Constantine Daskalakis wrote:
>
> I am using Stata 7 (using the executable last update, 6/11/02) on a PC.
> For -xtlogit, re- the manual says (p.380) that the value of rho is computed as
>
> rho = sigma2_u / [sigma2_u + 1]
>
> The numbers in the union example given in that page confirm that....
> the rho computed manually (0.70) does not agree with the value shown
> in the output (0.41). I'm stumped!
Computation of rho in the clustered logistic model was corrected
after an error was discovered by German Rodriguez. The new formula
is provided in: The Stata Journal, Volume 3, No. 1, pages 32-46.
I hear that the correct formula is also shown in the V 8 manual,
although I haven't observed this first-hand.
So your updated executable is computing rho as per the corrected
formula, not the one shown in the V 7 manual. The offending piece
is the 1 in the denominator.
- JK
--
Jay S. Kaufman, Ph.D
-----------------------------
email: [email protected]
-----------------------------
Department of Epidemiology
UNC School of Public Health
2104C McGavran-Greenberg Hall
Pittsboro Road, CB#7435
Chapel Hill, NC 27599-7435
phone: 919-966-7435
fax: 919-966-2089
-----------------------------
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
