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: qbeta and covariates?
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: qbeta and covariates?
Date
Thu, 24 Mar 2011 18:18:08 +0000
A more positive piece of trickery is to see if you can make progress by feeding
your response y and y2 = 1 - y as responses to -dirifit- (SSC).
-dirifit- does have more support for -predict-. I have not thought
this route through, but it may give you a way to approach the problem.
Nick
On Thu, Mar 24, 2011 at 5:54 PM, Nick Cox <[email protected]> wrote:
> -betafit- and -qbeta- are from SSC. Please remember to specify where
> user-written programs you refer to come from.
>
> Sorry, but there is no syntax for specifying covariates with -qbeta-.
> I don't know what kind of plot you would expect, but -qbeta- is
> focused on single-variable distributions.
>
> A good analogue is the official command -qnorm- which does not support
> covariates either.
>
> -betafit- supports a variety of standard tests and confidence intervals.
>
> Nick
>
> On Thu, Mar 24, 2011 at 5:43 PM, David Pacheco <[email protected]> wrote:
>
>> I’m using betafit with covariates for alfha and beta, but…How I can
>> use this same setting in qbeta?.... because I need to test the
>> goodness-of-fit. I’ve tried to put the covariates in the qbeta syntax,
>> but it has not worked.
>
*
* 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/