Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Panel Data Within Outside Region Effects

From   Aljar Meesters <>
Subject   Re: st: Panel Data Within Outside Region Effects
Date   Fri, 5 Apr 2013 19:49:36 +0200

Dear Max,

I do not know exactly what you are estimating, but the effects that
you are looking for are not be provided by xtreg. If you are
interested in these effects you should look for a spatial panel
estimator that can provide these. However, as far as I know, your
question is not standard in the spatial econometrics literature. A
standard spatial effect that can be calculated quite easily is the
effect of non local FDIs on the local private economy. If you want to
estimate such an effect you can use:

bysort t : egen allOtherFDI = total(FDI)
replace allOtherFDI = allOtherFDI - FDI

xtreg PE FDI allOtherFDI, fe

where I assume that t is your time variable, FDI is your FDI variable
and PE is the variable of Private Economy. Note that in this case FDIs
in all regions are weighted equally, even FDIs in regions that are far
away. So, you may want to weight the FDIs with respect to the distance
between regions, which is a common approach.


2013/4/5 Massimiliano Sassone <>
> Dear all,
> I am trying to evaluate the effects that FDI have on the Private
> Economy using Stata 11.
> I am running -xtreg, fe- on a panel data with 31 regions, named 1 to
> 31,  and 8 years, 2000 to 2008. I chose the fixed effects method after
> having interpreted the results of the -xtoverid- test.
> My question is:
> how can I use Stata to evaluate the Within Region and Outside Region
> FDI effect on the Private Economy?
> For example, how can I check the effects that FDI in Region 1 have on
> the Private Economy in Region 1 itself, and in all the other Regions
> (2-31) combined?
> I hope the question is clear enough.
> Thank you very much for the support
> Massimiliano (Max) Sassone
> *
> *   For searches and help try:
> *
> *
> *
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index