[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
"Daniel Schneider" <[email protected]> |

To |
<[email protected]> |

Subject |
RE: st: Interaction terms in a logit model |

Date |
Sat, 19 Mar 2005 09:36:40 -0800 |

```
Thanks Maarten,
But, is that really different from doing
When drep==0
prgen price, x(drep=0 drepXprice=0) f(3290) t(16000)
And a loop for all values of price using
prvalue, x(drep=1 price=$value drepXprice=$value)
When drep==1
And then using both results to generate the graph (sorry, my stata
programming skills are pretty non-existent, the previous lines is meant
as a a general statement not Stata code)?
Or, more specifically: is this enough to take into consideration the
issues raised by Norton, Wang, Ai?
Daniel
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of maartenbuis
> Sent: Saturday, March 19, 2005 1:40 AM
> To: [email protected]
> Subject: Re: st: Interaction terms in a logit model
>
>
> --- "Daniel Schneider" <daniel.schneider@s...> wrote:
> > My problem is that I would like to just do a -predict- command,
> > generate some simple graphs that show the different behavior of the
> > predicted probability depending on the manipulation of the two
> > variables (e.g., if X2 is a binary dummy, I would get two lines
> > running from left to right, when the yaxis is my predicted
> probability
> > and the xaxis is every value that X1 can take).
>
> One way to do just that is to do it manually like in the code
> below. The predicted probability whithin a logistic regression is
> exp(xb)/(1+exp(xb)) In the example xb is _b[_cons]+_b[price]
> if drep==0 and _b[_cons]+_b[price]+_b[drep]+_b[drepXprice]*x
> if drep==1.
>
> clear
> sysuse auto
> gen drep = rep78>=4
> gen drepXprice = drep*price
> logit foreign price drep drepXprice
> sum price
> twoway function y = exp(_b[_cons]+_b[price]*x)/ /*
> */ (1+exp(_b[_cons]+_b[price]*x)), range(3290 16000) || /*
> */ function y = exp(_b[_cons]+_b[price]*x + _b[drep] + /*
> */ _b[drepXprice]*x) / /*
> */ (1+exp(_b[_cons]+_b[price]*x + _b[drep] + /*
> */_b[drepXprice]*x)), range(3290 16000) /*
> */ ytitle("Pr(foreign)") xtitle("price in $") /*
> */legend(label(1 "drep=0") label(2 "drep=1"))
>
> Hope this helps,
> Maarten
>
>
>
>
>
>
> *
> * 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/
>
*
* 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/
```

**References**:**Re: st: Interaction terms in a logit model***From:*"maartenbuis" <[email protected]>

- Prev by Date:
**RE: st: compare zip and nbreg model** - Next by Date:
**Re: st: Interaction terms in a logit model** - Previous by thread:
**Re: st: Interaction terms in a logit model** - Next by thread:
**Re: st: Interaction terms in a logit model** - Index(es):

© Copyright 1996–2024 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |