Willingness to Answer Multiple-Choice Questions as Manifested Both in Genuine and in Nonsense Items

Abstract

A formal description of partial knowledge, ability, and willingness to answer multiple-choice items put forward by Hutchinson (1977, 1980) makes predictions about response behavior on items for which none of the stated alternatives is correct. Cross and Frary (1977) obtained data on subjects' responses under these conditions. Hutchinson's theory is shown to account for a moderate proportion of the variation between subjects in the number of nonsense items they respond to. Alternative versions of the theory were compared, and one which implies the existence of partial knowledge was found to be better than one which implies that an appropriate measure of ability is obtained by applying the conventional "correction for guessing."

Get full access to this article

View all access options for this article.

References

Cross, L. H. and Frary, R. B. An empirical test of Lord's theoretical results regarding formula scoring of multiple-choice tests. Journal of Educational Measurement, 1977, 14, 313-321.

Frary, R. B. The effect of misinformation, partial information, and guessing on expected multiple-choice test item scores . Applied Psychological Measurement, 1980, 4, 79-90.

Hutchinson, T. P. On the relevance of signal detection theory to the correction for guessing . Contemporary Educational Psychology, 1977, 2, 50-54.

Hutchinson, T. P. Partial knowledge and the theoretical basis of linear corrections for guessing . Contemporary Educational Psychology, 1980, 5, 227-231.

Waller, M. I. Estimating guessing tendency . Presented at the annual convention of the Psychometric Society, and circulated as Research Bulletin 74-33 of the Educational Testing Service, Princeton, NJ., 1974.

Ziller, R. C. A measure of the gambling response-set in objective tests . Psychometrika, 1957, 22, 289-292.