Estimating the Population Mean in Stratified Random Sampling Using Combined Regression with the Presence of Outliers

Abstract

In this research, the covariance estimates were used to estimate the population mean in the stratified random sampling and combined regression estimates. were compared by employing the robust variance-covariance matrices estimates with combined regression estimates by employing the traditional variance-covariance matrices estimates when estimating the regression parameter, through the two efficiency criteria (RE) and mean squared error (MSE). We found that robust estimates significantly improved the quality of combined regression estimates by reducing the effect of outliers using robust covariance and covariance matrices estimates (MCD, MVE) when estimating the regression parameter. In addition, the results of the simulation study proved that the Minimum covariance determinant (MCD) method is highly efficient at all sample sizes (n=35, 75, 150, 200, 500) and then followed by the method of the smallest ellipse Minimum volume Ellipsoid (MVE) handles outliers in the dataset, where it has lower values (MSE).