# Refer Back To Question # 3 Above: I) Use A Two-Sided T-Test To Check Individually Whether The Parameters

Refer back to Question # 3 above: i) Use a two-sided t-test to check individually whether the parameters B,B.B.,,,. and B, are equal to zero or not at 5% significance level? (Conduct 5 separate tests) ii) Use an F-test to check that LSAT and GPA are jointly insignificant versus they are significant at 1% significance level? View / Coefficient Diagnostics / Redundant Variable Test Likelihood ratio/ Isat gpa / OK iii) Why is the following sentence wrong? * The significance level of a statistical test gives us the probability that the Null Hypothesis is wrong. What is the correct meaning of the significance level of a statistical test? 1) Explain each of the following terms carefully in a simple or multiple regression). Which ones are fixed population parameters and which ones are estimators. For the estimators, indicate the population parameters they are estimating; 0,0°,0,VAR(B.), sd(B),selb) 2) Give reasons why the B, ‘s (the slope coefficients in a multiple regression) represent the partial effects (or ceteris paribus) of the related independent variables? 3) The median starting salary for new law school graduates is determined by log(salary)= B.+B, LSAT + B.GPA+B, log(libvol)+ B.log(cost) + Berank+u where LSAT is the log of median SAT score for the graduating class, GPA is the median college GPA for the class, libvol is the number of volumes in the law school library, cost is the annual cost of attending law school, and rank is a law school ranking (with rank = 1 being the best). 1) i) Explain why we expect B, 30. ii) What signs do you expect for the other slope parameters? Justify your answers. iii) Use the data in LAWSCH85.RAW and EVIEWS to estimate the equation above? Quick / Estimate equation / log(salary) c Isat gpa log(libvol) log(cost) rank

## Leave a Reply

Want to join the discussion?Feel free to contribute!