SUDAAN® Statistical Software for Analyzing Correlated Data

Internationally recognized statistical software package for analyzing data from complex studies


Developed by our expert statisticians and programmers, SUDAAN is a software package designed for researchers who work with study data. SUDAAN procedures properly account for correlated observations, clustering, weighting, stratification, and other complex design features—making them ideal for efficiently and accurately analyzing data from surveys and experimental studies.

Used by more than 1,400 analysts in government, academia, and the private-sector, SUDAAN offers valuable add-on capabilities to other statistical software packages.

By adding SUDAAN to your suite of statistical analysis tools, you will be able to perform more complex statistical procedures such as weight calibration and imputation, and support a wider range of survey designs with our fully tested and proven solution.

SAS-Callable and Standalone Versions for All Major Platforms

Versions of SUDAAN are available for a wide variety of computing platforms—either as a stand-alone product or as a callable add-on to SAS®. SUDAAN will read SAS and SPSS® files and complies with Section 508 and United States Government Configuration Baseline (USGCB) standards.

Perform Design-Corrected Analyses of Complex Data

SUDAAN will enable you to properly analyze

  • Data from complex sample surveys
  • Epidemiological study data
  • Clinical trial data
  • Experiments or observational studies
  • Longitudinal data.

SUDAAN provides estimates that correctly account for complex design features, including

  • Unequally weighted or unweighted data
  • Stratification
  • With- or without-replacement designs
  • Multistage and cluster designs
  • Repeated measures
  • General cluster-correlation
  • Multiply imputed analysis variables.

Unique Options for Robust Variance Estimation

SUDAAN offers eight design options to determine how standard error estimates are obtained, enabling you to specify a wide variety of sample designs often found in sample surveys and other correlated data situations. In addition, SUDAAN offers all three popular robust variance estimation methods:

  • Taylor series linearization (GEE for regression models)
  • Jackknife
  • Balance repeated replication (BRR).

SUDAAN is designed to handle observations that are not necessarily independent nor identically distributed.

SUDAAN Courses and Customized Training

To help you get the most value out of SUDAAN, RTI offers standard courses in SUDAAN descriptive procedures, modeling procedures, and computing weight adjustments and deriving imputations.

Our courses take place in computer labs that are applicable to all supported platforms and are taught by experienced instructors who use SUDAAN to analyze correlated data on a regular basis. Class size is kept small to allow one-on-one interaction with the instructor and classmates.

Robust Examples and Data Sets

SUDAAN comes with more than 200 examples and data sets to help you hone analytic skills and make the most of this robust tool.