Multiple choice test reliability can be improved by allowing several or all options of a given item to be correct. A procedure due to Serlin and Kaiser (1978) is used to compute a principal components solution for scoring weights for all options. With this procedure coefficient alpha is maximized for a given multiple choice test.
References
1.
Armor, D. J.Theta reliability and factor scaling. In H. Costner (Ed.), Sociological methodology 1973-1974. San Francisco: Jossey-Bass Pub., 1974.
2.
Ebel, R. L.The ineffectiveness of multiple true-false test items . Educational and Psychological Measurement, 1978, 38, 1, 37-44.
3.
Heise, D. R. and Bornstedt, G. W.Validity, invalidity, and reliability. In E. F. Borgata (Ed.), Sociological methodology 1971. San Francisco: Jossey-Bass Pub., 1971.
4.
Nelson, L. R.Guide to LERTAP use and interpretation. Dunedin, N. Z.: University of Otabo, 1974.
5.
SAS Institute Inc. , SAS User's Guide, 1979 Edition. Raleigh, N.C.: Author, 1979.
6.
Serlin, R. C. and Kaiser, H. F.A method for increasing the reliability of a short multiple-choice test. Educational and Psychological Measurement, 1978, 38, 2, 337-340.
7.
Stanley, J. C. and Hopkins, K. D.Educational and psychological measurement and evaluation. Englewood Cliffs, NJ: Prentice-Hall, 1972.
8.
Veldman, D. J.Program AOBSD. New York: Holt, Rinehart, & Winston, Inc., 1967.
