近年來針對成對設計的相等性評估，多應用在反應比率的差異、反應比率的比值、以及勝算比上。然而，這些相關係的量測只針對離散型的資料，無法解決連續型的資料所面臨的相同問題。因此在這篇論文中針對成對的連續型資料討論其相關係數的相等性。首先，會先回顧一些用來比較兩組相關係數是否相等的方法，並且利用近似的信賴區間方式來計算兩組相關係數的相等性。在過去的研究中提到如果將相關係數做Fisher-transformation後，相關係數的分配會更近似常態分配。利用前面建議的方法計算型I誤差發生的機率和檢定力，且也利用拔靴法做計算，並比較兩種方法的結果。我們也比較在相等性的檢定時，相關係數做Fisher-transformation後的常態近似檢定是會比較好的。最後，給一個實際的例子，利用這個論文提出的方法，來做相等性的檢定。

Current methods for evaluation of equivalence under a matched-pair design employ either difference in proportions, relative risk or odds ratio as measures of risk association. However, these measures of association are only for discrete data and they can not be applied to continuous data. In this paper, under a matched-pair design, the correlation coefficient is proposed to assess the equivalence for continuous data. We review the methods to test two different correlation coefficient equal or not, and suggest the use of the asymptotic confidence interval of the difference of two correlation coefficients for evaluation of equivalence. In the past research, the correlation coefficients that take Fisher-transformation are more asymptotic normal distribution. A simulation study was conducted to empirically investigate the size and power of the proposed procedures. A bootstrap-based approach is proposed and compared to the empirically investigate the size and power. We compare the correlation coefficient that take Fisher-transformation are more powerful than they are not in equivalence. Finally, a numerical example is used to illustrate the application of the proposed procedure.

[1] Anderson, S., and Hauck, W.W. (1983). A new procedure for testing equivalence in comparative bioavailability and other clinical trials. Communications in Statistics － Theory and Methods. Vol. 12, 2663-2692.
[2] Casella, G., and Berger, R.L. (2002). Statistical Inference 2nd edition. Thomson Learning, Australia, 381.
[3] Dunn, O.J., and Clark, V.A. (1969). Correlation coefficients measured on the same individuals. Journal of the American Statistical Association, Vol.64, 366-377.
[4] Dunnett, C.W., and Gent, M. (1977). Significance testing to establish equivalence between treatments with special reference to data in the form of 2×2 tables, Biometrics, Vol. 33, 593-602.
[5] Fisher, R.A. (1921). On the probable error of a coefficient of correlation deduced from a small sample. Metron, Vol.1, 1-32.
[6] Hauschke, D., Steinijans, V.W., and Diletti, E. (1990). A distribution-free procedure for the statistical analyses of bioequivalence studies. Int. J. Clin. Pharmacol. Ther. Toxic. Vol. 28, 72-78.
[7] Hotelling, H. (1940). The selection of variates for use in prediction with some comments on the general problem of nuisance parameters. Annals of Mathematical Statistics, Vol.11, 271- 283.
[8] Liu, J.P. (1991). Bioequivalence and intrasubject variability. Journal of Biopharmaceutical Statistics. Vol. 1, 205-219.
[9] Liu, J. P., and Chow, S. C. (1992). Design and analysis of bioavailability and bioequivalence studies. Marcel Dekker, New York, 70 – 125.
[10] Masaryk, A.M., Ross, J.S., DiCello, M. C., Modic, M. T., Paranandi, L., and Masaryk, T.J. (1991). 3DFT MR angiography of the carotid bifurcation: Potential and limitations as a screening examination, Radiology, Vol. 179, 797-804.
[11] Metzler, C.M. (1974). Bioavailability: A problem in equivalence. Biometrics, Vol. 30, 309-317.
[12] Olkin, l., and Siotani, M. (1964). Asymptotic distribution of functions of a correlation matrix (tech. Rep. 6). Stanford, Calif.: Stanford University, Laboratory for Quantitative Research in Education.
[13] Pearson, K., and Filon, L.N.G. (1898). Mathematical contributions to the theory of evolution: IV. On the probable errors of frequency constants and on the influence of random selection on variation and correlation. Philosophical Transactions of the Royal Society of London, Series A, Vol.191, 229 – 311.
[14] Peter, C.C., and Van Voorhis, W.R. (1940). Statistical procedures and the mathematical bases. New York: McGraw-Hill.
[15] Schuirmann, D.J. (1981). On hypothesis testing to determine if the mean of a normal distribution is continued in a known interval. Biometrics, Vol.37, 671.
[16] Schuirmann, D.J. (1987). A comparison of the two one-sided tests procedure and the power approach for assessing the equivalence of average bioavailability. J. of Pharmacokin. Biopharm, Vol. 15, 657-680.
[17] Steiger, J. H. (1978). Multivariate analysis for correlations (Tech. Rep. 78-35). Vancouver: University of British Columbia, Institute of Applied Mathematics and Statistics, September.
[18] Williams, E.J. (1959). The comparison of regression variable. Journal of the Royal Statistical Society, Series B, Vol.21, 396 – 399.