Re: Re: st: xtreg individual and year fixed effects

[Christopher Baum <kit.baum@bc.edu>]

<>
On Apr 1, 2012, at 2:33 AM, Daniele wrote:

> So now you suggest me to generate 2 new variables, one that represents
> the country-product fe and one that represents the year fe and then to
> sum them to the residual.
> 
> I think that something like this should work:
> 
> by countryproduct: egen cp_fe=mean(ife)
> 
> by year: egen year_fe=mean(ife)
> 
> gen newvar= cp_fe + year_fe + resid
> 
> Thank you very much
> 
> Daniele
> 
> 2012/3/29 Christopher Baum <kit.baum@bc.edu>:
>> <>
>> webuse grunfeld,clear
>> xtreg invest mvalue kstock i.year, fe
>> predict double ife, u
>> replace ife = ife + _b[_cons]
>> forv i=1936/1954 {
>> Â  Â  Â  Â qui replace ife = ife + _b[`i'.year] if year==`i'
>> }
>> su ife
>> tabstat ife, by(year)
>> tabstat ife, by(company)


No, it will not work. If you do the first three commands with grunfeld and then do

tabstat ife, by(company) 
tabstat ife, by(year)

you will see that ife has a (approx) zero mean for every year, by construction. That is because it is the individual fixed effect. To take account of the year fixed effects you need to do EXACTLY what I have spelled out above. 

Furthermore, why would you want to add the FE to the residual? I thought you were trying to identify the non-idiosyncratic piece.
If you want the individual FE + residual, then predict option -ue- will give you that. Then all you need to do is add the year effect as above.

Kit


Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                             An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
  An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/