Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: OLS, 2SLS, & SE

From   "Richard C. Feiock" <>
Subject   st: OLS, 2SLS, & SE
Date   Tue, 30 Nov 2010 16:08:41 +0900


I am running OLS and 2SLS and comparing the results from the two
analyses. My results show that the SE for the coefficient is larger in
OLS, compared to the SE for the same variable (instrument) in 2SLS. I
thought that the results should be the other way around. I checked
with all the data and procedures and the results are the same.

Why would I have this finding (the smaller SE in 2SLS) and would you
direct me to the relevant readings for this finding?

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index