Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: a error message in the first stage regression in the ivreg

From   "Mark Schaffer" <>
Subject   Re: st: a error message in the first stage regression in the ivreg
Date   Thu, 05 May 2005 11:27:27 +0100


Date sent:      	Thu, 05 May 2005 00:35:10 -0500
From:           	BINZHEN WU <>
Subject:        	st: a error message in the first stage regression in the ivreg
Send reply to:

> Dear Statalist,
> I got a error message and cannot figure out the reason. Could you
> help? I am runing the following model: Y=aT+bZ+cTZ+dX, Here,  TZ=T*Z
> is the interaction term, T is the time dummy (=1 after the policy
> change), and Z are the continuous endogenous treatments, X are
> exogenous variables.
> The command I use is: ivreg2 Y T X (TZ Z=W V TW TV)
> I got an error message for the first stage regression:
> Error: covariance matrix of moment conditions not of full rank; 
> specification
>        test stats not reported and standard errors above may be 
> meaningless.

A couple of ideas:

- Were you using robust or cluster as options?  Some phenomena, such 
as singleton dummies, can generate this.  See Vince Wiggins' very 
nice discussion at

- Do you get the same error if you drop TZ or Z as endogenous 
regressors?  With or without dropping W/V TW/TV at the same time?

- Not all the collinearities may have been dropped up front.  My 
recollection is that ivreg2 looks separately for collinearities in (T 
X), (TZ Z) and (W V TW TV), but collinearities may subsequently 
emerge that involve variables across these sets.

Hope this helps.


> This should be caused by collinearity, because collinearity variables
> have been automatically dropped by stata.
> Thank you very much.
> Binzhen 
> *
> *   For searches and help try:
> *
> *
> *

Prof. Mark E. Schaffer
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS  UK
44-131-451-3494 direct
44-131-451-3296 fax
44-131-451-3485 CERT administrator

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index