Presentation on theme: "CHAPTER 3: TWO VARIABLE REGRESSION MODEL: THE PROBLEM OF ESTIMATION"— Presentation transcript:
1 CHAPTER 3: TWO VARIABLE REGRESSION MODEL: THE PROBLEM OF ESTIMATION ECONOMETRICS ICHAPTER 3: TWO VARIABLE REGRESSION MODEL: THE PROBLEM OF ESTIMATIONTextbook: Damodar N. Gujarati (2004) Basic Econometrics, 4th edition, The McGraw-Hill Companies
2 3.1 THE METHOD OF ORDINARY LEAST SQUARES PRF:SRF:How is SRF determined?We do not minimize the sum of the residuals!Why not?
4 3.1 THE METHOD OF ORDINARY LEAST SQUARES We adopt the least-squares criterionWe want to minimize the sum of the squared residuals.This sum is a function of estimated parameters:Normal equations:
5 3.1 THE METHOD OF ORDINARY LEAST SQUARES Solving the normal equations simultaneously, we obtain the following:Beta2-hat can be alternatively expressed as the following:
6 Three Statistical Properties of OLS Estimators I. The OLS estimators are expressed solely in terms of the observable quantities (i.e. X and Y). Therefore they can easily be computed.II. They are point estimators (not interval estimators). Given the sample, each estimator provide only a single (point) value of the relevant population parameter.III. Once the OLS estimates are obtained from the sample data, the sample regression line can be easily obtained.
7 The properties of the regression line It passes through the sample means of Y and X.
21 Example of perfect multicollinearity: X1 = 2X2+X3 3.2 The Classical Linear Regression Model: The Assumptions Underlying the Method of Least SquaresExample of perfect multicollinearity: X1 = 2X2+X3YX1X2X36521111041722162519833315
22 PRECISION OR STANDARD ERRORS OF LEAST SQUARES ESTIMATES var: variancese: standard error: the constant homoscedastic variance of ui: the standard error of the estimate: OLS estimator of
23 Gauss – Markov TheoremAn estimator, say the OLS estimator , is said to be a best linear unbiased estimator (BLUE) of β2 if the following hold:
27 The coefficient of determination r2 The quantity r2 thus defined is known as the (sample) coefficient of determination and is the most commonly used measure of the goodness of fit of a regression line. Verbally, r2 measures the proportion or percentage of the total variation in Y explained by the regression model.