svars: An R Package for Data-Driven Identification in Multivariate Time Series Analysis

svars: An R Package for Data-Driven Identification in Multivariate Time Series Analysis

SVAR models, identification, independent components, non-Gaussian maximum
likelihood, changes in volatility, smooth transition covariance, R

Structural vector autoregressive (SVAR) models are frequently applied to trace the
contemporaneous linkages among (macroeconomic) variables back to an interplay of orthogonal structural shocks. Under Gaussianity the structural parameters are unidentified
without additional (often external and not data-based) information. In contrast, the often
reasonable assumption of heteroskedastic and/or non-Gaussian model disturbances offers
the possibility to identify unique structural shocks. We describe the R package svars which
implements statistical identification techniques that can be both heteroskedasticity-based
or independence-based. Moreover, it includes a rich variety of analysis tools that are well
known in the SVAR literature. Next to a comprehensive review of the theoretical background, we provide a detailed description of the associated R functions. Furthermore, a
macroeconomic application serves as a step-by-step guide on how to apply these functions
to the identification and interpretation of structural VAR models

Helmut Herwartz

https://www.jstatsoft.org/article/view/v097i05

University of Goettingen

Januari 2021

Fajar bagus W

PDF

Inggris

Text