Using projections and correlations to approximate probability distributions
Abstract
A method to approximate continuous multi-dimensional probability density functions (PDFs) using their projections and correlations is described. The method is particularly useful for event classification when estimates of systematic uncertainties are required and for the application of an unbinned maximum likelihood analysis when an analytic model is not available. A simple goodness of fit test of the approximation can be used, and simulated event samples that follow the approximate PDFs can be efficiently generated. The source code for a FORTRAN-77 implementation of this method is available.
Cite
@article{arxiv.physics/9805018,
title = {Using projections and correlations to approximate probability distributions},
author = {Dean Karlen},
journal= {arXiv preprint arXiv:physics/9805018},
year = {2009}
}
Comments
14 pages including 7 figures. The source code implementing the methods described in the paper are available from: ftp://ftp.physics.carleton.ca/pub/opal/karlen/procor