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: RE: SVAR estimation question

From   DE SOUZA Eric <>
To   "" <>
Subject   st: RE: SVAR estimation question
Date   Tue, 10 May 2011 20:48:44 +0200

This is common practice in estimating simultaneous equation models, of which an SVAR is a particular case. One "concentrates out" the variance covariance matrix and then maximises with respect to the remaining parameters.
Indeed maximum likelihood estimation of a linear regression model (y = x.beta + u)  with homoscedastic errors is often (always ?) presented in this way in textbooks.

Eric de Souza
College of Europe
Brugge (Bruges), Belgium

-----Original Message-----
From: [] On Behalf Of Charles Koss
Sent: 10 May 2011 18:01
To: Stata List
Subject: st: SVAR estimation question

Dear list members:

Does someone knows why stata estimates SVAR models using the concentrated likelihood function instead of estimating simultaneously the parameters of the underlying var altogether with matrices A and B?
what is the logic of this conditional estimation?

Reference page in stata 11: 405

Thank you,


Charles Koss
*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index