st: RE: xtregar postestimate - mfx, eyex command

["Jacobs, David" <jacobs.184@sociology.osu.edu>]

I don't understand because the coefficient when both the dependent and an explanatory variable are logged is equal to the elasticity.  

In any case and assuming that you have a Stata version more recent than version 10, the -mfx- command used to calculate elasticities is now out of date.  Try something like -margins, eyex(explanatory variable list separated by spaces or _cont [if you want elasticities for all continuous explanatory variables in your model])-. 

The interpretation of an elasticity is that for every one percent increase in the explanatory variable, the dependent variable changes by the percent indicated by the coefficient on that explanatory variable.

Check out any econometrics text.

Dave Jacobs

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Alice Nader
Sent: Friday, September 20, 2013 9:13 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: xtregar postestimate - mfx, eyex command

Dear Stata staff members, 

I have an unbalances panel dataset and both my independent and dependent variables were transformed using logarithmic functions to normalize them for xtregar command. 


I would like to calculate the elasticity/marginal effect from this autoregression panel model and I was wondering if the adequate command would be "mfx, eyex". Another inquiry that remains is how would I interpret the output of "mfx, eyex"? Would it be that for every 1 unit increase in x, y increases z? 

Thank you in advance for all your help and assistance. 

Kind regards, 
Alice  


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/