CProb: A Computational Tool for Conducting Conditional Probability Analysis
- Jeffrey W. Hollister *a,
- Henry A. Walkera and
- John F. Paulb
- a U.S. Environmental Protection Agency, Office of Research and Development, National Health and Environmental Effects Research Lab., Atlantic Ecology Div., 27 Tarzwell Drive, Narragansett, RI 02882
b U.S. Environmental Protection Agency, Office of Research and Development, Mail Code B343-06, Research Triangle Park, NC 27711
Conditional probability is the probability of observing one event given that another event has occurred. In an environmental context, conditional probability helps to assess the association between an environmental contaminant (i.e., the stressor) and the ecological condition of a resource (i.e., the response). These analyses, when combined with controlled experiments and other methodologies, show great promise in evaluating ecological conditions from observational data and in defining water quality and other environmental criteria. Current applications of conditional probability analysis (CPA) are largely done via scripts or cumbersome spreadsheet routines, which may prove daunting to end-users and do not provide access to the underlying scripts. Combining spreadsheets with scripts eases computation through a familiar interface (i.e., Microsoft Excel) and creates a transparent process through full accessibility to the scripts. With this in mind, we developed a software application, CProb, as an Add-in for Microsoft Excel with R, R(D)com Server, and Visual Basic for Applications. CProb calculates and plots scatterplots, empirical cumulative distribution functions, and conditional probability. In this short communication, we describe CPA, our motivation for developing a CPA tool, and our implementation of CPA as a Microsoft Excel Add-in. Further, we illustrate the use of our software with two examples: a water quality example and a landscape example. CProb is freely available for download at http://www.epa.gov/emap/nca/html/regions/cprobPlease view the pdf by using the Full Text (PDF) link under 'View' to the left.
Copyright © 2008.