Hi Statausers,
When trying to generate 3 fixed effects by subtracting all observations by
three different means (when generating dummy variables is not an option),
should we add back twice the mean of the whole sample?
To be more specific, in the following computation:
Y(i,j,k)-Mean_Y_i-Mean_Y_j-Mean_Y_k+2*Mean_Y=a+b[X(i,j,k)-Mean_X_i-Mean_X_j-
Mean_X_k+2*Mean_X]
will I be able to get the fixed effects for i, j, and k?
Or should I combine
Y(i,j,k)-Mean_Y_i-Mean_Y_j+Mean_Y=a+b[X(i,j,k)-Mean_X_i-Mean_X_j+Mean_X]
with xtreg, fe(where fe is the k fixed effect)?
Thank you very much for your time and help.
Maggie
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/