2015
DOI: 10.1057/jma.2015.4
|View full text |Cite
|
Sign up to set email alerts
|

What is the optimal number of response alternatives for rating scales? From an information processing perspective

Abstract: Rating scales are measuring instruments that are widely used in social science research. However, many different rating scale formats are used in the literature, differing specifically in the number of response alternatives offered. Previous studies on the optimal number of response alternatives have focused exclusively on the participants' final response results, rather than on the participants' information processing. We used an eye-tracking study to explore this issue from an information processing perspect… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 32 publications
(19 citation statements)
references
References 23 publications
(30 reference statements)
0
19
0
Order By: Relevance
“…In all cases, the items (see Appendix A) were measured with five-point Likert-type scales, ranging from 1 (strongly disagree) to 5 (strongly agreeing). We have used 5-point Likert scales based on the evidence provided by empirical research, in the sense that these scales require the shortest reaction time, compared to 7-point scales, and when considering the data showing potential acquiescence bias and extreme response bias, five is the optimal number of anchors [84]. Additionally, in order to characterize the sample obtained, a series of classification questions was included.…”
Section: Methodsmentioning
confidence: 99%
“…In all cases, the items (see Appendix A) were measured with five-point Likert-type scales, ranging from 1 (strongly disagree) to 5 (strongly agreeing). We have used 5-point Likert scales based on the evidence provided by empirical research, in the sense that these scales require the shortest reaction time, compared to 7-point scales, and when considering the data showing potential acquiescence bias and extreme response bias, five is the optimal number of anchors [84]. Additionally, in order to characterize the sample obtained, a series of classification questions was included.…”
Section: Methodsmentioning
confidence: 99%
“…This leads to the importance of considering information‐processing issues in survey design. Chen, Yu, and Yu () conducted an eye‐tracking experiment with a sample of 184 Chinese people to measure respondents’ reaction time in answering a question as evidence of their cognitive effort. They found that a 5‐point scale required the shortest reaction time, compared to 4‐, 6‐, 7‐, 8‐, and 9‐point scales.…”
Section: Research Findings On the Use Of A Midpoint On Likert‐type Scmentioning
confidence: 99%
“…This middle point can represent students' real attitudes in opinion measurement and reduce some response bias. A fivepoint Likert scale is also the best option to attain an information-processing perspective (Chen 2015;Cohen, Manion and Morrison, 2018).…”
Section: Research Proceduresmentioning
confidence: 99%