An Advanced Class of Log-Type Estimators for Population Variance Using an Attribute and a Variable

In this paper, a class of log-type estimator using the auxiliary information in form of attribute as well as variable is proposed. Double sampling technique has been considered as it is assumed that the auxiliary information about the auxiliary attribute as well as auxiliary variable is unknown. Bias and mean squared error has been found up to the first order of approximation. The proposed classes are compared to some commonly used estimators both theoretically as well as empirically and they perform better than commonly used estimators available in the literature.