Re: st: regression explanation

[Ron�n Conroy <rconroy@rcsi.ie>]

On 12 Ean 2007, at 12:14, Michelle Liu wrote:

> wage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
> ------------- 
> +----------------------------------------------------------------
>        educ |   .3498179   .0578807     6.04   0.000     . 
> 2361024    .4635334
>       exper |   .1606065   .0377335     4.26   0.000     . 
> 0864732    .2347398
>
>
> "Holding other variables fixed, ceteris paribus, another year on  
> education is associated with 0.3498 of average hourly earnings"
It depends on the currency in which wages are measured.

In this particular model, in two people have the same experience each  
additional year of education predicts a 0.34 euro difference in  
hourly earnings. Insert your own currency here.

> i am not very sure about the 0.35 of average hourly earnings, if  
> there is a better way to explain the 0.3498! thank you very much.
You are thinking of it as a ratio. In fact, it is expressed in the  
metric of your predicted variable.

And congratulations: you are the first person who has used the phrase  
'ceribus paribus' - or indeed any Latin ablative absolute  
construction - on Statalist this century. Or maybe ever.

Major Kudos.

=========
Ron�n Conroy
Royal College of Surgeons in Ireland
rconroy@rcsi.ie
+353 (0) 1 402 2431
+353 (0) 87 799 97 95
http://www.flickr.com/photos/ronanconroy




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/