Using Several Data to Structure Efficient Estimation of Intraclass Correlation Coefficients
The estimation of several intraclass correlation coefficients is considered when independent samples are drawn from multivariate normal distributions. We propose improved shrinkage estimator for the correlation parameters. It is shown analytically and computationally that the positivepart shrinkage estimator outperforms usual shrinkage estimator. The asymptotic relative performance of the estimators in the light of their bias and risk is presented both analytically and numerically. A Monte Carlo study is carried out to assess the performance of the proposed estimators for small samples.
KeywordsMultivariate Normal Distribution Shrinkage Estimator Noncentrality Parameter Multivariate Normal Population Unrestricted Estimator
Unable to display preview. Download preview PDF.
- Ahmed, S. E. (2001). Shrinkage estimation of regression coefficients from censored data with multiple observations. In Empirical Bayes and Likelihood Inference, S. E. Ahmed and N. Reid (eds.), 103–120, Springer Verlag, NewYork.Google Scholar
- Ahmed, S. E., Gupta, A. K., Khan, S. M. and Nicol, C. J. (2001). Simultaneous estimation of several intraciass correlation coefficients. To appear in Annals of the Institute of Statistical Mathematics.Google Scholar
- Elston, R.C. (1975). Correlation between correlations. Biometrika, 62, 133–148. Kapata, R. S. (1993). A test of hypothesis on familial correlations. Biometrics, 49, 569–576.Google Scholar
- Kubokawa, T. (1998). The Stein phenomenon in simultaneous estimation: A review. Nonparametric Statistics and Related Topics In S.E. Ahmed et al. (Eds.), 143–173, Nova Science, NewYork.Google Scholar