-------------------------------------------------------------------------------
help for kapprevi
-------------------------------------------------------------------------------

Dependence of kappa statistic on true prevalence

    kapprevi , r1(#sens #spec) r2(#sens #spec) [ nograph
              scatter_options ]

Description

    kapprevi provides a graphical representation of the kappa
          statistic as a function of the true prevalence of the
          characteristic in the population, given specified values of
          sensitivity and specificity for two raters.  It is an
          immediate command, see help immed.
 
Options

    r1(#sens #spec) specifies the sensitivity and specificity of rater 1.
        These numbers have to range between 0 and 1.

    r2(#sens #spec) specifies the sensitivity and specificity of rater 2.
        These numbers have to range between 0 and 1.

    nograph suppresses graphical output.

    scatter_options are any of the scatter options.

Examples

     . kapprevi, r1(0.90 0.95) r2(0.70 .99)
     . kapprevi, r1(0.90 0.95) r2(0.90 .95)
     . kapprevi, r1(0.70 0.90) r2(0.70 .90) ysize(4)  xsize(4)
     . kapprevi, r1(0.70 0.90) r2(0.70 .90) title(Dependence of kappa on preval
> ence)
     . kapprevi, r1(0.90 0.95) r2(0.70 .99) ysize(4) xsize(4) scheme(vg_blue)

Authors

    Nicola Orsini, Division of Nutritional Epidemiology, IMM, Karolinska
    Institutet, Sweden
    Debora Rizzuto, Division of Geriatric Epidemiology, Department of
    Neurotec, Karolinska Institutet, Sweden

Reference

    Thompson W.D and Walter S.D. A reappraisal of the kappa coefficient, J
    Clin Epidemiol, 1988, Vol.41, n.10, pp.949-959
 
Support

    http://nicolaorsini.altervista.org
    nicola.orsini@ki.se

Also see

On-line:  help for kappa