• Journal of the Korean Statistical Society
• /
• v.24 no.1
• /
• pp.257-266
• /
• 1995

Consider a p-variate $(p \geq 4)$ normal distribution with mean $\b{\theta}$ and identity covariance matrix. For estimating $\b{\theta}$ under a quadratic loss we investigate the behavior of risks of Stein-type estimators which shrink the usual estimator toward the mean of observations. By using concavity of the function appearing in the shrinkage factor together with new expectation identities for noncentral chi-squared random variables, a characterization of estimators with nondecreasing risk is obtained.

• Journal of the Korean Statistical Society
• /
• v.19 no.2
• /
• pp.182-185
• /
• 1990

Let a p-component vector y have a p-variate normal distribution $N(b\theta, \Sigma), \Sigma$ unknown, b specified, then for testing $\theta = 0$ against general $\theta$, Khatri and Rao (1987) derive a certain t test and obtain its power function. This paper presents a direct derivation of this power function in terms of the original variates unlike Khatri and Rao (1987) who resort to the canonical transformations of the original variates and the conditional distributions.