It is shown for the Shine-Bower single-subject ANOVA that the numerator and denominator of all F tests based on the Shine-Bower error term are independent of each other. It is also shown that the same property holds for all such tests in the Shine Combined ANOVA except for the test for the trial by subject interaction.
Get full access to this article
View all access options for this article.
References
1.
Scheffé, H.The analysis of variance. New York: John Wiley & Sons, Inc. , 1959.
2.
Shine, L. C.A design combining the single-subject and multi-subject approaches to research. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1973, 33, 763-766. (a)
3.
Shine, L. C.A multi-way analysis of variance for single-subject designs. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1973, 33, 633-636. (b)
4.
Shine, L. C.An extension of the Shine combined analysis of variance. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT , 1974, 34, 47-52.
5.
Shine, L. C. and Bower, S. M.A one-way analysis of variance for single-subject designs . EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1971, 31, 105-113.
6.
Winer, B. J.Statistical principles in experimental design (2nd ed.). New York: McGraw-Hill, 1971.
