Memory type general class of estimators for population variance under simple random sampling

Abstract

With an emphasis on memory-type approaches, this study presents a class of estimators specifically designed for estimating population variation in simple random sampling (SRS). The term ‘memory-type’ pertaining to the use of exponentially weighted moving averages (EWMA) statistic for the estimation, which utilizes the current and past information in temporal surveys. The study provides expressions for the bias and mean square error (MSE) of these estimators and establishes conditions under which their efficiency represses the conventional and other memory-type estimators. The theoretical findings are reinforced through a comprehensive simulation study conducted on hypothetically sampled populations. Additionally, the effectiveness of the proposed estimators is demonstrated utilizing real-life population data. The findings of simulation and real data application show the superiority of the proposed memory type estimator over the existing usual and memory type estimators.

Keywords

• Population variance
• Memory-based methods
• Simple random sampling
• Exponentially weighted moving averages (EWMA)
• Mean square error (MSE)
• Efficiency performance