Strong Words or Moderate Words: A Comparison of the Reliability and Validity of Responses on Attitude Scales

Bruce B. Frey, Lisa M. Edwards

.

DOI: 10.4236/psych.2011.21008                

Abstract

A common assumption in attitude measurement is that items should be composed of strongly worded statements. The presumed benefit of strongly worded statements is that they produce more reliable and valid scores than statements with moderate or weak wording. This study tested this assumption using commonly accepted criteria for reliability and validity. Two forms of attitude scales were created - a strongly worded form and a moderately worded form - measuring two attitude objects - attitude towards animal experimentation and attitude towards going to the movies. Different formats were randomly administered to samples of graduate students. There was no superiority found for strongly worded statements over moderately worded statements. The only statistically significant difference was found between one pair of validity coefficients (r = 0.69; r = 0.15; Z = 2.60, p ≤ 0.01) and that was in the direction opposite from expected, favoring moderately worded items over strongly worded items (total scores correlated with a general behavioral item).

Keywords

Attitude Scales, Reliabilty, Validity

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Andrich, D. (1996). A hyperbolic cosine latent trait model for unfolding polytomous responses: Reconciling Thurstone and Likert methodologies. British Journal of Mathematical and Statistical Psychology, 49, 347-365.
[2]	Andrich, D., & Styles, I. (1998). The structural relationship between attitudes and behavior statements from the unfolding perspective. Psychological Methods, 3, 454-469. doi:10.1037/1082-989X.3.4.454
[3]	Barnette, J. J. (2000). Effects of stem and Likert response option reversals on survey internal consistency: If you feel the need, there is a better alternative to using those negatively worded stems. Educational and Psychological Measurement, 60, 361-370. doi:10.1177/00131640021970592
[4]	Best, J. W., & Kahn, J. V. (1989). Research in education (6th Edition). Englewoods Cliffs, N.J.: Prentice-Hall.
[5]	Bourque, L. B., & Fielder, E. P. (1995). How to conduct self-administered and mail surveys. London: Sage.
[6]	Cronbach, L. J. (1951). Coefficient alpha and the internal structure of tests. Psychometrika, 16, 297-334.
[7]	Crocker, L., & Algina, J. (1986). Introduction to classical and modern test theory. New York: Harcourt Brace Jovanovich.
[8]	Feldt, L. S., Woodruff, D. J., & Slaih, F. A. (1987). Statistical inference for coefficient alpha. Applied Psychological Measurement, 11, 93- 103. doi:10.1177/014662168701100107
[9]	Ferguson, L. (1941). A study of the Likert technique of attitude scale construction. Journal of Social Psychology, 13, 51-57. doi:10.1080/00224545.1941.9714060
[10]	Fink, A. (1995). The Survey Handbook. London: Sage.
[11]	Fowler, F. J. Jr. (1995). Improving Survey Questions. London: Sage.
[12]	Henerson, M. E. Morris, L. L., & Fitz-Gibbon, C. T. (1987). How to measure attitudes. London: Sage.
[13]	Herche, J., & Engelland, B. (1996). Reversed-polarity items and scale unidimensionality. Journal of the Academy of Marketing Science, 24, 366-374. doi:10.1177/0092070396244007
[14]	Leedy, P. D. (1997). Practical research: Planning and design (6th Edition). New Jersey: Prentice-Hall.
[15]	Likert, R. (1932). A technique for the measurement of attitudes. Archives of Psychology, 140.
[16]	Mangione, T. W. (1995). Mail surveys: Improving the quality. London: Sage.
[17]	Millman, J., & Greene, J. (1989). The specifications and development of tests of achievement and ability. In: R. L. Linn (Ed.), Educational measurement (3rd Edition). Phoenix, AZ: American Council on Education.
[18]	Roberts, J., Laughlin, J., & Wedell, D. (1999). Validity issues in the Likert and Thurstone approaches to attitude measurement. Educational & Psychological Measurement, 59, 211-233. doi:10.1177/00131649921969811
[19]	Schmitt, N., & Stuits, D. M. (1985). Factors defined by negatively keyed items: The result of careless respondents? Applied Psychological Measurement, 9, 367-373. doi:10.1177/014662168500900405
[20]	Seiler, L., & Hough, R. (1970). Empirical comparisons of the Thurstone and Likert techniques. In: G. Summers (Ed.), Attitude measurement. Chicago: Rand McNally.
[21]	Shuman, H., & Presser, S. (1981). Questions and answers in attitude surveys. Sage.
[22]	Thurstone, L. L. (1928). Attitudes can be measured. American Journal of Sociology, 33, 529-554. doi:10.1086/214483
[23]	Wong, N., Rindfleisch, A., & Burroughs, J. E. (2003). Do reverse worded items confound measures in cross-cultural consumer research? The case of the material values scale. Journal of Consumer Research, 30, 72-91. doi:10.1086/374697