.-
help for ^prdc^ - 25Oct2005
.-

?? if, in, all and ystar options need to be verified.

Compute descrete change of a specified amount for list of variables.
--------------------------------------------------------------------

    ^prdc^ [varlist] [^if^ exp] [^in^ range] [, ^x(^variables_and_values^)^
        ^r^est^(^stat^)^ ^ys^tar ^b^rief ^all ^max^cnt ^(^#^)^ ^noba^se
        ^nola^bel ^f^rom^(^#^)^ ^to(^#^)^ ^c^hange^(^#^)^ ^bin^ary
        ^u^nit ^sd^ ^unc^entered <you can also use options for confidence
        intervals used with ^prvalue^.]
where

    ^varlist^ contains the names of variables for which discrete change will
        be computed.

    ^variables_and_values^ is an alternating list of variables and either
        numeric values or mean, median, min, max, upper, lower, previous

    ^stat^ is either mean, median, min, max, upper, lower, previous, grmean
        (group mean), grmedian, grmin, grmax

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

^prdc^ computes discrete changes with confidence intervals for regression
models for categorical and count variables. Discrete change is the
difference in the predicted value as one independent variable changes
values while all others are held constant at specified values. ^prdc^ is
simply a convenient way to execute a save-dif pair of ^prvalue^ commands.
By default, the discrete change is computed for a unit increase centered
around the mean.

Values for specific independent variables can be set using the x() option
after ^prdc^. Values for the unspecified independent variables can be
set using the rest() option. The ^if^ and ^in^ conditions specify conditions
for computation of means, min, etc., that are used with rest().

The discrete change is computed by the amounts (more than one can be specified)
specified with the options. ^prdc^ works with all regression programs that are
compatable with prvalue.

Options specifying levels of variables
--------------------------------------

^x()^ explicitly sets the values of specified independent variables.

^rest()^ sets the independent variables not specified in x() to their ^mean^
    (default), ^minimum^, ^maximum^, ^median^ when calculating predicted values.
    ^grmean^ sets these independent variables to the mean conditional on the
    variables and values specified in x().  If ^prvalue^ has already been run
    after the last estimate, ^previous^ will set unspecified variables to their
    prior values.  For models other than mlogit, ^upper^ and ^lower^ can be used
    to set independent variables to their minimum or maximum depending on
    which will yield the upper or lower extreme predicted value.

Options specifying the amout of change
--------------------------------------

^from()^ specifies the start value of the change.

^to()^ specifies the start value of the change.

^binary^ specifies a change from 0 to 1.

^unit^ specifies a unit change at the values specified with x() and rest().

^sd^ specifies a standard deviation change at the values specified with x()
    and rest().

^change()^ specifies the amount of the discrete change at the values
    specified with x() and rest().

^uncentered^ specifies that the uncentered discrete change rather than the
    centered discrete change is to be computed for unit, sd and change.

Other Options
-------------

^maxcnt()^ is the maximum count value for which the probability is computed
    in count models. Default is 9.

^ystar^ requests change in predicted y*, rather than probabilities.


^all^ specifies that any calculations of means, medians, etc., should use
    the entire sample instead of the sample used to estimate the model.

^nolabel^ uses values rather than value labels in output.

^nobase^ suppresses inclusion of the base values of x in the output.

^brief^ prints only limited output.

^help^ presents guide to interpreting headings of output.


Examples
--------
.-
Authors: J. Scott Long and Jeremy Freese
         www.indiana.edu/~jslsoc/spost.htm
         spostsup@@indiana.edu