Abstract
Currently one of the most important topics that are discussed in survey methodology is the accuracy of statistics or survey errors that may occur in the parameters estimation process and measurement error is one of the most important non-sampling error. In the present study general class of exponential and chain ratio type estimators are considered under two stage sampling for the estimation of population mean by using two auxiliary variables in the presence of measurement error. The bias and mean square error of these estimator has been obtained. Moreover, two artificial populations are generated to check the properties of proposed estimator among other estimator. The relative efficiency is also computed and the results revealed that proposed estimators are more efficient than the ratio estimator and by increasing sample size efficiency of suggested estimators are improved.