walker

Efficient Bayesian Linear Regression with Time-Varying Coefficients

Fully Bayesian linear regression where the regression coefficients are allowed to vary over "time", either as independent random walks. All computations are done using Hamiltonian Monte Carlo provided by Stan, using a state space representation of the model in order to marginalise over the coefficients for efficient sampling.

Total

17

Last month

17

Last week

17

Average per day

1

Daily downloads

Total downloads

Description file content

Package
walker
Type
Package
Title
Efficient Bayesian Linear Regression with Time-Varying Coefficients
Version
0.1.0
Date
2017-06-15
Author
Jouni Helske
Maintainer
Jouni Helske
Description
Fully Bayesian linear regression where the regression coefficients are allowed to vary over "time", either as independent random walks. All computations are done using Hamiltonian Monte Carlo provided by Stan, using a state space representation of the model in order to marginalise over the coefficients for efficient sampling.
License
GPL (>= 2)
Suggests
knitr (>= 1.11), rmarkdown (>= 0.8.1), testthat
Depends
R (>= 3.0.2), rstan (>= 2.14.1)
Imports
Rcpp (>= 0.12.9), methods
LinkingTo
StanHeaders (>= 2.14.0.1), rstan (>= 2.14.1), BH (>= 1.62.0.1), Rcpp (>= 0.12.9), RcppEigen (>= 0.3.2.9.0)
VignetteBuilder
knitr
SystemRequirements
C++11
RoxygenNote
6.0.1
NeedsCompilation
yes
Packaged
2017-06-15 14:11:29 UTC; jouni
Repository
CRAN
Date/Publication
2017-06-15 15:18:48 UTC

install.packages('walker')

0.1.0

8 days ago

Jouni Helske

GPL (>= 2)

Depends on

R (>= 3.0.2), rstan (>= 2.14.1)

Imports

Rcpp (>= 0.12.9), methods

Suggests

knitr (>= 1.11), rmarkdown (>= 0.8.1), testthat

Discussions