Free Software

Our software resources are permanently archived at

The software is no longer supported by the Help Desk. For the latest software and research updates, visit the sites of our investigators: Bethany Bray (LCA & LTA), Linda Collins (MOST), Stephanie Lanza (TVEM), Runze Li (ILD, Variable Screening/Selection), Susan Murphy (JITAI), and University of Michigan’s d3lab (SMART).

Latent Class Analysis & Latent Transition Analysis

SAS procedures for latent class analysis & latent transition analysis

SAS macros for use with PROC LCA
LCA Covariates 3-Step
LCA Distal
LCA Graphics
LCA Bootstrap
Simulate LCA Dataset

LCA Stata plugin
Stata plugin for latent class analysis

Functions for use with the LCA Stata plugin
LCA Bootstrap Stata
LCA Distal Stata

Standalone program for latent transition analysis

LCA outcome probability calculator
for Microsoft Excel

Latent Class Causal Analysis
R package


Variable Selection

SAS procedures for variable selection

R package for high-dimensional screening in semiparametric, longitudinal regression (Hosted on CRAN.)

Time-Varying Effect Modeling (TVEM)

SAS macro for time-varying effect modeling

Weighted TVEM
SAS TVEM macro that accommodates survey weights and clusters

Optimizing Interventions

Multiphase optimization strategy (MOST)

SAS macro for charting the relative cost of reduced factorial designs

SAS macro for calculating the power, effect size, or sample size of a factorial experiment

Random assignment generator for factorial experiments
Web applet that provides a list of random numbers that can be used to assign participants to conditions in an experiment with many conditions

MOST Toolkit for R
R package for implementing functionality of other MOST software in R. (Hosted on CRAN.)

Analysis of Intensive Longitudinal Data

SAS macro for estimating functional hierarchical linear models using local linear regression estimation

R Package for functional regression of irregularly timed ILD. (Hosted on CRAN.)

TVEM can be used to analyze intensive longitudinal data.

Just-in-Time Adaptive Interventions

Micro-randomized trials (MRTs)

A sample size calculator for micro-randomized trials is available both as a web applet and as an R package hosted on CRAN

R code for assessing time-varying causal effect moderation
For analyzing data from an MRT

Sequential, Multiple Assignment, Randomized Trial (SMART)

SAS code to compare embedded adaptive interventions

R package for informing the development of adaptive interventions

SAS procedure for informing the development of adaptive intervention


SMART sample size applets

Applet for selecting the best embedded adaptive intervention in a SMART based on a continuous outcome

Applet for comparing two embedded adaptive interventions in a SMART based on a survival outcome

Applet for calculating the minimum sample size for a pilot SMART

Applet for calculating the minimum sample size for SMARTs with Binary or Continuous Outcomes