Suppose the dgp is y i = 0 x i + u i , u i
Question:
Suppose the dgp is , and . Assume that data are independent over and that is independent of . Note that the first four central moments of are , and .
(a) Show that the error term is conditionally heteroskedastic.
(b) Obtain plim . [Obtain and apply a law of large numbers.]
(c) Obtain , where the expectation is with respect to all stochastic variables in the model.
(d) Obtain plim , where .
(e) Using answers to the preceding parts give the default OLS result (4.22) for the variance matrix in the limit distribution of , ignoring potential heteroskedasticity. Your ultimate answer should be numerical.
(f) Now give the variance in the limit distribution of , taking account of any heteroskedasticity. Your ultimate answer should be numerical.
(g) Do any differences between answers to parts (e) and (f) accord with your prior beliefs?
Step by Step Answer:
Microeconometrics Methods And Applications
ISBN: 9780521848053
1st Edition
Authors: A.Colin Cameron, Pravin K. Trivedi