The TETRAD Project:

Causal Models and Statistical Data

TETRAD IV

Now in development, Tetrad IV runs on any platform that supports version 1.4 of the Java Runtime Enviroment (JRE). Tetrad IV provides a graphical user interface to most of the functionality of previous versions of Tetrad, plus additional functionality that reflects ongoing research. You may download and run the current development version of Tetrad IV from our download site:

Tetrad IV Download Site

Basic features include

Building causal graphs.
Parameterizing causal graphs as Bayes nets or structural equation models.
Instantiating Bayes net and structural equation models from their parameterizations.
Simulating data from Bayes nets and structural equation models.
Estimating Bayes net and structural equation models from data.
Searching for causal structure from data using PC, FCI, and Genetic Algorithm procedures.

The Tetrad IV architecture allows for modular addition of new models and editors. One set of modules currently in Tetrad IV allows data sets of gene expression levels to be simulated from known time series causal structures.

scheines@andrew.cmu.edu