光华方向专业金融计量lecture056检验.pptxVIP

Lecture 05--06 Linear Model Inference ;Outline;Introduction;2 Sampling distribution of the OLS estimators;Assumptions 1 (linear model): the true model (population model) is linear in the parameters Assumption 2 (random sampling): We have a random sample of n observations from the true model Assumption 3 (no perfect collinearity) In the sample (and therefore in the population), none of the independent variables is constant, and there are no exact linear relationships among the independent variables. Assumption 4 (zero conditional mean or 外生性) The error u has an expected value of zero, given any values of the independent variables. Assumption 5 (homoskedasticity) ;The six assumptions MLR.1 through MLR.6 are called the classical linear model (CLM) assumptions. It can be shown that the OLS estimators are the minimum variance unbiased estimators Not only in all linear estimators Why can we make such an assumption? central limit theorem ;Potential problems under this assumption While the central limit theorem (CLT) holds in the infinite case, for finite dimension reality, the normal approximation can be poor depending on how many factors appear in u and how different are their distributions. While the CLT argument is that it assumes that all unobserved factors affect y in a separate, additive fashion. Nothing guarantees that this is so. Distribution of stock return? Stock price? But As we will see later, non-normality of the errors is not a serious problem with large sample sizes. ;Theorem 4.1 (normal sampling distributions) Why does it hold? OLS estimator is a linear combination of error terms! proof;3 Testing Hypotheses about a Single Population Parameter; 这个分布图的含义：做N0次Monte Carlo实验，估计的beta的经验分布;11;12;13;14;15;16;17;18;19;20;H0 vs H1 H0（往往与目的相反）与H1（往往是欲得到的结论） 不能拒绝H0，有什么意义？证伪（反例）问题 Economic versus Statistical Significance Statistically significant, but very small coefficient has any meaning? t can indicate statistical significance either because b?j is “large