logcondiscr: Estimate a Log-Concave Probability Mass function from Discrete i.i.d. Observations

Given independent and identically distributed observations X(1), ..., X(n), this package allows to compute the maximum likelihood estimator (MLE) of probability mass function (pmf) under the assumption that it is log-concave, see Weyermann (2007) and Balabdaoui, Jankowski, Rufibach, and Pavlides (2012). The main functions of the package are 'logConDiscrMLE' that allows computation of the log-concave MLE, 'logConDiscrCI' that computes pointwise confidence bands for the MLE, and 'kInflatedLogConDiscr' that computes a mixture of a log-concave PMF and a point mass at k.

Version: 1.0.2
Depends: Matrix, mvtnorm, cobs
Published: 2012-01-24
Author: Kaspar Rufibach and Fadoua Balabdaoui and Hanna Jankowski and Kathrin Weyermann
Maintainer: Kaspar Rufibach <kaspar.rufibach at gmail.com>
License: GPL (≥ 2)
URL: http://www.kasparrufibach.ch , http://www.ceremade.dauphine.fr/~fadoua , http://www.math.yorku.ca/~hkj
CRAN checks: logcondiscr results

Downloads:

Package source: logcondiscr_1.0.2.tar.gz
MacOS X binary: logcondiscr_1.0.2.tgz
Windows binary: logcondiscr_1.0.2.zip
Reference manual: logcondiscr.pdf
News/ChangeLog:NEWS
Old sources: logcondiscr archive