Assuming a multiple linear regression model with q independent variables, a procedure is developed for determining the minimum statistically significant increase in the multiple correlation coefficient when an additional independent variable is considered for regression. The procedure is presented analytically as well as in table form. Examples are used to illustrate the process and describe table utilization.
Get full access to this article
View all access options for this article.
References
1.
Baggaley, A.Intermediate correlational methods . New York: John Wiley & Sons , 1964.
2.
Bmd, Biomedical computer programs. Berkeley, Calif.: University of California Press, 1973.
3.
Cohen, J.Multiple Regression as a General Data-Analytic Model. Psychological Bulletin, 1968, 70, 426-443.
4.
Crocker, D.Some Interpretations of the Multiple Correlation Coefficient. The American Statistician, 1972, 26, 31-33.
5.
Crow, E., Davis, F., and Maxfield, M.Statistics manual . New York: Dover Publications , 1960.
6.
Kerlinger F. and Pedhazur, E.Multiple regression in behavioral research. New York: Holt, Rinehart and Winston, Inc. , 1973.
7.
McNemar, Q.Psychological statistics. New York: John Wiley & Sons, 1969.
8.
Wallace, H. A. and Snedecor, G. W.Correlation and machine calculation. Ames: Iowa State College, 1931.
