The familiar x 2 test is ordinarily used to compare percentage distributions of categorical data for two or more independent samples. A more accurate com parison of the percentages is sometimes obtained if the samples consist of matched individuals. The NcNemar test is generally used when comparing only two related samples. Where there are three or more samples the Cochran Q test is used. Both of these tests apply only to the case of dichotomized responses. This thesis extends the Cochran Q test to the case where the responses are multinomial. A generalized statistic corresponding to Cochran's result is obtained. As in Cochran's case this statistic has asymptotically a x 2 distribution with degrees of freedom equal to one less than the number of samples.
Paul Y. Yahiku
Jen W. Kuzma
C. Duane Zimmerman
Master of Science (MS)
Year Degree Awarded
Date (Title Page)
Library of Congress/MESH Subject Headings
Loma Linda University Libraries
This title appears here courtesy of the author, who has granted Loma Linda University a limited, non-exclusive right to make this publication available to the public. The author retains all other copyrights.
Cho, Soo-Young, "An Extension of the Cochran Q test" (1971). Loma Linda University Electronic Theses, Dissertations & Projects. 619.
Loma Linda University Electronic Theses and Dissertations
Loma Linda University. Del E. Webb Memorial Library. University Archives