The difference in the results of two-stage seperated procedure and "ivreg"?
This post has NOT been accepted by the mailing list yet.
I have implemented two-stage separated procedure and the direct command "ivreg" to the same dataset. However, I found the results from the two methods are not the same, and the less is the number of the observations in the dataset, the greater is the difference between them. so what's the reason for the difference?