.-
help for ^exactcc^, ^exactcci^                                      [STB-52: sbe31]
.-

Case-control studies
--------------------

    ^exactcc^ case_var ex_var [weight] [^if^ exp] [^in^ range] [^, l^evel^(^#^) e^xact ^tb^ 
        ^w^oolf ^by(^varname^) no^crude ^bd^ ^p^ool ^noh^om ^es^tandard ^is^tandard 
        ^s^tandard^(^varname^) b^inomial^(^varname^)^ ]

    ^exactcci^ #a #b #c #d [^, l^evel^(^#^) e^xact ^tb w^oolf ]


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

These commands are identical to @cc@ and @cci@ except that additional output is
provided.  The default output includes Cornfield's confidence interval for 
the odds ratio calculated both with and without a continuity correction.
These intervals are labeled "adjusted" and "unadjusted", respectively.
We also provide Yates' continuity corrected chi-squared test of the null 
hypothesis that the odds ratio equals 1.  When the ^exact^ option is given
the exact confidence interval for the odds ratio is also derived, as well
as twice the 1-sided Fisher's exact P value.  Analogous confidence intervals
for the attributable or preventive fractions are also provided.


Authors
-------

    William D. Dupont 
    Vanderbilt University 
    bill.dupont@@vanderbilt.edu

    Dale Plummer 
    Vanderbilt University, 
    dale.plummer@@mcmail.vanderbilt.edu


Also see
--------

Manual:  ^[R] epitab^
On-line:  help for @cc@ and @cci@
STB:      Dupont and Plummer.  Exact confidence intervals for odds ratios from 
          case-control studies.  Submitted for publication