- CATMOD — Categorical data modeling
- CORRESP — Simple and multiple correspondence analysis
- FREQ — Produces one-way to
*n*-way frequency and contingency (crosstabulation) tables - GAM — Fits generalized additive models
- GENMOD — Generalized linear models
- GLIMMIX — Generalized linear mixed models
- LOGISTIC — Models with binary, ordinal, or nominal dependent variables
- PRINQUAL — Principal component analysis
- PROBIT — Maximum likelihood estimates of regression parameters and the natural (or threshold) response rate for quantal response data from biological assays or other discrete event data
- SURVEYFREQ —
One-way to
*n*-way frequency and crosstabulation tables from complex multistage survey designs with stratification, clustering, and unequal weighting - SURVEYLOGISTIC — Models with binary, ordinal, or nominal dependent variables and incorporates complex survey designs
- TRANSREG — Linear models with optimal nonlinear transformations of variables

There are two approaches to performing categorical data analyses. The first computes statistics based on tables defined by categorical variables (variables that assume only a limited number of discrete values), performs hypothesis tests about the association between these variables, and requires the assumption of a randomized process; call these methods randomization procedures. The other approach investigates the association by modeling a categorical response variable, regardless of whether the explanatory variables are continuous or categorical; call these methods modeling procedures.

Below are highlights of the capabilities of the SAS/STAT procedures that perform categorical data analysis:

- contingency tables and measures of association
- weighted least squares regression
- loglinear models
- generalized estimating equations
- Mantel-Haenszel methods
- Fisher's exact test
- exact tests for
*r x c*tables - probit analysis
- logistic analysis including the estimation and analysis of logits, generalized logits, cumulative logits, and adjacent-category logits
- various model-selection methods
- proportional odds model for ordinal response
- regression diagnostics
- conditional logistic model
- receiver operating characteristic (ROC) curves

- discrete choice models
- multinomial logit models
- bioassay analysis
- generalized linear model
- probability distributions include normal, binomial, Poisson, negative binomial, gamma, and inverse Gaussian
- link functions include logit, probit, identity, complementary log-log, log, and power with lambda=value
- profile likelihood-based confidence intervals
- likelihood ratio statistics for contrasts
- user-defined link functions and probability distributions

- principal component analysis (PCA)
- simple and multiple correspondence analysis
- repeated measures analysis
- growth-curve analysis
- split-plot designs