Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# RE: Antwort: st: Fwd: exponential regression in stata

 From Nick Cox <[email protected]> To "'[email protected]'" <[email protected]> Subject RE: Antwort: st: Fwd: exponential regression in stata Date Wed, 19 Jan 2011 17:08:14 +0000

```Absolutely not so.

1. I've already pointed out that these (Justina's and mine) proposals are exactly the same.

2. There is no objection in principle to using the functional form exp(a + bx) with x sometimes negative. You can see this for yourself in Stata, e.g. by

. twoway function exp(1 + 2*x) , ra(-2 2) || function exp(1 - 2*x), ra(2 -2)

Whether it is a good choice for your data is a different question.

I suggest a crash (revision) course in exponential and logarithmic functions!

Nick
[email protected]

Bastian Steingros

hi Justian, the point is, that some of my x var's are negative, so ln would not work. nick cox suggest to consider transforming the y var's only...

Justina Fischer <[email protected]>

> You might consider transforming your model prior to estimating, e.g. taking
> the  log (ln) on both sides.

> Von: "Bastian Steingros" <[email protected]>

> I want to run a exp. regression in stata. But I have not found any
> instructions in the help options. do you have any ideas what to enter in
> stata to obtain such a regression model?
>
> I mean by exp. function something like : y=0,343 * e^(22,33*x)
>
> [my data set has 1 dep. var. and 3 indep. var.'s --> is such a model also
> possible for 3 x-var's?]

*
*   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/
```