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: initial value of a regressor in panel data

From   Jan Bryla <>
To   "" <>
Subject   st: RE: initial value of a regressor in panel data
Date   Thu, 24 Feb 2011 11:02:05 +0100


To make an initial value a regressor you could do something like

Sort countryid time
Bys countryid: gen gdp_ini=gdp[1] 

Regarding the insignificance of your regressors, I guess that would depend on a lot of things, so I would suggest you seek help in the existing literatue within the subject you are working on.

Hope this helps

-----Original Message-----
From: [] On Behalf Of Humaira Asad
Sent: 24. februar 2011 00:14
Subject: st: initial value of a regressor in panel data

I am working with a panel of 107 countries over 1960 to 2010 averaged in five years data.
I have two questions:
1. How can I take initial value of say real gdp per capita as one of the regressors.
2. I have estimated the equations using xtabond, xtdpd etc but all the regressors are insignificant, how can i improve the estimates?
I have followed Cameron and Trivedi's Books Chap 9.

Humaira Asad
PhD Research Scholar

UoE Business School

University of Exeter, England 		 	   		  
*   For searches and help try:

*   For searches and help try:

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