Weighted regression - Panel data, fixed effects

[Meggy Pandolfo]

Hi everyone,
I am an Economics master student and I would be very grateful if somebody could help me.
I need to do a weighted regression, in particular I would like to weight every observation by the population size of the country (the higher the population, the more important should be the observation). I know the possibility of the aweight function; I have a panel dataset and I would like to know if I can use the aweight function in a fixed effect estimation.

Thank you in advance for the help.

Meggy

[Marcos Almeida]

Hello Meggy,

Here you have the information on weights (http://www.stata.com/help.cgi?weight).

Also, this excerpt from the manual (http://www.stata.com/manuals13/xt.pdf) may help you:

aweights, fweights, and pweights are allowed for the fixed-effects model. iweights, fweights, and pweights are allowed for the population-averaged model. iweights are allowed for the maximum-likelihood random-effects (MLE) model. See [U] 11.1.6 weight. Weights must be constant within panel

Best,

Marcos

[FernandoRios]

Hi Meggy,
The other option you have is to use an alternative to panel estimation, like areg, (different assumptions on the panel component), which allows for weights that change within the panel variable.
Best,
Fernando