Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

Re: st: AW: Poisson regression with survey data - goodness of fit -


From   Paolina Medina <carmencitamedina@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: AW: Poisson regression with survey data - goodness of fit -
Date   Mon, 14 Jun 2010 09:02:37 -0500

Thank you very much again...

On Sun, Jun 13, 2010 at 4:29 PM, Steve Samuels <sjsamuels@gmail.com> wrote:
> There are references in the Manual to -linktest-, introduced by Darryl
> Pregibon.  See also:
> http://www.ats.ucla.edu/stat/stata/webbooks/logistic/chapter3/statalog3.htm.
>  -ovtest- after -regress-  is  similar in idea.  Type: "help regress
> postestimation"
>
> -linktest- will work if some of the variables are dummies.
>
>  A correction: at least as of Version 11, possibly earlier, you don't
> have to compute the linktest variables by hand after a survey
> estimation command. Just run -linktest- after svy: poisson--.
>
> Zero-inflated Poisson, run with  -svy: zip-, is another model which
> generalizes the Poisson assumption.  However the -vuong-- option is
> not allowed after -svy: zip-, but you can use a -test- statement to
> check on the joint significance of the variables in the  inflate
> equation.
>
> Steve
>
> On Sun, Jun 13, 2010 at 4:59 PM, Paolina Medina
> <carmencitamedina@gmail.com> wrote:
>> Thank you verymuch Steve and Martin.
>>
>> Steve, I do have come continuous covariates but some of them are dummy
>> variables.
>> Would this work anyway? And just one more question, do you know where
>> can i find more info about this linktest that you are recommending me?
>>
>> Thank you very much...
>>
>> Paolina
>>
>> On Sun, Jun 13, 2010 at 3:26 PM, Steve Samuels <sjsamuels@gmail.com> wrote:
>>>
>>> The -linktest-- works best if you have some continuous covariates. You
>>> can run the -linktest-  for -svy: poisson-- as follows:
>>> **************************
>>> sysuse auto, clear
>>> svyset _n
>>> svy: poisson rep78 mpg weight length
>>> predict xb
>>> gen xb2 = xb^2
>>> svy: poisson rep78 xb xb2
>>> *******************************
>>>
>>> Steve
>>>
>>>
>>> Steven Samuels
>>> sjsamuels@gmail.com
>>> 18 Cantine's Island
>>> Saugerties NY 12477
>>> USA
>>> Voice: 845-246-0774
>>> Fax:    206-202-4783
>>>
>>> On Sun, Jun 13, 2010 at 3:11 PM, Martin Weiss <martin.weiss1@gmx.de> wrote:
>>>>
>>>>
>>>> Try http://www.stata.com/meeting/dcconf09/dc09_valliant.pdf>
>>>> HTH
>>>
>>>> Martin
>>>
>>> Von: owner-statalist@hsphsun2.harvard.edu
>>> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Paolina Medina
>>>>
>>>> Hi everybody,
>>>>
>>>> I am running a poisson regression using survey data,
>>>> Does anyone know about any measure of goodness of fit that i could use?
>>>> estat gof does not work.
>>>> Thank you very much in advance.
>>>>
>>>> Regards,
>>>>
>>>> Paolina
>>>> *
>>>
>>> --
>>>
>>> *
>>> *   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/
>>>
>>
>>
>>
>> --
>> Paolina Medina Palma
>>
>> *
>> *   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/
>>
>
>
>
> --
> Steven Samuels
> sjsamuels@gmail.com
> 18 Cantine's Island
> Saugerties NY 12477
> USA
> Voice: 845-246-0774
> Fax:    206-202-4783
>
> *
> *   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/
>



-- 
Paolina Medina Palma

*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index