Showing data of fixed effect variable in the panel

[Jinghui Yu]

Hi everyone!

I have a problem in my current research and it would be great if you could give me some advice and help with it!

I am working on the following equation as part of my research:

What i've done is to decompose the Z_it which is the productivity growth of all i countries and i've got d_t as the time dummies which is the common element of productivity among all the countries for the further research. However, now i have problems in removing the time dummies from the panel of Z_it for the fixed effect d_i, which is the country specific (or country element of) productivity growth for each country once it's estimated.

The time dummies are significant in each time period, but i seem to have difficulties removing the time dummies from the Z_it for the fixed effect which is the country element of productivity for each country.

It would be really appreciated if you could give me some help and advice!


Thanks again!

[Carlo Lazzaro]

Jinghui:
provided that I'm not clear with what you're after and what you coded before posting (please share this information, as per FAQ. Thanks).
That said, you may want to take a look at the community-contributed module -reghdfe-.

[Jinghui Yu]

Hi Carlo!

Thanks a lot for your reply!

As for my data, i have the gA as the productivity growth from 1971 to 2014 for 21 countries, i have worked out the time dummies with following code:

xtset Country Period
xtreg gA i.Period, fe

i was trying to replicate the results i have had that are all significant and worked out very well, but the results after this code are not the same as the results i worked out last time because the first column is Period and it is from 1972 to 2014. and coefficients of some years are not significant. i used the same data and same variable with same code but im not sure where it went wrong for the different results. and based on this, i need to remove the time dummies for each country's productivity for the country specific element of productivity growth from 1971 to 2014.

it would be really really appreciated if you could give me some advice. Thanks a lot!!

Best,
Jinghui

[Carlo Lazzaro]

Jinghui:
coud you please provide an excerpt/example of your dataset via -dataex-? Thanks.
In addition, you're dealing with a T>N panel dataset.
Therefore, you should switch from -xtreg- to -xtregar- or -xtgls-.