The Researcher's Tool Kit

Resources for working smarter

Leave a comment >

The Center for Health Statistics at the University of Chicago distributes products of their work freely as a series of computer programs via the Internet.  These programs are developed under the direction of Don Hedeker in collaboration with Dave Patterson and his colleagues at Discerning Systems.cropped-cropped-toolkit-24157707-copy.jpg

Check out the table below with links to free downloads for:

DRUGStat, MVPreg, MIXZIP, RMASS, BIFACTOR, SuperMix, Mixed-Up Suite, NPPL, LPL, and Hakan.  Happy analyses!

DRUGStat  |  MVPreg  |  MIXZIP  |  RMASS  |  BIFACTORSuperMix  |  Mixed-Up Suite  |  NPPL  |  LPL  |  Hakan
DRUGStat is an easy to use system for determining which drugs are potentially harmful or protective relative to all other drugs in the specific class of drugs of interest.
MVPreg computes a general multivariate probit regression model for the analysis of multivariate binary data.
MIXZIP provides the maximum marginal likelihood estimates of mixed-effects Zero-Inflated Poisson (ZIP) regression models.
Authors list:
Kwan Hur, Robert D. Gibbons and Kush Kapur
Graphical user interface by Dave Patterson
The RMASS program computes sample size for three-level mixed-effects linear regression models for the analysis of clustered longitudinal data. Three-level designs are used in many areas, but in particular, multi-center randomized longitudinal clinical trials in medical or health-related research. In this case, level 1 represents measurement occasion, level 2 represents subject, and level 3 represents center.The model allows for random-effects of the time trends at both the subject-level and the center-level. The sample size determinations in this program are based on the requirements for a test of treatment by time interaction(s) for designs based on either subject-level or cluster-level randomization.The approach is general with respect to sampling proportions and number of groups, and it allows for differential attrition rates over time. The general methodology is discussed in Sample Size Determination for Hierarchical Longitudinal Designs with Differential Attrition Rates
Authors list:
Anindya Roy, Dulal K. Bhaumik, Subhash Aryal and Robert D. Gibbons
Web interface by Monica Jercan
The BIFACTOR program estimates the bifactor model for ordinal and dichotomous data.
Authors list:
Robert D. Gibbons and Donald Hedeker
SuperMix extends the functionality available in the Mixed-Up Suite by providing advanced data handling, the ability to reference columns by name, sophisticated import and export capability, visualization of data and results, increased analysis speed and additional statistical engine functions.SuperMix has been developed by Scientific Software International under an SBIR Phase II contract N44MH32056. The application will fit models with continuous, count, ordinal, nominal, and survival outcome variables with nested data, allowing for up to three levels of nesting. For a more in-depth look at SuperMix and to download a free fully functional 15-day trial edition vist the SSI SuperMix homepage.
The Mixed-Up Suite
The Mixed-up Suite provides mixed-effects regression functionality not available anywhere else — at any price. MIXOR, MIXREG, MIXNO and MIXPREG are based on the collaborative effort of Drs. Donald Hedeker and Robert D. Gibbons of the University of Illinois at Chicago and University of Chicago, respectively. Discerning Systems Inc. produced the user interfaces around the computer programs written by Don Hedeker.The work was supported by the National Institute of Mental Health and the MacArthur Foundation, and the programs are available free of charge for download from the MIXOR/MIXREG homepage located at the University of Illinois at Chicago.
Nonparametric Prediction Interval for Analysis of Microarray Data
The statistical methodology implemented in this applet is based on a nonparametric prediction interval described in Sequential Prediction Bounds for Identifying Differentially Expressed Genes in Replicated Microarray Experiments  by Robert D. Gibbons, Dulal K. Bhaumik, David R. Cox, Dennis R. Grayson, John M. Davis, and Rajiv P. Sharma.
Lognormal Prediction Limit for the Arithmetic Mean of n future samples
This program computes the 95% lognormal prediction limit for a future mean of n samples based on a historical set of m samples.
Hakan’s R Packages
R is a language and environment for statistical computing and graphics. It is a GNU project which is similar to the S language and environment which was developed at Bell Laboratories by John Chambers and colleagues. R can be considered as a different implementation of S. There are some important differences, but much code written for S runs unaltered under R. R provides a wide variety of statistical and graphical techniques, and is highly extensible. The S language is often the vehicle of choice for research in statistical methodology, and R provides an Open Source route to participation in that activity. One of R’s strengths is the ease with which well-designed publication-quality plots can be produced, including mathematical symbols and formulae where needed. Great care has been taken over the defaults for the minor design choices in graphics, but the user retains full control.1) BinNor: An R package for simultaneous generation of binary and normal data2) OrdNor: An R package for concurrent generation of ordinal and normal data3) PoisNor: An R package for simultaneous generation of count and normal data4) MultiOrd: An R package for generation of multivariate ordinal variates
Authors list:
Anup Amatya and Hakan Demirtas