st: a bug in the new command kapci?

[Jose Maria Pacheco de Souza <jmpsouza@usp.br>]

Dear David and Statalisters:

The new commands of confidence interval for kappa is welcome.
But it seems to have a bug. I compared the results on page 1519 of the 
article (kappa=.81, ci= .67-.92, and ci= .70-.92) executing the commands

. kap  var1 var2

             Expected
Agreement   Agreement     Kappa   Std. Err.         Z      Prob>Z
-----------------------------------------------------------------
  90.68%      51.29%     0.8086     0.0920       8.79      0.0000

. kapci  var1 var2

 Expected    Observed   -- Binomial Exact --
Agreement   Agreement   [95% Conf. Interval]
--------------------------------------------
   51.29%      90.68%      83.93%     95.25%

  Kappa  [95% Conf. Interval]        Z     Prob>Z
-------------------------------------------------
 0.8086     0.3400     0.8914     8.79     0.0000

Clearly the result 0.3400 for the lower limit is not correct.

In the ado file for kapci it is missing -(1/3)*`y2' in the equation for 
-lb-; adding it, I got the  correct result:

kapci  var1 var2

 Expected    Observed   -- Binomial Exact --
Agreement   Agreement   [95% Conf. Interval]
--------------------------------------------
   51.29%      90.68%      83.93%     95.25%

  Kappa  [95% Conf. Interval]        Z     Prob>Z
-------------------------------------------------
 0.8086     0.6735     0.8914     8.79     0.0000

I did not checked the .ado for kappaci.
Greetings,
Jose Maria


--
Jose Maria Pacheco de Souza, Professor Titular
Departamento de Epidemiologia/Faculdade de Saude Publica, USP
Av. Dr. Arnaldo, 715
01246-904  -  S. Paulo/SP - Brasil
fones (11)3082-3886; (11)3066-7724; (11)3768-8612; (11)3714-2403
fax (11)3082-2920; (11)3714-2403
www.fsp.usp.br/~jmpsouza
*
*   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/