Department of Bioinformatics and Computational Biology

Home > Public Software > Archive > WFMM

This project is archived and no longer maintained.

WFMM

hidden rowfor table layout
Overview
DescriptionImplements Markov Chain Monte Carlo (MCMC) Bayesian wavelet-based functional mixed models procedue
Development Information
LanguageC++
Current version1.0
PlatformsWindows
StatusInactive
Last updated2005-04-15
NewsAs of July/August 2016, this highly cited paper received enough citations to place it in the top 1% of the academic field of Mathematics based on a highly cited threshold for the field and publication year.
References
Citation Morris JS, & Carroll RJ. (2006). Wavelet-based functional mixed models. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 68, 179-199. http://dx.doi.org/10.1111/j.1467-9868.2006.00539.x 

WFMM : Wavelet-based Functional Mixed Models

The code implements the Markov Chain Monte Carlo (MCMC) Bayesian wavelet-based functional mixed models procedure described in Section 5 of the Morris and Carroll (2004) paper. The program itself runs in the windows command prompt interface. It takes in a matlab file as an input, and outputs posterior samples for many model quantities.

Packages

WFMM.exe: The main executable.

Various DLL files: Required to run WFMM.exe

Download

You can download the package here .

System Requirements

Requires at least Windows XP to run.

Documentation

We apologize that this initial documentation is incomplete. More extensive documentation will be provided in the near future, along with scripts for performing some of the most commonly used Bayesian estimation, inference, and prediction procedures from the MCMC output from this program. We also plan to develop an R interface for this program, which we will also post when it is ready.

Sample program call (from DOS window)

wfmm c:\work\input.mat output.mat > log_file.log

Input

The program requires an input file (“input.mat” in the call) that is a matlab file containing the following objects:

Output

The output of the program is a Matlab data file (“output.mat” in the sample call), containing the following Matlab objects, as well as a log file.

Comments

Reference

Morris, JS and Carroll, RJ (2004).
Wavelet-based functional mixed models, Technical Report, University of Texas MD Anderson Cancer Center Department of Biostatistics and Applied Mathematics, UTMDABTR-006-04.