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 (Formula presented.) 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 language | English |
|---|---|
| Pages (from-to) | 328-343 |
| Number of pages | 16 |
| Journal | Journal of Applied Econometrics |
| Volume | 35 |
| Issue number | 3 |
| Early online date | 20 Jan 2020 |
| DOIs | |
| Publication status | Published - Apr 2020 |
Funding
This work was partly written while Sean Telg visited the CREST in Paris, Alain Hecq EPGE/FGV in Rio de Janeiro, and João Victor Issler Maastricht University. We thank all institutions for hosting us. We would like to express gratitude to Christian Francq and Jean‐Michel Zakoïan for stimulating and fruitful discussions. We also thank participants of CFE (Seville, 2016), SNDE (Paris, 2017), EcoSta (Hong Kong, 2017), IAAE (Sapporo, 2017), and ESEM (Lisbon, 2017), as well as two anonymous referees for valuable comments and remarks. João Victor Issler acknowledges the financial support of CNPq, FAPERJ, and CAPES on different grants. This study was partly financed by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES; Finance Code 001). The authors declare no conflict of interest.
| Funders | Funder number |
|---|---|
| ESEM | |
| Jo?o Victor Issler Maastricht University | |
| SNDE | |
| International Association for Applied Econometrics | |
| Coordenação de Aperfeiçoamento de Pessoal de Nível Superior | |
| Conselho Nacional de Desenvolvimento Científico e Tecnológico | |
| Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro | |
| Conseil Français de l'Ãnergie |