An efficient class of estimators using two auxiliary attributes

This paper proposes a class of estimators based on information of two auxiliary attributes. The expressions of mean square errors of the proposed class of estimators are derived in a general form. It is shown that the proposed class of estimators is always more efficient than regression estimator based on two attributes, estimators recently proposed by Verma et al. (2013) and Malik and Singh (2013). In addition, we support this theoretical result by an empirical study using original data to show the superiority of the constructed estimators over others.