Hostname: page-component-5f745c7db-xx4dx Total loading time: 0 Render date: 2025-01-06T07:22:36.488Z Has data issue: true hasContentIssue false
  • English
  • Français

A Simplified Method for Approximating Multiple Regression Coefficients

Published online by Cambridge University Press:  01 January 2025

J. A. Gengerelli
J. A. Gengerelli*
Affiliation:
University of California, Los Angeles
Get access Rights & Permissions [Opens in a new window]

Abstract

A method of exhaustion has been described for calculating regression coefficients. This method dispenses with the solution of simultaneous equations but utilizes a process of successive extraction in obtaining β's, where each successive β is maximized. This procedure permits the worker to discard as he goes along those weights which are deemed unsatisfactory for purposes of prediction. The β coefficients and the R in a problem involving a criterion and six independent variables were calculated in sixty minutes. The R's obtained by this method are smaller than those yielded by the Doolittle technique, but in problems which have been considered this discrepancy has not exceeded .05.

Type
Original Paper
Information
Psychometrika , Volume 13 , Issue 3 , September 1948 , pp. 135 - 146
Copyright
Copyright © 1948 The Psychometric Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bakst, A. A modification of the compilation of the multiple correlation and regression coefficients by the Tolley and Ezekiel method. J. educ. Psychol., 1931, 22, 629–635.CrossRefGoogle Scholar
Brolyer, C. R. Another short method for calculating β weights and the resulting multiple R on a computing machine. J. gen. Psychol., 1933, 8, 278–281.CrossRefGoogle Scholar
Dwyer, P. S. The square root method and its use in correlation and regression. J. Amer. Statist. Assoc., 1945, 40, 493–503.CrossRefGoogle Scholar
Franzen, R. and Derryberry, M. The routine computation of partial and multiple correlation. J. educ. Psychol., 1931, 22, 641–651.CrossRefGoogle Scholar
Garrett, H. C. A modification of Tolley and Ezekiel's method of handling multiple correlation problems. J. educ. Psychol., 1928, 19, 45–49.CrossRefGoogle Scholar
Griffin, H. D. Fundamental formulas for the Doolittle method using zero-order correlation coefficients. Ann. math. Statist., 1931, 2, 150–153.CrossRefGoogle Scholar
Griffin, H. D. Simplified schemas for multiple linear correlation. J. exper. Educ., 1933, 1, 239–254.CrossRefGoogle Scholar
Griffin, H. D. A further simplification of the multiple and partial correlation process. Psychometrika, 1936, 1, 219–228.CrossRefGoogle Scholar
Guilford, J. P. Psychometric methods, New York: McGraw Hill, 1936.Google Scholar
Horst, P. A short method for solving for a coefficient of multiple correlation. Ann. math. Statist., 1932, 3, 40–44.CrossRefGoogle Scholar
Horst, P. A general method for evaluating multiple regression constants. J. Amer. Statist. Assoc., 1932, 27, 270–278.CrossRefGoogle Scholar
Jackson, R. W. B. Approximate multiple regression weights. J. exp. Educ., 1943, 11, 221–225.CrossRefGoogle Scholar
Kelley, T. L. and Salisbury, F. S. An iteration method for determining multiple correlation constants. J. Amer. Statist. Assoc., 1926, 21, 282–292.CrossRefGoogle Scholar
Kelley, T. L. and McNemar, Q. Doolittle vs. Kelley-Salisbury iteration method for computing multiple regression coefficients. J. Amer. Statist. Assoc., 1929, 24, 164–169.CrossRefGoogle Scholar
Kurtz, A. K. A special case of the multiple correlation coefficient. J. educ. Psychol., 1929, 20, 378–385.CrossRefGoogle Scholar
Kurtz, A. K. The use of the Doolittle Method in obtaining related multiple correlation coefficients. Psychometrika, 1936, 1, 45–51.CrossRefGoogle Scholar
Mosak, J. L. On the simultaneous determination of the elementary regressions and their standard errors in subsets of variables. J. Amer. Statist. Assoc., 1937, 32, 517–524.CrossRefGoogle Scholar
Peters, C. C. and Wykes, E. C. Simplified methods for computing regression coefficients and multiple and partial correlations. J. educ. Res., 1931, 23, 383–394.CrossRefGoogle Scholar
Peters, C. C. and Van Voorhis, W. R. Statistical procedures and their mathematical bases, New York: McGraw-Hill, 1940.CrossRefGoogle Scholar
Salisbury, F. S. A simplified method of computing multiple correlation constants. J. educ. Psychol., 1929, 20, 44–52.CrossRefGoogle Scholar
Stead, Willia. and Shartle, C. L. Occupational counseling techniques (pp. 245–245). New York: American Book, 1940.Google Scholar
Thomson, G. H. On the computation of regression equations, partial correlations, etc.. Brit. J. Psychol., 1932, 23, 64–68.Google Scholar
Thomson, G. H. The factorial analysis of human ability, New York: Houghton-Mifflin, 1939.CrossRefGoogle Scholar
Tolley, H. R. and Ezckiel, M. J. B. A method of handling multiple correlation problems. J. Amer. Statist. Assoc., 1923, 18, 993–1003.CrossRefGoogle Scholar
Toops, H. A. in Martin, E. M. An aptitude test for policemen. J. crim. Law and Criminol., 1923, 14, 376–404.Google Scholar
Van Boven, Alic. A modified Aitken pivotal condensation method for partial regression and multiple correlation. Psychometrika, 1947, 12, 127–133.CrossRefGoogle ScholarPubMed
Waugh, F. V. A simplified method of determining multiple regression coefficients. J. Amer. Statist. Assoc., 1935, 30, 694–700.CrossRefGoogle Scholar
Waugh, F. V. The analysis of regression in sub-sets of variables. J. Amer. Stat. Assoc., 1936, 31, 729–730.CrossRefGoogle Scholar
Wherry, R. J. A modification of the Doolittle method: a logarithmic solution. J. educ. Psychol., 1932, 23, 455–459.CrossRefGoogle Scholar
Wherry, R. J. Two methods of estimating β weights. J. educ. Psychol., 1938, 29, 701–709.CrossRefGoogle Scholar
Wherry, R. J. An extension of the Doolittle method to simple regression problems. J. educ. Psychol., 1941, 32, 459–464.CrossRefGoogle Scholar
Wren, F. L. The calculation of partial and multiple coefficients of regression and correlation. J. educ. Psychol., 1938, 29, 695–700.CrossRefGoogle Scholar