I mean
Badi Baltagi wrote 2002 in "Econometrics" Page 84: In the
multivariate analyses,the variable wage per hour are a log function.
With these semi-log regression, the coefficient can in an exponential
equation [exp(b)-1] interpret the covariate over the dependent
variable as an percental effect.
In german: " In den multivariaten Analysen geht der Stundenlohn in
logarithmierter Form ein. Bei einer solchen semi-logarithmischen
Regression kann der exponentierte Koeffizient [exp(b)-1] als
prozentualer Effekt der Kovariaten auf die abhängige Variable
interpretiert werden" Pollman-Schult "Veränderung der
Einkommensverteilung infolge von Höherqualifikation" Seite 164.
Hopefully i could explained it now, Boris
2008/10/29, Martin Weiss <[email protected]>:
> The question is unclear: With a response in log and covariates in levels,
> you interpret the coefficients as semi-elasticities, see, for instance,
> Baum(2006) (http://www.stata-press.com/books/imeus.html), chap. 4.3.4. Now
> where do you want to take it from here?
>
>
> HTH
> Martin
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of bumbuminc
> Sent: Wednesday, October 29, 2008 10:34 AM
> To: [email protected]
> Subject: st: Mincer wage function as a log function - how can stata
> calculate the percent values
>
> Hi, i have here the standard Mincer wage function as a log function:
>
> Log(W) = b + cX ^2 + dX + eX + fX
>
> Now if i want the Values of the coefficients in percent i have to
> calculate by hand every value with:
>
> 100 * (exp^b - 1)
>
> Is there a way that stata can do this after the regress command?
>
> Thanks Boris
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/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/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/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
