Dear all
I have a question regarding scaling the dependant variable (or independant variables) in a regression. In my estimation the dependant variable is volatility of commodities, and explanatory variables are some macroeconomic factors like business cycles, inflation and etc...
As the value of volatility is very small in compare to the explanatory variables the regression estimation results generate very small coefficients and standard errors (zero) for all of the explanatory variables, while they are mostly statistically significant.
If I re-scale the dependant variable (volatility) by multiplyig it to for instanse 1000000, the amount of the coefficients increases, my question is that then how I have to interprete these results (for instance as the elasticiy) because the amount of the coefficients are not real.
Thank you in advance
Scaling data
Moderators: EViews Gareth, EViews Moderator
Return to “Econometric Discussions”
Who is online
Users browsing this forum: No registered users and 46 guests