A calibrated synthetic estimator for small area estimation

Abstract Synthetic estimators are known to produce estimates of population mean in areas where no sampled data available, but such usually highly biased with invalid confidence statements. This paper presents a calibrated synthetic estimator the which addresses these problematic issues. Two special cases this were obtained form combined ratio and regression estimators, using selected tuning parameters under stratified sampling. In result, their biases variance derived. The empirical demonstration usage involving proposed shows that they provide better than existing discussed study. particular, examined through simulation three distributional assumptions, namely normal, gamma exponential distributions. results show displaying less relative bias greater efficiency. Moreover, prove more consistent classical estimator. further evaluation carried out coefficient variation provides additional confirmation estimator’s advantage over ones relation small area estimation.