Comparison of the performance of some r- (k,d) class estimators with the (PCTP) estimator that used in estimating the general linear regression model in the presence of autocorrelation and multicollinearity problems at the same time "

Abstract

In the analysis of multiple linear regression, the problem of multicollinearity and auto-correlation drew the attention of many researchers and given the appearance of these two problems together and their bad effect on the estimation, some of the researchers found new methods to address these two problems together at the same time. In this research a comparison for the performance of the Principal Components Two Parameter estimator (PCTP) and The (r-k) class estimator and the r-(k,d) class estimator by conducting a simulation study and through the results and under the mean square error (MSE) criterion to find the best way to address the two problems together. The results showed that the r-(k,d) class estimator is the best estimator.