0
$\begingroup$

I have a regression where both my Y and X variables are measured in percent (so they are decimals values, mostly less than 0). The coefficient from the regression is 0.43. Is it correct to say that a 1 increase in X increases Y by 0.43, so when X increases by 100%, Y increases by 43%?

$\endgroup$
  • $\begingroup$ You mentioned 'mostly less than 0', meaning they are measuring percentage changes, right? $\endgroup$ – dlnB Mar 16 at 2:17
  • $\begingroup$ the dependent variable is abnormal returns (stocks) and the independent variable is earnings surprise, so I think neither are the percentage changes you may be thinking of $\endgroup$ – turtle101 Mar 16 at 2:43
  • $\begingroup$ Standardized abnormal returns and standardized unexpected earnings? Following the wikipedia formulas? $\endgroup$ – dlnB Mar 16 at 2:48
  • $\begingroup$ Neither are standardized, the values are calculated from financial data $\endgroup$ – turtle101 Mar 16 at 3:29
1
$\begingroup$

Is it correct to say that a 1 increase in X increases Y by 0.43, so when X increases by 100%, Y increases by 43%?

Yes, if you have a linear model, y = x*coef + intercept.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.