Estimation of finite population mean using multi-auxiliary information

This paper makes an attempt to provide a general class of estimators for the mean of a survey variable when the means as well as the variances of $p$ supplementary variables are known. The minimum attainable mean square error (variance) of the suggested class, up to terms of order $n^{-1}$, is obtained and the best estimator is also identified. The class of estimators recently developed by Diana and Perri (2006) can be easily viewed as a sub-class of this class when only the means of the auxiliary variables are taken into consideration. A case study is given in order to evaluate the gain in efficiency that can occur when the information on the variances in used.