.-
help for ^diagtest^
.-

Report summary statistics for diagnostic tests
----------------------------------------------

        ^diagtest^ testvar diagvar [weight ^if^ exp ^in^ range][, ^prev(^#^)^
                                  ^level(^#^)^ table_options]


Description 
-----------

^diagtest^ displays various summary statistics for diagnostic tests; 
sensitivity, specificity, and predictive values, from a 2x2 table.

^testvar^ is the variable which identifies the result of the diagnostic test,
and ^diagvar^ is the variable which contains the real status of the patient.
Note that the lower category must identify the non-exposed, the negative 
result of the test, or the false status of the patient.


Options
-------

^prev(^#^)^ request the estimated prevalence, in percentage, of the exposure 
to provide the positive and negative predicted values based on the Bayes' 
theorem. Default is the estimated prevalence thorough the data.

                       (Sensibility x Prevalence)
  PPV = -------------------------------------------------------------
         (Sensibility x Prevalence) + (1-Specificity x 1-Prevalence)


                       (Specificity x 1-Prevalence)
  PPN = -------------------------------------------------------------
         (1-Sensibility x Prevalence) + (Specificity x 1-Prevalence)


^level(^#^)^ specifies the confidence level, in percent, for calculation of
confidence intervals of the sensitivity, specificity, predictive values,
and prevalence. Default is the 95%. Note that if the ^prev^ option is used
the confidence interval is only displayed for the sensitivity and specificity
values.


Author
------

        Aurelio Tobias
        Medical Statistician
        Getafe (Spain)
        e-mail: bledatobias@@ctv.es


Examples
--------

        . ^diagtest test truediag^
        . ^diagtest test truediag, prev(25)^
        . ^diagtest test truediag, prev(50) chi^
        . ^diagtest test truediag, all^


Also see
--------

 Manual:  ^[R] tabulate, [R] lstat, [R] lsens, [R] lroc^
On-line:  help for @tabulate@, @lstat@, @lsens@, @lroc@