REMIS: Retrieval from Mixed Sampling Frequency Data: G-Identifiability and Estimation of Regular and Singular VAR(MA) Systems

• Activity Number: 413 - Time Series with a Twist
• Type: Topic Contributed
• Date/Time: Wednesday, August 5, 2020 : 1:00 PM to 2:50 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Manfred Deistler and Philipp Gersing*
• Companies: Vienna University of Technology and Vienna University of Technology, Institute for Advanced Studies Vienna
• Keywords: Mixed frequency data; VAR and VARMA systems; identifiability; parameter estimation

Abstract

This paper is concerned with identifiability and estimation of an underlying high frequency VAR or VARMA system from mixed frequency observations. Such problems arise for instance in economics when some variables are observed monthly whereas others are observed quarterly. If we have identifiability, the system and noise parameters and thus all second moments of the output process can be estimated consistently from mixed frequency data. The main results show that for VAR systems, as well as for VARMA systems where the MA order is smaller than the AR order, on a generic, i.e., open and dense subset of the parameter space, identifiability holds. We deal with systems with nonsingular, as well as with singular innovation variance matrices, the latter being important in the context of generalized dynamic factor models.