Mixed Causal-Noncausal Autoregressions with Exogenous Regressors

Alain Hecq, João Victor Issler, Sean Telg

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Mixed causal‐noncausal autoregressive (MAR) models have been proposed to model time series exhibiting nonlinear dynamics. Possible exogenous regressors are typically substituted into the error term to maintain the MAR structure of the dependent variable. We introduce a representation including these covariates called MARX to study their direct impact. The asymptotic distribution of the MARX parameters is derived for a class of non‐Gaussian densities. For a Student's t‐likelihood, closed‐form standard errors are provided. By simulations, we evaluate the MARX model selection procedure using information criteria. We examine the influence of the exchange rate and industrial production index on commodity prices.
Original languageEnglish
JournalJournal of Applied Econometrics
DOIs
Publication statusPublished - 20 Jan 2020

    Fingerprint

Cite this