st: Re: xttobit error "number of quadrature points must be less than or equal to number of obs"

[John Simpson <john.simpson@ualberta.ca>]

Hello Stata Experts,

Clearing and reloading wouldn't work.  Shutting down STATA and  
restarting wouldn't work. I eventually solved the error by running the  
do-file that built the dataset again.

Strange.

-John

John Simpson
Department of Philosophy
University of Alberta


On 13-Jul-09, at 7:40 PM, John Simpson wrote:

> Hello Stata Experts,
>
> I am receiving a strange error when trying to run xttobit on a large  
> set of panel data.  Basically, when I enter:
>
> xttobit agentsend generation genSQ genCU initial roundante spawncost  
> spawndisc playdisc randomizelike randomizeafterplay treatment  
> agentsendLag1 agentsendLag2 agentsendLag3 agentsendLag4  
> agentsendLag5, ll(1) ul(15000)
>
> it spits back:
>
> number of quadrature points must be less than or equal to number of  
> obs
>
> I'm thinking that something odd is going on because I have over 10  
> million observations as is shown by describe:
>
> . describe
>
> Contains data from /Users/jsimpson/Documents/workspace/SR6-COMBINED- 
> dropALL-TOBIT.dta
>  obs:    10,471,680
> vars:            25                          13 Jul 2009 19:27
> size:   806,319,360 (56.1% of memory free)
> --------------------------------------------------------------------------------------------------------
>              storage  display     value
> variable name   type   format      label      variable label
> --------------------------------------------------------------------------------------------------------
> trialline       byte   %8.0g                  TrialLine#
> population      byte   %8.0g                  Population#
> environment     byte   %8.0g                  Environment#
> roundante       int    %8.0g                  Round-Ante
> spawncost       int    %8.0g                  Spawn Cost
> spawndisc       byte   %8.0g                  Spawn Disc?
> playdisc        byte   %8.0g                  Play Disc?
> randomizelike   byte   %8.0g                  Randomize Like?
> randomizeafte~y byte   %8.0g                  Randomize AfterPlay?
> initial         int    %8.0g                  Initial-#
> generation      byte   %8.0g                  Generation
> agentsend       int    %8.0g                  #Agents-End
> xPO             double %10.0g
> xAPO            double %10.0g
> xM              double %10.0g
> xAM             double %10.0g
> panelid         double %12.0g
> treatment       byte   %9.0g
> agentsendLag1   int    %9.0g
> agentsendLag2   int    %9.0g
> agentsendLag3   int    %9.0g
> agentsendLag4   int    %9.0g
> agentsendLag5   int    %9.0g
> genSQ           int    %9.0g
> genCU           float  %9.0g
> --------------------------------------------------------------------------------------------------------
> Sorted by:  panelid  generation
>
> Any thoughts?
>
> -John
>
> John Simpson
> Department of Philosophy
> University of Alberta

*
*   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/