Regression

[scyazombre]

hello guys!!

i'm new here, I just want to ask if it is okay to do regression where the dependent variable's measurement is in million pesos, then its independent variables are unemployment rate, inflation rate, interest rate and remittances. . . thank you for any reply!!! :D

[SnakeCharmerII]

Yes, it is 100% right.

Maybe you’re going to have kind of large estimated parameters, let’s say Y in millions of pesos and a Beta-hat for unemployment equal to -20. So a 1% increase in unemployment, decreases Y by 20 millons of pesos.

I would suggest also to use a semi logarithmic regression, were Y is in (natural) logarithms. This way your beta-hat for unemployment is going to be e.g. -0.015 or something like that, so a 1% increase in unemployment is going to decrease Y by 1.15%, etc.

This is an unbelievable simple issue, isn’t it? Maybe their simplicity is the reason why so many people saw the thread but none actually answered (Maybe that’s why NONE NEVER answers my posts ;-D!)

[scyazombre]

Thank you very for your answer!!! I didn't really expect that someone would response to my question. . . :D your so kind, Thank you again.