No, there are no 0 or negative values. There are some missing values
in the y variable, but these are missing in both y and ln(y). The
data is like this:
x y
1 5
2 .
3 .
4 7
So ln(y) does have missings, but those are also missing in y. I still
don't see, then, how mfx, eyex gives me a value different than the
coefficient on lnx in regress lny lnx. Thanks again for all your
thoughts.
On Tue, Sep 8, 2009 at 10:20 AM, Maarten buis<[email protected]> wrote:
> --- On Tue, 8/9/09, Dorothy Bridges wrote:
>> But what I don't understand is: the second method
>> (using mfx, eyex) gives me a different value than
>> the first method (storing the coefficient on x
>> from *regress lny lnx*). Why?
>
> Does x or y contain values that are 0 or less? In
> that case you are creating missing values by
> creating lnx and/or lny.
>
> -- Maarten
>
> --------------------------
> Maarten L. Buis
> Institut fuer Soziologie
> Universitaet Tuebingen
> Wilhelmstrasse 36
> 72074 Tuebingen
> Germany
>
> http://www.maartenbuis.nl
> --------------------------
>
>
>
>
> *
> * 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/
