Learn R Programming
⚠️There's a newer version (2.0) of this package.Take me there.

bbemkr (version 1.5)

Bayesian bandwidth estimation for multivariate kernel regression with Gaussian error

Description

Bayesian bandwidth estimation for Nadaraya-Watson type multivariate kernel regression with Gaussian error density

Copy Link

Version

Install

install.packages('bbemkr')

Monthly Downloads

83

Version

1.5

License

GPL (>= 2)

Maintainer

Han Lin Shang

Last Published

August 30th, 2011

Functions in bbemkr (1.5)

LaplaceMetropolis

Laplace-Metropolis estimator of log marginal likelihood
logpriorh2

Prior of square bandwidths
np_gibbs

Estimating bandwidths of the regressors
warmup

Burn-in period
ker

Type of kernel function
kern

Calculate the R square value and mean square error as measures of goodness of fit
bbemkr-package

Bayesian bandwidth estimation for multivariate kernel regression with Gaussian error assumption
data_y

Simulated response variable
cost2

Negative of log posterior associated with the error variance
loglikelihood

Calculate the log likelihood used in the Chib's (1995) log marginal density
nrr

Normal reference rule for estimating bandwidths
mcmcrecord

MCMC iterations
cov_chol

Calculate log marginal likeliood from MCMC output
cost

Negative of log posterior associated with the bandwidths
logdensity

Calculate an estimate of log posterior ordinate used in the log marginal density of Chib (1995).
NadarayaWatsonkernel

Nadaraya-Watson kernel estimator
xm

Values of true regression function
data_x

Simulated three-dimensional regressors
logpriors

Calculate the log prior used in the log marginal density of Chib (1995).