Efficient Bayesian generalized linear models with time-varying coefficients : The walker package in R
Abstract
The R package walker extends standard Bayesian general linear models to the case where the effects of the explanatory variables can vary in time. This allows, for example, to model the effects of interventions such as changes in tax policy which gradually increases their effect over time. The Markov chain Monte Carlo algorithms powering the Bayesian inference are based on Hamiltonian Monte Carlo provided by Stan software, using a state space representation of the model to marginalize over the regression coefficients for efficient low-dimensional sampling.
Main Author
Format
Articles
Research article
Published
2022
Series
Subjects
Publication in research information system
Publisher
Elsevier BV
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-202204062188Use this for linking
Review status
Peer reviewed
ISSN
2352-7110
DOI
https://doi.org/10.1016/j.softx.2022.101016
Language
English
Published in
SoftwareX
Citation
- Helske, J. (2022). Efficient Bayesian generalized linear models with time-varying coefficients : The walker package in R. SoftwareX, 18, Article 101016. https://doi.org/10.1016/j.softx.2022.101016
License
Funder(s)
Research Council of Finland
Research Council of Finland
Research Council of Finland
Research Council of Finland
Funding program(s)
Research costs of Academy Research Fellow, AoF
Research profiles, AoF
Research costs of Academy Research Fellow, AoF
Academy Project, AoF
Akatemiatutkijan tutkimuskulut, SA
Profilointi, SA
Akatemiatutkijan tutkimuskulut, SA
Akatemiahanke, SA
Additional information about funding
This work has been supported by the Academy of Finland research grants 284513, 312605, 311877, and 331817.
Copyright© 2022 The Author(s). Published by Elsevier B.V.