Statalist The Stata Listserver

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

st: =?gb2312?B?tPC4tDogWHRhYm9uZCBSb2J1c3Q=?=

From   "Cheng, Xiaoqiang" <>
To   <>
Subject   st: =?gb2312?B?tPC4tDogWHRhYm9uZCBSb2J1c3Q=?=
Date   Sun, 12 Nov 2006 23:38:14 +0100

3 solutions in general,
1. Try to take lags starting from t-2 or t-3 as instruments. You might find a favorable Sargan test.
2. Exclude some variables that might both correlated with endogenous variables and LHS variable from instruments.
3. Use xtabond2 rather then xtabond.
Hope these help.


From: 代表 Fausto Araujo
Sent: 11/12/2006 (星期日) 7:50 下午
Subject: st: Xtabond Robust


I have a problem with xtabond, Sargan test. Any model was not acceptable
because Sargan test. I saw Xtabond robust. In this command don’t have a
sargan estimative. When can I use xtabond robust? Is wrong I use xtabond
robust in my case? If is wrong, what can I use(have other command which
would better)?


O Windows Live Spaces é seu espa?o na internet com fotos (500 por mês), blog
e agora com rede social

*   For searches and help try:



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