Re: st: Agreement statistic, gold standard not binary

[Jeph Herrin <junk@spandrel.net>]

Not quite sure what you are aiming for, but try -kappa-

Marcus Fischer wrote:
> How can I estimate  and compare two diagnostic tests� accuracies with
> a gold standard when the diagnostic test scales and the scale of the
> gold standard are ordinal variables (each 0 to 3) ?
> Thanks
> *
> *   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/