This package implements a novel method for fitting a bounded probability distribution to quantiles (for example stated by an expert), see Bornkamp and Ickstadt (2009) for details. For this purpose B-splines are used, and the density is obtained by penalized least squares based on a Brier entropy penalty. The package provides methods for fitting the distribution as well as methods for evaluating the underlying density and cdf. In addition methods for plotting the distribution, drawing random numbers and calculating quantiles of the obtained distribution are provided.
|Date of publication||2010-05-23 07:10:59|
|Maintainer||Bjoern Bornkamp <firstname.lastname@example.org>|
comparePlot: Compare different elicitated densities.
fit.SEL: Fit an SEL object
getbinPost: Calculate posterior distribution for binomial model
knotave: Calculate the knot averages of a B-spline basis.
min.abs: Find gamma given Delta
plot.SEL: Plotting an SEL object
predict.SEL: Evaluate the expert's density (or cdf)
quantSEL: Calculate quantiles of an SEL object.
rvSEL: Simulate from the expert's distribution
SEL: Semiparametric Elicitation of a bounded parameter
SEL-internal: SEL internal functions
SEL-package: Semiparametric Elicitation of a bounded parameter.