Modified Ridge Parameters for Seemingly Unrelated Regression Model |
| |
Authors: | Z Zeebari B M G Kibria |
| |
Institution: | 1. Department of Economics, Finance, and Statistics , J?nk?ping University , J?nk?ping , Sweden;2. Department of Mathematics and Statistics , Florida International University , Miami , FL , USA |
| |
Abstract: | In this article, we modify a number of new biased estimators of seemingly unrelated regression (SUR) parameters which are developed by Alkhamisi and Shukur (2008
Alkhamisi , M. A. ,
Shukur , G. ( 2008 ). Developing ridge parameters for SUR model . Commun. Statist. Theor. Meth. 37 ( 4 ): 544 – 564 .Taylor & Francis Online], Web of Science ®] , Google Scholar]), AS, when the explanatory variables are affected by multicollinearity. Nine estimators of the ridge parameters have been modified and compared in terms of the trace mean squared error (TMSE) and (PR) criterion. The results from this extended study are the also compared with those founded by AS. A simulation study has been conducted to compare the performance of the modified estimators of the ridge parameters. The results showed that under certain conditions the performance of the multivariate ridge regression estimators based on SUR ridge R MSmax is superior to other estimators in terms of TMSE and PR criterion. In large samples and when the collinearity between the explanatory variables is not high, the unbiased SUR, estimator produces a smaller TMSEs. |
| |
Keywords: | Modified SUR ridge regression Monte Carlo simulations Multicollinearity TMSE |
|
|