Learn R Programming

pendensity (version 0.2.13)

Density Estimation with a Penalized Mixture Approach

Description

Estimation of univariate (conditional) densities using penalized B-splines with automatic selection of optimal smoothing parameter.

Copy Link

Version

Install

install.packages('pendensity')

Monthly Downloads

347

Version

0.2.13

License

GPL (>= 2)

Maintainer

Christian Schellhase

Last Published

April 7th, 2019

Functions in pendensity (0.2.13)

my.positive.definite.solve

my.positive.definite.solve
Derv1

Calculating the first derivative of the pendensity likelihood function w.r.t. parameter beta
Derv2

Calculating the second order derivative with and without penalty
my.AIC

Calculating the AIC value
my.bspline

my.bspline
bias.par

Calculating the bias of the parameter beta
print.pendensity

Printing the main results of the (conditional) penalized density estimation
ck

Calculating the actual weights ck
pendenForm

Formula interpretation and data transfer
pendensity-package

The package 'pendensity' offers routines for estimating penalized unconditional and conditional (on factor groups) densities.
test.equal

Testing pairwise equality of densities
variance.par

Calculating the variance of the parameters
variance.val

Calculating variance and standard deviance of each observation.
distr.func

These functions are used for calculating the empirical and theoretical distribution functions.
dpendensity

Calculating the fitted density or distribution
pendensity

Calculating penalized density
plot.pendensity

Plotting estimated penalized densities
Allianz

Daily final prices (DAX) of the German stock Allianz in the years 2006 and 2007
D.m

Calculating the penalty matrix
new.lambda

Calculating new penalty parameter lambda
pen.log.like

Calculating the log likelihood
L.mat

Calculates the difference matrix of order m
DeutscheBank

Daily final prices (DAX) of the German stock Deutsche Bank in the years 2006 and 2007
f.hat

Calculating the actual fitted values 'f.hat' of the estimated density function f for the response y
marg.likelihood

Calculating the marginal likelihood
new.beta.val

Calculating the new parameter beta