Summary
Dunn and Clark (1969, 1971) have presented numerical studies on the comparative performance of several classes of test statistics for the hypothesis HO: ρ12=ρ13 of the equality of two dependent correlation coefficients. This note suggests a X2 statistic for HO based on properties of the trivariate normal surface. The proposed test is approximately distribution-free and its power function representable approximately in terms of the non-centralx 2 with 1 DF. The relative efficiency is derived with reference to a class of tests studied by Neill & Dunn (1975).
Similar content being viewed by others
References
Bennett, B.M. (1962), On multivariate sign tests,J. R. Statist. Soc. B 24, 159–161. (1968), Note on X2 for matched samples,J. R. Statist. Soc. B 30, 368–370.
Dunn, O. J. and Clark, V. A. (1969), Correlation coefficients measured on the same individuals,J. Amer. Statist. Ass. 64, 366–377; (1971), Comparisons of tests of equality of dependent correlation coefficients,J. Amer. Statist. Ass. 66, 904–908.
Fieller, E. C., Lewis, T. and Pearson, E. S. (1955),Correlated Random Normal Deviates, No. 26,Tracts for Computers, University Press, Cambridge.
Fisher, R. A. (1928), The general sampling distribution of the multiple correlation coefficient,Proc. Roy. Soc. A 121, 654–673.
Hotelling, H. (1940), The selection of variates for use in prediction with some comments on the problem of nuisance parameters.Ann. Math. Statist. 11, 271–283.
Kendall, M. G. and Stuart, A. (1969),The Advanced Theory of Statistics, vol. I, 3rd ed. Griffin & Co. Ltd. London.
Neill, J. J. and Dunn, O. J. (1975), Equality of dependent correlation coefficients,Biometrics 31, 531–543.
Williams, E. J. (1959), The comparison of regression variables,J.R. Statist. Soc. B21, 396–399.
Rights and permissions
About this article
Cite this article
Bennett, B.M. On a test for equality of dependent correlation coefficients. Statistische Hefte 19, 71–76 (1978). https://doi.org/10.1007/BF02932765
Issue Date:
DOI: https://doi.org/10.1007/BF02932765