OLS Regression - Problem with the independent variables

[Leo Dromi]

Hey guys,

im working on a linear regression and have some problems with that. I appreciate every comment on my topic and thank you guys in advance for your help!

So i would like to run a linear regression and i have around 100 independent variables. Around 80 of them are control variables and when i want to run the regression i receive the no observations
r(2000) return code. At first i thought this might be the case because of missing values or strings in my variables. But both is not the case. When i split the whole regress command into 50 independent variables and another 50 variables my regression is working. So for example if i run regress dependent var independent 1 - 50 it is working but if i compute it for the whole set i get the r(2000). So its not working for all the independent variables when im trying to run it as a complete formula.
Do you have any suggestions why this is the case and how to overcome this problem?

Thanks
Leo

[Jeff Thompson]

Someone is going to tell you to post your regression code first before they help you.

[Eric de Souza]

A hundred independent variables ?! Besides the questions of interpretation, multicollinearity and so on, how many degrees of freedom are left over. That could be the reason for the error message because it works, at least mechanically, with 50 variables. At least reproduce the top of the regression output with 50 variables (before the listing of the individual coefficients begins).

[Leo Dromi]

Hello,

ok thank you. You are totally right. The number of independent variables is ways too high. I have a high number of collinearity problems in my regression now.

[Carlo Lazzaro]

Leo:
as always, the best approach is trying to give a fair and true view of the data generating process (which, in all likelihhod, is not the case with 100 predictors). I would recommend you to skim through the literature of your research field and see what Others did in the past when presented with the same research topic: re-inventing the wheel often means just wasting your time.