Suppose you detect heteroskedasicity and or auto correlated


Suppose you detect heteroskedasicity and /or auto correlated errors in your regression. What is the difference between (I) calculating robust errors versus (ii) conducting a weighted least squares or feasible generalized least squares analysis. What are the pros and cons of each approach? Give an example of when each might be preferred over the other.

Request for Solution File

Ask an Expert for Answer!!
Business Economics: Suppose you detect heteroskedasicity and or auto correlated
Reference No:- TGS01115094

Expected delivery within 24 Hours