We discuss the problem of non-response in the study of auxiliary variables while estimating population mean in stratified random sampling. We propose a class of exponential-type estimators that uses known values of some population parameters of the auxiliary variable, such as coefficient of variation, kurtosis, skewness, standard deviation and correlation coefficient. Properties of the proposed estimators, including efficiency and optimality conditions, are obtained up to first order approximation. The theoretical results are illustrated with numerical data, which show the efficiency of some of the proposed estimators, in terms of having smaller mean square errors, over the customary non-response mean estimator based only on the study variable.

non-response, stratified random sampling, auxiliary information, exponential-type estimators.