Catreg Software for Categorical Regression Analysis

CatReg is a computer program, written in the R (http://cran.r-project.org) programming language, to support the conduct of exposure-response analyses by toxicologists and health scientists. CatReg can be used to perform categorical regression analyses on toxicity data after effects have been assigned to ordinal severity categories (e.g., no effect, adverse effect, severe effect) and associated with up to two independent variables corresponding to the exposure conditions (e.g., concentration and duration) under which the effects occurred. CatReg calculates the probabilities of the different severity categories over the continuum of the variables describing exposure conditions. The categorization of observed responses allows expression of dichotomous, continuous, and descriptive data in terms of effect severity and supports the analysis of data from single studies or a combination of similar studies.

There are many potential applications of the CatReg program in the analysis of health effects studies and other types of data. The software was developed to support toxicity assessment for acute inhalation exposures, but the U.S. Environmental Protection Agency (EPA) encourages the broad application of this software. CatReg can be run in the Microsoft Windows environment and any other computer operating system tha supports the R statistical program (http://cran.r-project.org). Knowledge of the R programming language is not required. The CatReg software is accompanied by CatReg Software User Manual (R-version) (U.S. EPA, 2006). The User Manual provides a technical description of the statistical methods used by the program, along with instructions for installing the software, creating data input files, performing analyses, using hypothesis testing and diagnostics, and plotting graphics. Potential users are encouraged to examine the user manual, which contains illustrated examples, for ideas on adapting CatReg for their own applications. CatReg reads data from ordinary text files in which data are separated by commas. Aquery-based interface guides the user through the modeling process. Simple commands provide model summary statistics, parameter estimates, diagnostics, and graphical displays.

The special features offered by CatReg include options for:

• stratifying the analysis by user-specified covariates (e.g., species, sex, etc.)
• choosing among several basic forms of the exposure-response curve;
• using effects assigned to a range of severity categories, rather than a single category;
• using cluster-correlated data;
• including user-specified weights;
• using aggregate data; and
• query-based exclusion of user-specified data (i.e., filtering) for sensitivity analysis.

Additional Information

Citation