Endogenity and multicollinearity in balanced panel data

[Mirna Faltas]

Hello all,

I need to ask two questions to all #Econometric and #STATA experts: First: If I have a balanced panel data set and I applied FGLS model, Do I need to check for multi-co linearity and if yes how can I do this using STATA? Second : In the same model , do I have to check for endogenity and if yes , how could I do this on STATA? I appreciate your kind help and response
please note that I have a small data set of four countries and n= 30.

[Phil Bromiley]

First, you'll increase your chances of a helpful answer by following the FAQ on asking questions - provide Stata code in code deimiters, Stata output, and sample data using dataex. Also, try to reduce the code you include to what is needed to demonstrate your problem. You should also have searched for the major terms in your question from the command window of Stata (findit majorterm) and in the subject index in the documentation (under index at the bottom of the list of documentation).

You haven't told us what FGLS estimator you used, or even what your problem looks like. You should look at the colinearity discussion in Greenberger's text. Colinearity below the not identified level does not change the properties of your estimates. How you test for endogeneity again would depend on your original estimator. Also, almost all Stata procedures work just fine with unbalanced panels.

However, with four countries and only 30 observations, the benefits of different estimators is unclear - almost all of the advanced estimators only have asymptotic properties. Indeed, even entering just the panel fixed effects will eat up a lot of your degrees of freedom.