Package: svars Type: Package Title: Data-Driven Identification of SVAR Models Version: 1.3.13 Date: 2025-08-24 Author: Alexander Lange [aut, cre], Bernhard Dalheimer [aut], Helmut Herwartz [aut], Simone Maxand [aut], Hannes Riebl [ctb] Authors@R: c(person("Alexander", "Lange", role = c("aut", "cre"), email = "alexanderlange328@gmail.com"), person("Bernhard", "Dalheimer", role = c("aut"), email = "bernhard.dalheimer@uni-goettingen.de"), person("Helmut", "Herwartz", role = c("aut"), email = "hherwartz@uni-goettingen.de"), person("Simone", "Maxand", role = c("aut"), email = "smaxand@uni-goettingen.de"), person("Hannes", "Riebl", role = c("ctb"))) Maintainer: Alexander Lange Description: Implements data-driven identification methods for structural vector autoregressive (SVAR) models as described in Lange et al. (2021) . Based on an existing VAR model object (provided by e.g. VAR() from the 'vars' package), the structural impact matrix is obtained via data-driven identification techniques (i.e. changes in volatility (Rigobon, R. (2003) ), patterns of GARCH (Normadin, M., Phaneuf, L. (2004) ), independent component analysis (Matteson, D. S, Tsay, R. S., (2013) ), least dependent innovations (Herwartz, H., Ploedt, M., (2016) ), smooth transition in variances (Luetkepohl, H., Netsunajev, A. (2017) ) or non-Gaussian maximum likelihood (Lanne, M., Meitz, M., Saikkonen, P. (2017) )). Depends: R (>= 2.10), vars (>= 1.5.3) Encoding: UTF-8 Imports: expm, reshape2, ggplot2, copula, clue, pbapply, steadyICA, DEoptim, zoo, strucchange, Rcpp, methods LinkingTo: Rcpp, RcppArmadillo NeedsCompilation: yes License: MIT + file LICENSE LazyData: TRUE RoxygenNote: 7.3.2 SystemRequirements: C++17 Suggests: testthat (>= 2.1.0), tsDyn Config/pak/sysreqs: libgsl0-dev libicu-dev Repository: https://alexanderlange53.r-universe.dev Date/Publication: 2025-10-18 10:24:57 UTC RemoteUrl: https://github.com/alexanderlange53/svars RemoteRef: HEAD RemoteSha: 1e06a32f998cd477633f158b79995a68f4701bf9 Packaged: 2026-06-15 09:00:00 UTC; root