Three methods of gathering and evaluating value profiles for use in market segmentation are compared. Different reliability estimates are found to produce different conclusions as to the relative test-retest reliability of the three methods. However, the most appropriate statistical measure, Kendall's tauB, reveals that Likert rating scales are significantly less reliable than either rank ordering or paired comparison procedures. No differences in subject interest are found among the methods, but Likert scales and rank ordering require less response time than do paired comparisons. Implications for method choice and future research are discussed.
Get full access to this article
View all access options for this article.
References
1.
HaysW. L. (1973), Statistics for the Social Sciences. New York: Holt, Rinehart and Winston, Inc.
2.
KendallM. G. and SmithB. (1940), “On the Method of Paired Comparisons,” Biometrika, 31, 324–45.
3.
MostellerF. (1951), “Remarks on the Method of Paired Comparisons: III. A Test of Significance for Paired Comparisons When Equal Standard Deviations and Equal Correlations are Assumed,” Psychometrika, 16, 207–18.
4.
MunsonJ. M. and McIntyreS. H. (1979), “Developing Practical Procedures for the Measurement of Personal Values in Cross-Cultural Marketing,” Journal of Marketing Research, 16 (February), 48–52.
5.
RokeachM. (1973), The Nature of Values. New York: Free Press.
6.
SchefféH. A. (1959), The Analysis of Variance. New York: John Wiley & Sons, Inc.
7.
WinerB. J. (1971), Statistical Principles in Experimental Design. New York: McGraw-Hill Book Company.
