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: RE: ZINB - how do you use lagged variables?
From
Jorge Eduardo Pérez Pérez <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: RE: ZINB - how do you use lagged variables?
Date
Mon, 25 Apr 2011 17:55:18 -0400
As a suggestion, if you are using only lagged independent variables,
including them in a -zinb- model poses no problem. However, if you
want to include lags of your integer dependent variable, using -zinb-
is ill-advised as it does not model the time series correlation of the
dependent variable properly. Autorregresive conditional poisson models
or integer autorregresive models are more suitable for time series
count data.
_______________________
Jorge Eduardo Pérez Pérez
On Mon, Apr 25, 2011 at 5:43 PM, Nick Cox <[email protected]> wrote:
> As -zinb- is objecting to the use of operators such as L. in the call, why not create those variables explicitly with -generate- beforehand? You can that manual, but you could probably do it in a loop.
>
> But don't expect -zinb- to have any special knowledge of time series.
>
> Nick
> [email protected]
>
> Jung-eun Lee
>
> Stata won't allow lagged right-hand-side variables(time-series operators, which the -nbreg- command does allow) when I use the -zinb- command. Is there a way to solve this problem?
> Or do I have to manually lag all the explanatory variables?
>
> *
> * 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/