The characteristics of rating scales are very important in questionnaires on attitudes and satisfaction. In the construction of a rating scale, one is often concerned about the number of rating categories. Effects of scale length on relationships among variables are explored through a study of students' satisfaction with college instruction. Six rating scales of length n are compared, for n = 2, 3, 4, 5, 7, 10. The results indicate that deviations of actual averages from the theoretical means increase as the number of choice points increase. Also, Pearson's correlations and etas generally increase with scale length.
Get full access to this article
View all access options for this article.
References
1.
BendigA. W.Transmitted information and the length of rating scales. Journal of Experimental Psychology, 1954, 47, 303–308.
2.
BlalcockH. M.Jr.Social statistics. New York: McGraw-Hill, 1972.
3.
BrysonK. R.PhillipsD. P.Method for classifying interval-scale and ordinal-scale data. In HeiseD. R. (Ed.), Sociological methodology. San Francisco: Jossey-Bass, 1975. Pp. 171–190.
4.
ChampneyH.MarshallH.Optimal refinement of the rating scale. Journal of Applied Psychology, 1939, 23, 323–331.
5.
GreenP. E.RaoV. R.Rating scales and information recovery—how many scales and response categories to use?Journal of Marketing, 1970, 34, 33–39.
6.
MillerG. A.The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychological Review, 1956, 63, 81–97.
7.
NeumannL.Effects of categorization on relationships in bivariate distributions and applications to rating scales. Unpublished Ph.D. dissertation, Department of Mathematics., Boston Univer., Boston, MA1979.
8.
NeumannL.NeumannY.Dimensions and predictors of students' satisfaction with college instruction. Journal of Instructional Psychology, 1980, 7, 99–107.
9.
RamsayJ. O.The effect of number of categories in rating scales on precision of estimation of scale values. Psychometrika, 1973, 38, 513–532.
10.
SymondsP. M.On the loss of reliability in ratings due to coarseness of the scale. Journal of Experimental Psychology, 1924, 7, 456–461.
