Bayesian Structural Vector Autoregressions with Time-Varying Identification
Efficient algorithms for Bayesian estimation of Structural Vector Autoregressions (VARs) with Stochastic Volatility heteroskedasticity, Markov-switching and Time-Varying Identification of the Structural Matrix, and a three-level global-local hierarchical prior shrinkage for the structural and autoregressive matrices. The models were developed for a paper by Camehl & Woźniak (2023). The ‘bsvarTVPs’ package is aligned regarding objects, workflows, and code structure with the R packages ‘bsvars’ by Woźniak (2024) and ‘bsvarSIGNs’ by Wang & Woźniak (2024), and they constitute an integrated toolset.
To install the bsvarTVPs package just type in R:
devtools::install_github("donotdespair/bsvarTVPs_res")