The Midpoint on a Five-Point Likert-Type Scale
- 1 April 1987
- journal article
- research article
- Published by SAGE Publications in Perceptual and Motor Skills
- Vol. 64 (2), 359-362
- https://doi.org/10.2466/pms.1987.64.2.359
Abstract
Previous studies on the points of the Likert-scale format have not addressed the question of the effect on the score resulting from the use of “neutral” or “undecided” as the midpoint of a five-point scale. The present study addressed this topic with a scale on attitude toward the school board, using 389 undergraduate and 190 graduate students in education, the latter having at least one year of teaching experience, in seven geographically separated universities in the United States. The two formats of the scale were identical (strongly agree to strongly disagree) except that one scale midpoint was designated “undecided” and the midpoint of the other scale was designated as “neutral” with “undecided” as a no-answer alternative. Analysis showed differences were negligible and little if any erosion of score appears to result.Keywords
This publication has 8 references indexed in Scilit:
- The Construct Validity of Balanced Likert ScalesThe Journal of Social Psychology, 1982
- Ratings of Equal and Unequal Response Choice IntervalsThe Journal of Social Psychology, 1980
- Equidistant Categorical Labels for Construction of Likert-Type ScalesPerceptual and Motor Skills, 1979
- When Thurstone and Likert Agree—a Confounding of MethodologiesEducational and Psychological Measurement, 1977
- The Neutral Point on a Likert ScaleThe Journal of Psychology, 1977
- Choosing response categories for summated rating scales.Journal of Applied Psychology, 1976
- Is there an optimal number of alternatives for Likert-scale items? Effects of testing time and scale properties.Journal of Applied Psychology, 1972
- Is There an Optimal Number of Alternatives for Likert Scale Items? Study I: Reliability and ValidityEducational and Psychological Measurement, 1971