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

st: Re: fe regression with a threshold

From   "Rodrigo A. Alfaro" <>
To   <>
Subject   st: Re: fe regression with a threshold
Date   Tue, 10 Jul 2007 15:14:37 -0400


It seems that you want to estimate something like

gen double x2c = x2*h
xtreg y x1 x2 x2c, fe

... right?


----- Original Message ----- From: <>
To: "statalist" <>
Sent: Tuesday, July 10, 2007 1:31 PM
Subject: st: fe regression with a threshold

Dear Stata users,

I am trying to estimate the following function on a panel database of 3000 schools for ten years:

y = a + b*X1 + c*X2*I(h=0) + d*X2*I(h=1)

-- h= 0,1 is an already created dummy variable (each "schools" is assigned a value of zero or one, for every year);
-- X1 and X2 are the regressors.

I need to compute a fe regression, in order to find any difference between coefficients "c" and "d".

It would be great if someone could help me understand how to get it-

Thanks in advance for any help.


Scegli infostrada: ADSL gratis per tutta l'estate e telefoni senza canone Telecom

* For searches and help try:
*   For searches and help try:

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