The asymptotic normality for the simulation method of the repeated measures model

Abstract

Using the simulation method is important for evaluating estimator properties, and through asymptotic normality in simulation, we can approximate estimator distributions to make important statistical inferences and informed statistical decisions. When estimating parameters of any statistical model, we search for estimators that are both unbiased and efficient, which is the main focus of our research. Althoughmany methods like the maximum likelihood technique are effective in estimating the parameters of the repeated measures model, the power of these methods is limited by estimating bias variance in the model's random components .This study aims to address the limitations of current methods by minimizing the bias in variance estimations of a repeated measures model. We utilize the maximum likelihood approach (mean bias reducing method) along with the simulation technique to analyze the performance of the new estimator by verifying its asymptotic normality. This study aims to address the limitations of current methods by minimizing the bias in variance estimations of a repeated measures model. We utilize the maximum likelihood approach (mean bias reducing method) along with the simulation technique to analyze the performance of the new estimator by verifying its asymptotic normality. As a consequence, the new estimator was normality convergent.