A note on estimating quantiles of exponential populations

Independent random samples from k exponential populations with the same location parameter [theta] but different scale parameters [sigma]1, ..., [sigma]k are available. We estimate the quantile [eta]1 = [theta] + b[alpha]1 of the first population with respect to squared error loss. Sharma and Kumar (1994) derived the UMVUE of [eta]1 and then obtained further improvements over it for b > n-1. For 0 [less-than-or-equals, slant] b < n-1, the improvements were obtained only for k = 2. In this note we show that it is possible to get such improvements for a general k.