INTRODUCTION TO ECONOMETRICS II ECO 306 NOUN 74 2.3.6.0 Conclusion 2.3.7.0 Tutor-Marked Assignment 2.3.8.0 References/Further Reading 2.3.1.0 INTRODUCTION The multiple regression analysis is an extension of simple regression analysis. It covers cases in which the dependent variable is hypothesized to depend on more than one descriptive variable. Most of the multiple regression analysis is a direct extension of the simple regression model but hasonly two new dimensions. First, when evaluating the influence of a given descriptive variable on the dependent variable, we would now have to face the problem of discriminating between its effects and the effects of the other descriptive variables. Second, we shall have to tackle the problem of model specification. Often some variables might bethought to influence the behaviour of the dependent variable though, they might be unconnected. We shall have to decide which should be included in the regression equation and which should be omitted. However, the arrangement of flow for the multiple regression analysis is to firstly, carryout derivation of formula, then estimation procedures using values, followed by presentation of results and lastly interpretations. As an extension of unit 2, we shall discuss multicollinearity being a problem associated with CLRM. 2.3.2.0 OBJECTIVE The main objective of this unit is to provide broad understanding of the topic multiple regression analysis and appropriate alleviation measures associated with multicollinearity problems. This understanding includes the knowledge of the properties, principles behind the derivation of and how to interpret multiple regression coefficients. 2.3.3.0 MAIN CONTENTS 2.3.3.1The Multiple Regression Coefficients Derivation In the simple regression case, the values of the regression coefficients were chosen to make the fit as good as possible in the hope of obtaining most satisfactory estimates of
