Thanks to Kit, the package kaputil has been updated on SSC.
The changes are:
* kapci is renamed kappci (to avoid conflict with a new program of the same name in Stata J)
* a bug in the lower confidence bound from kappci has been corrected (with thanks to Jose Maria Pacheco de Souza) - please note, the same bug remains in the older package kapgof on SSC.
The package calculates confidence intervals for the kappa statistic of inter-rater agreement for a binary outcome and 2 raters (kappci) using a goodness-of-fit approach (note that this will have better properties than the analytic or bootstrap approaches of the Stata J kapci program in small samples) and for 3 or more raters (kappci/kappaci) using an inverted modified Wald test approach. It also performs sample size calculations for the same situations (kapssi).
ssc describe kaputil
David
[email protected]
*
* 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/
