Innovative memory-type calibration estimators for better survey accuracy in stratified sampling

Calibration methods play a vital role in improving the accuracy of parameter estimates by effectively integrating information from various data sources. In the context of population parameter estimation, memory-type statistics-such as the exponentially weighted moving average (EWMA), extended exponentially weighted moving average (EEWMA), and hybrid exponentially weighted moving average (HEWMA)-leverage both current and historical data. This study proposes new ratio and product estimators within a calibration framework that utilizes these memory-type statistics. A simulation study is conducted to evaluate the performance of the proposed estimators. The mean squared error (MSE) and relative efficiency (RE) are computed, accompanied by graphical representations to illustrate the behavior of the estimators. The performance of the proposed estimators is compared with existing memory-type estimators. Furthermore, a real-world application is presented to validate the effectiveness of the proposed methods. The comparison, based on MSE and RE across different values of the smoothing constant, demonstrates that the calibration-based memory-type estimators outperform the existing approaches. The results indicate that the proposed estimators consistently achieve lower MSE and higher RE, confirming their superiority over traditional methods.