Published online by Cambridge University Press: 01 January 2025
Items have been studied heretofore for their value as elements of particular tests to the neglect of more fundamental research into the multiple potentiality of items. This article proposes a method of grouping items into “synonymies” comprising all of the items which correlate with a given key item. These synonymies can be used for interpretation of the total meaning of the key item: (1) by inspection of the constituent items and (2) by correlational study of obtained single scores of individual persons. The method is illustrated by four items with inter- and intra-correlations, and characteristics of an ideal background reservoir of items are pointed out.
* Articles appear under these names: Dorothy C. Adkins and H. A. Toops, Walter Merrill, J. C. Flanagan, T. J. Kelley, G. F. Kuder, T. F. Lentz, J. Lev, L. H. Mathews, C. J. Mosier and J. V. McQuitty, R. C. Pace, M. W. Richardson and Dorothy C. Adkins, E. A. Rundquist, R. F. Sletto, M. Smith, F. Swineford.
* R. F. Sletto. Construction of personality scales by the criterion of internal consistency. Minneapolis, Minnesota: The Sociological Press, 1937.
† T. F. Lentz. Generality and specificity of conservatism-radicalim, J. educ. Psychol, 1938, 10, 540-546.
‡ G. V. Sheviakov and Jean Friedberg. Use of interest inventories for personality study. J. educ. Research, 1940, 33, 692-697.
* Commonly called “battery,”’ but synonymy is more descriptive. As one refers to the synonymy or list of synonyms of a word to find all of its meanings, may he not also refer to an item synonymy to find the item’s meanings?
* For some of the data the authors are indebted to tbe Work Projects Administration, Recreation Division, District No. 10, St. Louis, Missouri.
* A full account is given by Edith Whitmer, “Item Analysis Through Correlations,” Unpublished Master’s Thesis, Washington University, 1940.
* Reactions to 959 other items were used in the construction of D and 479 for each of the other synonymies.
† Numbers in parentheses refer to the number of coefficients represented by the median.
‡‡ For attenuation due to unreliability of both synonymy and item. The reliability of the item was assumed to be .60. (See Lentz, op. cit.; also Lentz, T. F., Reliability of opinionaire technique studied intensively by the retest method, J. soc. Psychol. 1934, 5, 338-364.