Abstract
The purpose of this study is to describe and com pare the methods used by Thorndike, Thurstone, and Rasch for calibrating test items. Thorndike and Thur stone represent a traditional psychometric approach to this problem, whereas Rasch represents a more mod em conceptualization derived from latent trait theory. These three major theorists in psychological and edu cational measurement were concerned with a common set of issues that seem to recur in a cyclical manner in psychometric theory. One such issue involves the in variance of item parameters. Each recognized the im portance of eliminating the effects of an arbitrary sam ple in the estimation of item parameters. The differ ences generally arise from the specific methods chosen to deal with the problem. Thorndike attempted to solve the problem of item invariance by adjusting for mean differences in ability distributions. Thurstone ex tended Thorndike's work by proposing two adjust ments which included an adjustment for differences in the dispersions of ability in addition to Thomdike's adjustment for mean differences. Rasch's method im plies a third adjustment, which involves the addition of a response model for each person in the sample. Data taken from Trabue (1916) are used to illustrate and compare how Thomdike, Thurstone, and Rasch would approach a common problem, namely, the cali bration of a single set of items administered to several groups.
Get full access to this article
View all access options for this article.