.-
Help for ^desmat^, ^desrep^, ^tstall^                                 [STB-52: sbe31]
.-


Using categorical variables in Stata
-------------------------------------

	^desmat^ model [, default_parameterization]

	^desrep^ [^exp^]

	^tstall^ [^equal^]


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

^desmat^ is used to generate a design matrix, i.e. a set of dummy
variables based on categorical and/or continuous variables. These
dummy variables _x_* can then be used in any appropriate Stata
procedure.

^desmat^ therefore serves the same purpose as ^xi^, but allows
different types of parameterizations than the indicator contrast
(i.e. dummy variables with a fixed reference category).

In addition, ^desmat^ allows the specification of higher order
interaction effects and an easier specification of the reference
category.

^desrep^ can be used after estimating a model, to produce a compact
overview of the estimates with informative labels.

^tstall^ can be used to perform a Wald test on all terms in the model.


Choices for default parameterization
------------------------------------

^dev(^ref^)^ indicates the deviation contrast. Parameters sum to zero
    over the categories of the variable. The parameter for ref is omitted
    as redundant, but can be found from minus the sum of the estimated
    parameters.

^ind(^ref^)^ indicates the indicator contrast, that is, dummy
    variables with ref as the reference category. This is the
    parameterization used by ^xi^ and the default parameterization for
    ^desmat^.

^sim(^ref^)^ indicates the simple contrast with ref as reference
    category. The highest order effects are the same as indicator contrast
    effects, but lower order effects and the constant will be different.


^dif(^ref^)^ indicates the difference contrast, for ordered
    categories. Parameters are relative to the previous category. If the
    first letter of ref is ^b^, then the backward difference contrast is
    used instead, and parameters are relative to the previous category.

^hel(^ref^)^ indicates the Helmert contrast, for ordered
    categories. Estimates represent the contrast between that category and
    the mean value for the remaining categories.  If the first letter of
    ref is ^b^, then the reverse Helmert contrast is used instead, and
    parameters are relative to the mean value of the preceding categories.

^orp(^ref^)^ indicates orthogonal polynomials of degree ref. The first
    dummy models a linear effect, the second a quadratic, etc. This option
    calls ^orthpoly^ to generate the design (sub)matrix.

^use(^ref^)^ indicates a user-defined contrast. ref refers to a
    contrast matrix with the same number of columns as the variable has
    categories, and at least one fewer rows. If row names are specified
    for this matrix, these names will be used as variable labels for the
    resulting dummy variables. (Single lowercase letters as names for the
    contrast matrix cause problems at the moment; for example, ^use(^c^)^.
    Use uppercase names or more than one letter, for example, ^use(^cc^)^ 
    or ^use(^C^)^.)

^dir^ indicates a direct effect, used to include continuous variables
    in the model.


Optional argument for ^desrep^
-------------------------------

^desrep^ is usually used without any arguments. If ^e(b)^ and ^e(V)^
are present, it will produce a summary of the results. If the argument
for ^desrep^ is ^exp^ it will produce multiplicative parameters, e.g.,
incident-rate ratios in Poisson regression, and odds ratios in
logistic regression. The parameters are transformed into ^exp(b)^ and
their standard errors into ^exp(b)*se^, where ^b^ is the linear
estimate and ^se^ its standard error.

Optional argument for ^tstall^
-------------------------------

The optional argument ^equal^, if used, is passed on to ^testparm^ as an
option to test for equality of all parameters in a term.  The default
is to test whether all parameters in a term are zero.


Author
------

    John Hendrickx
    University of Nijmegen, Netherlands
    j.hendrickx@@mailbox.kun.nl