rather than confessing to an unpopular viewpoint. The implication is that the midpoint should be offered on obscure topics, where many respondents will have no basis for choice, but omitted on controversial topics, where social desirability is uppermost in respondents' minds. Applying these principles to the 2001 BES demonstrates that varying format by topic thus is not only advisable but also straightforward in practical terms.",
keywords = "response scales, BES attitude items, Likert format, survey responses",
author = "Johns, {Robert A.}",
year = "2005",
month = "9",
doi = "10.1080/13689880500178849",
language = "English",
volume = "15",
pages = "237--264",
journal = "Journal of Elections, Public Opinion and Parties",
issn = "1745-7289",
number = "2",

}

One size doesn't fit all: Selecting response scales for BES attitude items. / Johns, Robert A.

In: Journal of Elections, Public Opinion and Parties, Vol. 15, No. 2, 09.2005, p. 237-264.

Research output: Contribution to journalArticle

TY - JOUR

T1 - One size doesn't fit all: Selecting response scales for BES attitude items

AU - Johns, Robert A.

PY - 2005/9

Y1 - 2005/9

N2 - The simple 5-point Likert format is ubiquitous in British public opinion research. Yet recent thinking on survey response questions the validity of even the simplest measures. Respondents seek satisficing strategies to cope with the cognitive demands of answering, and the Likert midpoint provides such a strategy. This suggests that 4-point scales might be more appropriate. Evidence is presented on who chooses the midpoint, and what they do when denied it. Omitting the midpoint may impair validity, because some respondents opt for it when they have no basis for choosing between agreement and disagreement. Yet omission may improve validity, because the midpoint is also used as a safe haven by a 'silent minority', taking refuge in that option rather than confessing to an unpopular viewpoint. The implication is that the midpoint should be offered on obscure topics, where many respondents will have no basis for choice, but omitted on controversial topics, where social desirability is uppermost in respondents' minds. Applying these principles to the 2001 BES demonstrates that varying format by topic thus is not only advisable but also straightforward in practical terms.

AB - The simple 5-point Likert format is ubiquitous in British public opinion research. Yet recent thinking on survey response questions the validity of even the simplest measures. Respondents seek satisficing strategies to cope with the cognitive demands of answering, and the Likert midpoint provides such a strategy. This suggests that 4-point scales might be more appropriate. Evidence is presented on who chooses the midpoint, and what they do when denied it. Omitting the midpoint may impair validity, because some respondents opt for it when they have no basis for choosing between agreement and disagreement. Yet omission may improve validity, because the midpoint is also used as a safe haven by a 'silent minority', taking refuge in that option rather than confessing to an unpopular viewpoint. The implication is that the midpoint should be offered on obscure topics, where many respondents will have no basis for choice, but omitted on controversial topics, where social desirability is uppermost in respondents' minds. Applying these principles to the 2001 BES demonstrates that varying format by topic thus is not only advisable but also straightforward in practical terms.

KW - response scales

KW - BES attitude items

KW - Likert format

KW - survey responses

UR - http://dx.doi.org/10.1080/13689880500178849

U2 - 10.1080/13689880500178849

DO - 10.1080/13689880500178849

M3 - Article

VL - 15

SP - 237

EP - 264

JO - Journal of Elections, Public Opinion and Parties

T2 - Journal of Elections, Public Opinion and Parties

JF - Journal of Elections, Public Opinion and Parties

SN - 1745-7289

IS - 2

ER -