A Comparative Study of Some Methods of Estimating Robust Variance Covariance Matrix of the Parameters Estimated by (OLS) in Cross-Sectional Data

Abstract

Abstract

The Classical Normal Linear Regression Model Based on Several hypotheses, one of them is Heteroscedasticity as it is known that the wing of least squares method (OLS), under the existence of these two problems make the estimators, lose their desirable properties, in addition the statistical inference becomes unaccepted table. According that we put tow alternative,  the first one is  (Generalized Least Square) Which is denoted by (GLS), and the second alternative is to (Robust covariance matrix estimation) the estimated parameters method(OLS), and that the way (GLS) method neat and certified, if the capabilities (Efficient) and the statistical inference Thread on the basis of an acceptable but this method requires knowledge and knowledge of the nature of the problem and the private model of the problem, whether the Heteroscedasticity otherwise, the method (GLS) become inappropriate. The second alternative is a matrix contrast common variation fortified it does not require prior knowledge of the nature of your problem model, it's also an easy way and by this method has met with popular and interest in more than two decades by researchers, that the estimated of Robust covariance matrix the estimated parameters method(OLS), shall be according to data that is handled type, and we have dealt with in this study, cross-sectional data where the problem of Heteroscedasticity in contrast may be contained therein(Heteroscedasticity- Consistent Covariance matrix Estimation) and symbolized by the (HCCME) and includes many ways, and we have dealt with in our study of these methods