BayesGESM (version 1.4)

BayesGESM-package: Bayesian Analysis of Generalized Elliptical Semi-Parametric Models and Flexible Measurement Error Models

Description

This package allows to perform the statistical inference based on the Bayesian approach for regression models under the assumption that independent additive errors follow normal, Student-t, slash, contaminated normal, Laplace or symmetric hyperbolic distributions, i.e., additive errors follow a scale mixtures of normal distributions. The regression models considered in this package are: (i) Generalized elliptical semi-parametric models, where both location and dispersion parameters of the response variable distribution include non-parametric additive components described by using B-splines; and (ii) Flexible measurement error models under the presence of homoscedastic and heteroscedastic random errors, which admit explanatory variables with and without measurement additive errors as well as the presence of non-parametric components approximated by using B-splines.

Details

Package:

BayesGESM

Type:

Package

Version:

1.4

Date:

2015-06-04

License:

GPL-2 | GPL-3

References

Rondon, L.M. and Bolfarine, H. (2015) Bayesian Analysis of Generalized Elliptical Semi-parametric Models. (submitted).

Rondon, L.M. and Bolfarine, H. (2015). Bayesian analysis of flexible measurement error models.(submitted)

Examples

######### Example for Generalized Elliptical Semi-parametric Models #####
#library(ssym)
#data(Erabbits)
#Erabbits2 <- Erabbits[order(Erabbits$age,Erabbits$wlens),]
#attach(Erabbits2)

#fit <- gesm(wlens ~ bsp(age) | bsp(age), family= "ContNormal", eta=c(0.8,0.9),
#				 burn.in=1000, post.sam.s=5000, thin=2)			 
#summary(fit)

######### Example for Flexible Measurement Error Models ################
#### Ragweed Pollen ####
#library(SemiPar)
#data(ragweed)
#attach(ragweed)
#ragweedn <- as.data.frame(ragweed[year==1993,])
#
#model <- fmem(sqrt(ragweed) ~ wind.speed | rain + temperature + bsp(day.in.seas),
#			   data=ragweedn,family="Normal", burn.in=500, post.sam.s=2000,
#			   thin=10, omeg=1)
#summary(model)
# bsp.graph.fmem(model, 1, xlab="day.in.seas", ylab="f(day.in.seas)")
#						
#
#### Boston Data set #########
#library(MASS)
#data(Boston)
#attach(Boston)
#model <- fmem(log(medv) ~ nox | crim + rm + bsp(lstat) + bsp(dis), data=Boston,
#              family="ContNormal", burn.in=10000, post.sam.s=5000, omeg=4, thin=10)
#summary(model)			   
#bsp.graph.fmem(model,1) ### for variable lstat
#bsp.graph.fmem(model,2) ### for variable dis
#