Chapter 2
In explaining each of the misspecification issues 1 through 5, I start from a basic model of the form
y = a0 + a1x + e (2.1)
Typically the errors, e, are assumed NIID. However, if any one of the misspecifications 1 through 5 exist, some area of this assumption is violated. It is these violations that we will identify and, if encountered, will correct for. Correcting for these basic forms of misspecification will allow the empirical researcher to draw more accurate inference from their results and, therefore, have more confidence that the outcomes they reach are some of the best attainable.
The order with which I describe, test, and correct for each misspecification is not by accident. The ordering of these ...
Get Building Better Econometric Models Using Cross Section and Panel Data now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.