Statalist The Stata Listserver

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

st: Re: xtivreg2 - little questions

From   "Rodrigo A. Alfaro" <>
To   <>
Subject   st: Re: xtivreg2 - little questions
Date   Sun, 4 Jun 2006 13:44:37 -0400


(1) If you are planning to use lags of your dependent variable (LDV) with 
FE, you should learn how to compute the Anderson-Hsiao estimator (basically 
which instruments use) or Arellano-Bond estimator -xtabond- because FE with 
LDV generates bias in the estimation. Also, you could take a look of Bruno 
bias-corrected estimators -findit xtlsdvc- that improves the results 
obtained by AH or AB.

(2) I don't understand the question. Let me give you some information: I 
guess that i. command is not included in xtivreg2, but you found an 
alternative. In addition, time-dummies are fine even for dynamic model 
(where you have LDV). You may read Arellano-Bond paper, that provides an 
example using time-dummies.


----- Original Message ----- 
From: "Susie Enders" <>
To: <>
Sent: Sunday, June 04, 2006 9:12 AM
Subject: st: xtivreg2 - little questions


I am working with xtivreg2 and just wanted to clarify
3 little things:

1. Is it OK to specified lagged value(s) of the
dependent vaiable as regressors, as in
xtivreg2 profit l.profit l4.profit ...(other
regressors etc)?

2. xtivreg2 does not allow one to put in time dummies
in order to carry out 2-way fixed effects by
specifying, as one could with OLS. With
xtivreg2 one gets the error message:
i:  operator invalid
But if I generate individual time dummies (tab date,
g(time)) and then put these time dummies into the
specification as (time1-time48), the regression seems
to run OK. However, I wondered whether, since the
programme does not allow the option, this
approach was wrong anyway? I did include time dummies
( in my OLS regression as this seemed to make
sense and some broad comparability between the
specifications would be nice, but perhaps it is
nonsensical for xtivreg2.

3. What criteria should one use for the # of the bw(3)
option, the bandwidth of the HAC (in the case of
robust) covariance estimator, in order to get
estimates robust to autocorrelation? The examples I
saw used 3 or 4, but I was not sure how to choose

I would greatly appreciate any help with these small
but important (for me) questions.


24 FIFA World Cup tickets to be won with Yahoo! Mail
*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2022 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index