Abstract

Este trabalho compara previsoes da taxa de inflacao mensal brasileira a partir de diferentes modelos lineares e nao lineares de series temporais e da curva de Phillips. Em geral, os modelos nao lineares apresentaram um melhor desempenho preditivo. Um modelo VAR produziu o menor erro quadratico medio de previsao (EQM) entre os modelos lineares, enquanto as melhores previsoes, entre todos os modelos, foram geradas pela curva de Phillips ampliada com threshold, a qual apresentou um EQM 20% menor do que a do modelo VAR. Essa diferenca e significante de acordo com o teste de Diebold e Mariano (1995).

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.