# st: R: linear regression question

 From "Carlo Lazzaro" To Subject st: R: linear regression question Date Sun, 15 Mar 2009 09:17:50 +0100

```Dear Galina,
your thread seems to refer to a log-linear model, where only the dependent
variable (i.e., Y) is log-transformed.

In a log-linear model, a unit-change in the independent variable X (i.e.,
DeltaX=1)is associated with a 100*Beta% change in Y.

For instance, a coefficient = 0.2 in your log-linear model means that the
dependent variable Y increases by [(0.2*100)%]=20% for each additional unit
of X.

You can find a lot more on this topic (and other related issues) in an
introductory econometric textbook (please, find some references below):

Koop G. Introduction to Econometrics. Wiley, 2007.
Stock JH, Watson MW. Introduction to Econometrics. Second Edition.Pearson
International Edition, 2007.
For Stata Users, the reference textbook is:
Baum K. An Introduction to Modern Econometrics Using Stata.
http://www.stata-press.com/books/imeus.html.

HTH and Kind Regards,
Carlo
-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di Galina Hayes
Inviato: domenica 15 marzo 2009 2.52
A: statalist
Oggetto: st: linear regression question

Hello everyone,
In a linear regression model, if I have had to perform a natural log
transformation of outcome to meet the homoscedasticity assumption, can
someone tell me how to interpret the coefficents? Do I simply exponentiate
them?
Thanks, Galina
*
*   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/
```