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: nbreg or ologit?


From   Joerg Luedicke <joerg.luedicke@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: nbreg or ologit?
Date   Tue, 19 Jun 2012 16:32:27 -0500

On Tue, Jun 19, 2012 at 12:23 PM, Shittu, Aminu <ameen_vet@yahoo.com> wrote:
> In a count data from individual animals (20 samples collected from each of the 23 farms and production questionnaire administered); should the count data be modelled using "nbreg" or the count response be converted to an ordinal variable as low, medium and high egg counts and modelled using "ologit?"

No. (Whether -nbreg- is the right thing cannot be said based on the
information you provide. But reducing a count variable to a
categorical one makes no sense whatsoever.)


> Could both be interpreted similarly?
With a wide definition of "similar", regression coefficients from all
kinds of models can be interpreted similarly.


> Furthermore, is it ok including farm as random effect as animals are clustered within farms?
I assume you mean varying intercepts across farms. Sure, why not? You
could perhaps include varying coefficients as well, if it seems
reasonable.


J.



>
> Regards,
>
> Aminu.
>
> *
> *   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/

*
*   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