政治大学中山所共同选修课程名称：社会科学计量方法与统计－计量.PPT

政治大學中山所共同選修課程名稱：社會科學計量方法與統計－計量方法Methodology of Social Sciences授課內容： Further Inference in the Multiple Regression Model 日期：2003年11月6日 Restricted Least Square. Single parameter t test Joint null hypothesis F test The F test is based on a comparison of the sum of original, unrestricted multiple regression model to the sum of squared error from a regression model in which the null hypothesis is assumed to be true. Ex: y=α0 +α1 X1 +α2 X2+ α3 X3 + e H0: α2 = α3 = 0 Ie y= α0 +α1 X1 + e F= F≧ F(J,T-K, α) reject null hypothesis P=P(F(2,96) ≧F) ＜0.05 reject hypothesis No greater than or less than in null hypothesis H0: β2 =0, β3 =0… βK=0 H1: β2 =0 orβ3 =0 or both are non zero at least one of βK is non zero. F= T2 if J=1 Notice that if model is: y= β0 + β1 X1 + β2X22+ e =2β2X2 implies that X2 has different influence on each y. =β1 some influence of X1 on all y Another example y= β0 + β1 X1 + β2X2+ e H0: β1=β2 =0 H0: β1=β2 y= β0 + β1 (X1 + X2)+ e F1 test F(1,T-3, α) 8.6 Model Specification Three essential features of model choice : (1)choice of functional form (2)choice of explanatory variables (regressors) to be included in the model. (3)whether the multiple regression model assumption MR1-MR6 1. Omitted and irrelevant variables Ex:y= β0 + β1 X1 + β2X2+ e If we don’t haveX2 ,instead we regress y= β0 +β1*X1 + e then β1* =β1 if Cov(X1 ,X2) =0 And we have a very strong null assumption which is β1=0 However, Cov(X1 ,X2)=0 is very rare If an estimated equation has coefficients with unexpected sign, or unrealistic magnitudes, a possible cause of these strange results is the omission of an important variable. T-test or F- test, the two significant tests can assessing whether a variable or a group of variables should be included in an equat