Question: Consider the multiple linear regression model (2 y = Bo + Bix1 + B2xz + u E(ulx1, x2) = 0 Var(ulx1, X2 =02Suppose that B2


Consider the multiple linear regression model (2 y = Bo + Bix1 + B2xz + u E(ulx1, x2) = 0 Var(ulx1, X2 =02Suppose that B2 # 0. Suppose also that the above model satisfies the Gauss- Markov assumptions. We would like to find the marginal effect of x1 on y: 1 a. List the Gauss-Markov assumptions for this model (8 marks). b. Suppose further that X2 has a linear relationship with x1: X2 = bo + 6,*+r E(r|x]) = 0 Var(r|x] ) = 12 Now, if we run the following regression and would like to estimate the marginal effect of x] on y: y =dotax tv Show E(y|x1) in terms of x, and B1. Can we interpret the estimated an as the marginal effect of x1 on y? Why? (10 marks) c. Show E(v|x ) and Var(v|x1) respectively. (7 marks)
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
