It is generally believed that the correction for restriction of range will yield exact correlational values only when the regression of z on x is both linear and homoscedastic. However it is shown that the correction formula can hold even for non-linear heteroscedastic relationships. A simple sufficient condition for the validity of the formula is described. Further, simple conditions for predicting when the formula will overestimate and underestimate are also described. The results are demonstrated in terms of a numerical example.
Get full access to this article
View all access options for this article.
References
1.
Birnbaum, Z. W. , Paulson, E., and Andrews, F. C.On the effect of selection performed on some coordinates of a multi-dimensional population. Psychometrika, 1950, 15, 191-204.
2.
Forsyth, R. A.An empirical note on correlation coefficients corrected for restriction in range . EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1971, 31, 115-123.
3.
Greener, J. M. and Osburn, H. G.Accuracy of corrections for restriction in range due to explicit selection in heteroscedastic and non-linear distributions. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 1980, 40, 337-346.
4.
Gulliksen, H.Theory of Mental Tests. New York: Wiley, 1950.
5.
Levin, J.The occurrence of an increase in correlation by restriction of range . Psychometrika, 1972, 37, 93-97.
6.
Linn, R. L.Range restriction problems in the use of self-selected groups for test validation . Psychological Bulletin, 1968, 69, 69-73.
7.
Lord, F. M. and Novick, R. M.Statistical theories of mental test scores. Reading Massachusetts: Addison-Wesley, 1968.
8.
Sands, W. A. , Alf, E. F., and Abrahams, N. M.Correction of validity coefficients for direct restriction in range occasioned by univariate selection. Journal of Applied Psychology, 1978, 63, 747-750.
