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]

Re: st: coefficient interpretation in OLS

From   John Antonakis <>
Subject   Re: st: coefficient interpretation in OLS
Date   Fri, 17 Aug 2012 11:18:02 +0200

Hi Lynn:

If you want formal (and simple) explanation run through Eq. 2 to 5c in:

Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A review and recommendations. The Leadership Quarterly, 21(6), 1086-1120.



Prof. John Antonakis
Faculty of Business and Economics
Department of Organizational Behavior
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

Associate Editor
The Leadership Quarterly

On 17.08.2012 11:06, Nick Cox wrote:
This really is covered in every decent regression text (in your case,
perhaps, an econometrics text). It's an inevitable consequence of any
correlations between X4 and X1, X2, X3.


On Fri, Aug 17, 2012 at 11:25 PM, Lynn Lee <> wrote:

When I run simple OLS regression or pooled OLS regression, I find if I add
more variables to the model, the coefficient on specific explanatory
variable can vary in magnitude. For example,
Y1=beta+beta1*X1+beta2*X2+beta3*X3+error term;
Y2=alpha+alpha1*X1+ alpha2*X2+ alpha3*X3+ alpha4*X4+error term.
The absolute value of estimates of beta1 or alpha1 can increase or sometimes
decrease.  I am not confident to explain this theoretically. Is it related
to potential endogeneity issue?
*   For searches and help try:

*   For searches and help try:

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