Instrumental Variables Inference in a State Space Model

68 Pages Posted: 9 Jan 2019 Last revised: 25 Sep 2019

See all articles by Federico Carlini

Federico Carlini

Università della Svizzera italiana; Dipartimento di Economia e Finanza

Patrick Gagliardini

USI Università della Svizzera italiana; Swiss Finance Institute

Date Written: September 24, 2019

Abstract

We study semi-parametric inference in a Vector Autoregressive (VAR) model of order p augmented by unobservable common factors with a dynamic described by a VAR process of order q. This state-space specification is useful to define a network of interconnectedness and to measure separately the impulse responses to either systematic, or idiosyncratic, shocks. We show that the state-space parameters are identifiable from the autocovariance function of the observed process.

We estimate the model by means of a multi-step procedure in closed-form, which combines an eigenvalue-eigenvector matrix decomposition and Instrumental Variable (IV) estimation allowing for Hansen-Sargan specification tests. We study the asymptotic and finite-sample properties of the parameter estimators and of rank tests for selecting the number of unobservable factors and VAR orders. In an empirical application we investigate which are the dynamic common factors that drive the co-movements in the daily log absolute return series of four sectorial stock market indices of the Chinese economy.

Keywords: State Space, FAVAR, Identification, Network, Financial Crisis

JEL Classification: C32, C38

Suggested Citation

Carlini, Federico and Gagliardini, Patrick, Instrumental Variables Inference in a State Space Model (September 24, 2019). Available at SSRN: https://ssrn.com/abstract=3306732 or http://dx.doi.org/10.2139/ssrn.3306732

Federico Carlini (Contact Author)

Università della Svizzera italiana ( email )

Via Buffi 13
Lugano, 6900
Switzerland

Dipartimento di Economia e Finanza ( email )

Rome
Rome, ID Rome
Italy

Patrick Gagliardini

USI Università della Svizzera italiana ( email )

Via Buffi 13
Lugano, TN 6900
Switzerland

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
14
Abstract Views
139
PlumX Metrics