[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: GMM estimation

From   John Bunge <[email protected]>
To   [email protected]
Subject   Re: st: GMM estimation
Date   Sat, 22 Sep 2007 13:56:29 +0200

Hi Nanna,

Arellano/Bond is for panel data and your dataset obviously is not a panel data set.

You have to look for a adequate time series technique. There are lots of possible methods. If you have quarterly or montly data, I would first try to estimate a VAR or a VECM.

Good luck,


Von: [email protected]
Gesendet: 22.09.07 13:40:01
An: [email protected]
Betreff: st: GMM estimation

Dear Sir/Madam, 

I am currently trying to estimate a model containing lagged dependent 
variables as explanatory variables along with lagged explanatory variables 
(Y = a + BXt-1+BXt-2 + Yt-1+Yt-2+e). It is time-series data (1977-2005) for 
one country only and I am wondering if the Arellano-Bond GMM method for 
dynamic panel is the correct estimation method. 

More specifically, I have a data set for 1977-2005 for one country with the 
following variables: dependent variable is investment at time t, explanatory 
variables are investment at time t-1 and t-2, FDI inflows at time t, t-1, 
and t-2, and growth rate at time t-1, t-2. Since it is a dynamic model OLS 
is not appropriate, but is A-B GMM estimation method the most appropriate 

It's quite an urgent matter and I really look forward to hearing from you. I 
apologize for the inconvenience. 

Your help is greatly appreciated! 

Nanna Matsson
World Trade Institute

* For searches and help try:

Jetzt neu! Schützen Sie Ihren PC mit McAfee und WEB.DE. 3 Monate
kostenlos testen.

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index