A comparison of methods of item selection for a personality test

Abstract

A comparison of nine methods of item selection for a personality test for grades IV to IX was made. This comparison made use of four sub-tests and two populations of 100 cases each. The methods of item selection have been compared on the basis of the scores obtained on the items selected by each method. This was done for the best 35, the middle 30, and the worst 35 items respectively. Scores based upon items selected by the nine methods show very high intercorrelations, particularly with reference to the best items and total scores. It would seem to make little difference in actual practical work which method of item selection is used in the selection of the best (most consistent) items. Correlation of the validity values assigned to all items by the nine methods shows a fairly high agreement among the various methods in the assignment of such validity values. (PsycInfo Database Record (c) 2025 APA, all rights reserved)