CMStatistics 2020: Start Registration
View Submission - CFE
Title: Identifiability and estimation of possibly non-invertible SVARMA models: A new parametrisation Authors:  Bernd Funovits - University of Helsinki (Finland) [presenting]
Abstract: The focus is on parameterisation, identifiability, and maximum likelihood (ML) estimation of possibly non-invertible structural vector autoregressive moving average (SVARMA) models driven by independent and non-Gaussian shocks. We introduce a new parameterisation of the MA polynomial matrix based on the Wiener-Hopf factorisation (WHF) and show that the model is identified in this parametrisation for a generic set in the parameter space (when certain just-identifying restrictions are imposed). In particular, this parmetrization allows for MA zeros at zero, which can be interpreted as informational delays. Typically imposed identifying restrictions on the shock transmission matrix as well as on the determinantal root location are made testable. Furthermore, we provide low-level conditions for asymptotic normality of the ML estimator and analytic expressions for the score and the information matrix. As an application, we analyze non-invertibility (and in particular delays) in a standard macro-econometric model. This and further analyses are implemented in a well documented R-package.