Consider the simple regression model with classical measurement error, y = (0 + (0x* + u, where
Question:
(i) Show that
[The plim of 1 is Cov(w, y)/Var(w).]
(ii) How does the inconsistency in 1 compare with that when only a single measure is available (that is, m = 1)? What happens as m grows? Comment.
Fantastic news! We've Found the answer you've been seeking!
Step by Step Answer:
Related Book For
Introductory Econometrics A Modern Approach
ISBN: 978-0324660548
4th edition
Authors: Jeffrey M. Wooldridge
Question Posted: