[
Data Screening ||
Matrix Algebra with SAS/IML ||
Regression analysis ||
General Linear Models ||
Canonical correlation, Discriminant analysis ||
Logistic Regression ||
Factor Analysis ||
Clustering and scaling ||
SAS macro programs ||
Data sets ||
Programs]
These macro programs are stored in an "autocall" library on the
Hebb server, so you don't need to do anything special to have them included
in your work. Simply include lines to call the macro program.
For example (assuming you have already read in the AUTO dataset),
%boxcox(data=auto, resp=MPG, model=Weight Displa Gratio);
will search for and load the BOXCOX macro (if it has not already been loaded)
and invoke the macro with the AUTO data.
See the notes on The SAS Macro Facility for information on SAS macros.
For those items below which have links, selecting the name will take you to
brief documentation of the macro program.
The main links for these programs are:
Within SAS for Windows in the Psych Lab, online documentation may also
be obtained using the WEBHELP macro. For example,
%webhelp(boxcox);
brings up (in Firefox) documentation on the BOXCOX macro.
- biplot.sas
- Implements the biplot technique (e.g., Gabriel, 1971)
for plotting multivariate observations and variables together
in a single display.
- boxcox.sas
- Finds power transformations of the response
variable in a regression model (PROC REG) by the Box-Cox method,
with graphic display of the maximum likelihood
solution, t-values for model effects, and the
influence of observations on choice of power.
- boxglm.sas
- Finds power transformations of the response
variable in a general linear model (PROC GLM) by the Box-Cox method.
- canplot.sas
- Canonical discriminant structure plot.
Displays the observations in a dataset in the space of the two canonical
variables which discriminate most among groups. Also plots class means
on the canonical variates, confidence circles for those means, and
variable vectors showing the correlations of variables with the canonical
variates.
- corresp.sas
- Macro for correspondence analysis for analysis of patterns
of association in a contingency table. Similar to the CORRESP procedure,
but produces a data set of point labels for plotting, an produces
plots with properly equated axes.
- cpplot.sas
- Plots of Mallow's C(p) and related statistics for
model selection in linear models
- cqplot.sas
- QQ comparison plots for multivariate normal data, with confidence
envelopes.
- csmpower.sas
- Power analysis for Covariance Structure Models
- faces.sas
- Draws (possibly asymmetric) faces to represent multivariate
data.
- gtree.sas
- Graphic display of a clustering tree, using the result of either
PROC CLUSTER or PROC VARCLUS.
- inflogis.sas
- Produces an influence plot for a logistic
regression model. The plot shows a measure of
badness of fit for a given case (DIFDEV or DIFCHISQ)
vs. the fitted probability (PRED) or leverage (HAT),
using an influence measure (C or CBAR) as the size of
a bubble.
- inflplot.sas
- Produces an influence plot for a regression model
-- a plot of studentized residuals vs. leverage
(hat-value), using COOK's D or DFFITS as the size of
a bubble symbol.
- linpro.sas
- Linearly optimal profiles algorithm.
For a set of multivariate observations, this algorithm (from Hartigan, 1977)
finds scale positions
for the variables along a single dimension so that the profile traces of
the observations are as nearly linear as possible.
- meanplot.sas
- Plot means for factorial designs: plots 1-way, 2-way, or 3-way means
for a factorial design with any number of factors.
- mpower.sas
- Multivariate retrospective power analysis
Similar to the RPOWER macro, but calculates power for the multivariate tests
based on Wilks' Lambda, Pillai Trace criterion, Lawley/Hotelling Trace,
and Roy's Largest Root criterion.
- outlier.sas
- Multivariate outlier detection
The OUTLIER macro calculates
robust Mahalanobis distances by iterative multivariate trimming
(Gnanadesikan & Kettenring, 1972; Gnanadesikan, 1977),
and produces a chisquare Q-Q plot.
- partial.sas
- Produces high-resolution partial regression residual plots.
Observations with high leverage and/or large studentized
residuals can be individually labeled.
- rpower.sas
- Retrospective power analysis. Takes the OUTSTAT dataset from a PROC GLM
analysis and computes the power for each effect tested, as if the
means were population means.
- rsqdelta.sas
- Compute R-square change and F-statistics in regression.
- scatmat.sas
- Draws a scatterplot matrix for all pairs of
variables.
A classification variable may be used to assign the plotting symbol
and/or color of each point.
- scatter.sas
- Scatterplot matrix using SAS/INSIGHT.
- symbox.sas
- Boxplots for transformations to symmetry.