Weighting Systems for Linear Functions of Correlated Variables When There is no Dependent Variable | Psychometrika | Cambridge Core (original) (raw)

Abstract

When no criterion variable is available, the combination of tests or other variables by the use of multiple correlation is not possible. Three methods of combining variables are described mathematically, and discussed with reference to the linear combination of tests. Iterative computational schemes are outlined and illustrated.

References

* Empirical evidence of this fact has been gathered and incorporated in a non-techical paper by J. M. Stalnaker entitled: “Weighting Questions in the Essay Type Examinations”, Journal of Education Psychology, 28, 1937.

* Cf.—Wilks, S. S., “Certain Generalizations in the Analysis of Variance”, Biometrika, 24, 1933, 471–494.

* H. Hotelling, “Analysis of a Complex of Statistical Variables into Principal Components,” The Journal of Educational Psychology, 24, 1933, 429

* Report on the Scholastic Aptitude Test 1930, College Entrance Examination Board, New York.

* H. Hotelling, loc. cit., pp. 417-441, 498-520.

† L. L. Thurstone, The Vectors of Mind, The University of Chicago Press, 1935.

‡ Horst, Paul, “Obtaining a Composite Measure from a Number of Different Measures of the Same Attribute,ȍ Psychometrika, 1, 1936, 53-60.

∥ Edgerton, H. A. and Kolbe, Laverne E., “The Method of Minimum Variation for the Combination of Criteria,” Psychometrika, 1, 1936, 183-188.