Bookmark and Share

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


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: beta regression


From   Nick Cox <[email protected]>
To   "'[email protected]'" <[email protected]>
Subject   RE: st: beta regression
Date   Wed, 26 Oct 2011 15:16:03 +0100

It is. The point is explaining where user-written programs you use come from. 

Nick 
[email protected] 

Jet

Sorry for not being clearer. Had thought zoib is under the category of
beta regression.

On Wed, Oct 26, 2011 at 9:30 AM, Nick Cox <[email protected]> wrote:

> The first is a user-written command (-zoib-, SSC). I imagine Maarten will respond if he forgives your not giving him proper credit!
>
> Nick
> [email protected]
>
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Jet
> Sent: 26 October 2011 14:17
> To: [email protected]
> Subject: Re: st: beta regression
>
> Thanks to Cam and Nick. Below are the two sets of commands:
>
>  zoib DV predictors, ///
>  zeroinflate (predictors)
>
> Question: For the 0<DV<1 model (first line), do we need to
> exponentiate the estimated coefficients, and interpret the exp(B) as
> changes in odds ratio (of having what value?) or as changes in the
> outcome measured as proportion/ratio?
>
> **postestimation.
> *proportion conditional on 0 < DV < 1
> margins, predict(prcond) at(______)
>
> Question: For the estimated value in the margins in the
> post-estimation function [predict(prcond)], do we interpret the ouptut
> as the predicted proportion or probability?
>

*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index