Providing software solutions since 1976
Exact Methods Procedures
- FREQ — Produces one-way to n-way frequency and contingency (crosstabulation) tables
- GENMOD — Generalized linear models
- LOGISTIC — Fits models with binary, ordinal, or nominal dependent variables
- MULTTEST — Addresses the multiple testing problem by adjusting the p-values from a family of hypothesis tests
- NPAR1WAY — Performs nonparametric tests for location and scale differences across a one-way classification
Exact Methods
Exact nonparametric methods have an advantage over asymptotic methods since they remain valid for very small sample sizes, as well as for data that are sparse, skewed, or heavily tied.
Below are highlights of the capabilities of the SAS/STAT procedures that can be used to perform exact conditional inference:
- exact p-values and confidence intervals for many test statistics and measures based on one-way and n-way frequency and contingency tables
- exact tests for the parameters of a logistic regression model
- exact tests for the parameters of a Poisson regression model
- exact versions of the Cochran-Armitage and Peto tests that use permutation distributions
- exact p-values for nonparametric tests
