This preview shows pages 1–8. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 51Regression with a Single Regressor: Hypothesis Tests and Confidence Intervals (SW Chapter 5) OverviewNow that we have the sampling distribution of OLS estimator, we are ready to perform hypothesis tests about 1and to construct confidence intervals about 1Also, we will cover some loose ends about regression: oRegression when Xis binary (0/1) oHeteroskedasticity and homoskedasticity (this is new) oEfficiency of the OLS estimator (also new) oUse of the tstatistic in hypothesis testing (new but not surprising) 52But first abig picture view (and review) Wewantto learn about the slope of the population regression line, using data from a sample (so there is sampling uncertainty). There are four steps towards this goal: 1.State precisely the population object of interest 2.Derive the sampling distribution of an estimator (this requires certain assumptions) 3.Estimate the variance of the sampling distribution (which the CLT tells us is all you need to know if nis large) that is, finding the standard error (SE) of the estimator using only the information in the sample at hand!4.Use the estimator (1) to obtain a point estimate and, with its SE, hypothesis tests, and confidence intervals. 53Object of interest: 1in, Yi= + 1Xi+ ui, i= 1,, n 1= Y/X, for an autonomous change in X(causal effect) The Least Squares Assumptions: 1.E(uX= x) = 0. 2.(Xi,Yi), i=1,,n, are i.i.d. 3.Large outliers are rare (E(X4) < , E(Y4) < . The Sampling Distribution of 1: Under the LSAs, for nlarge, 1is approximately distributed, 1~ 214,vXNn, where vi= (Xi X)ui54Hypothesis Testing and the Standard Error of 1(Section 5.1) The objective is to test a hypothesis, like 1= 0, using data to reach a tentative conclusion whether the (null) hypothesis is correct or incorrect. General setup Null hypothesis and twosidedalternative: H: 1= 1,0vs. H1: 11,0where 1,0is the hypothesized value under the null. Null hypothesis and onesidedalternative: H: 1= 1,0vs. H1: 1< 1,055General approach: construct tstatistic, and compute pvalue (or compare to N(0,1) critical value) In general: t= estimator  hypothesized valuestandard error of the estimatorwhere the SEof the estimator is the square root of an estimator of the variance of the estimator. For testing the mean of Y:t= ,0/YYYsnFor testing 1, t= 11,01()SE, where SE(1) = the square root of an estimator of the variance of the sampling distribution of 156Formula for SE(1) Recall the expression for the variance of 1(large n): var(1) = 22var[()]()ixiXXun= 24vXn, where vi= (XiX)ui. The estimator of the variance of 1replaces the unknown population values of 2and 4Xby estimators constructed from the data: 12= 2221estimator of (estimator of )vXn= 212211121()niiniivnnXXn==where iv= ()iiXXu. 5712= 21221112...
View Full
Document
 Spring '11
 j

Click to edit the document details