Re: st: Curious behavior of fracpoly with Stata 11

[Steven Samuels <sjsamuels@gmail.com>]

I see something similar, except that the first version completes and gives the same results as the 10.1 version.

*********************
timer  on 1
fracpoly: logistic foreign mpg, adjust(no) degree(4)
timer off 1

sysuse auto, clear
version 10.1
 timer on 2
fracpoly: logistic foreign mpg, adjust(no) degree(4)
timer off 2
timer list
***********************

yields:

 timer list
   1:    223.83 /        2 =     111.9145
   2:      1.04 /        1 =       1.0410



Steve
sjsamuels@gmail.com


On May 31, 2011, at 5:27 PM, Jean Bouyer wrote:

Hi,

I observe a curious behavior of frapoly with Stata 11 :

when I use the command    fracpoly logistic Y X, adjust(no) degree(4) where Y is a 0/1 variable 
the dot-line begins indicating the progression of the computation, then stops and the program seems to be blocked

On the contrary, with the commands
version 10.1
fracpoly logistic Y X, adjust(no) degree(4)
the computation begins seems much more quick at the beginning and, what is more important, provides a result.

Is there an explanation ?

Thanks

Jean
*
*   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/