THE ACCURACY OF DIFFERENT METHODS FOR ESTIMATING THE STANDARD ERROR OF CORRELATIONS CORRECTED FOR RANGE RESTRICTION

A Monte Carlo study was conducted to compare the accuracy of different estimates of the standard error of correlations corrected for restric tion in range. It was found that the procedure suggested by P. Bobko a nd A. Rieck, also derived by N. S. Raju and colleagues, generated the most accurate estimates of the standard error compared to other existi ng procedures. The study also repeated previous findings that Pearson correlations corrected for restriction in range resulted in more accur ate estimates of the population rho than did the restricted correlatio ns, but the accuracy of the approximation of population rho decreased as the selection criterion became higher. Another finding of the study was that the standard error of correlations under range restriction t ended to increase as the selection ratios decreased.