Indicadores coincidentes para a atividade industrial brasileira baseado em modelos vetoriais auto-regressivos de freqüências mistascomparação de metodologias

Resumo

Very useful information, usually ignored, for construction of coincident index is the target quarterly series itself. This can be very inefficient because typically the monthly coincident series keep just high economical correlation, not always tested, with the quarterly target series.
 Actually, the construction of a mixed-frequency coincident index is statistically
 complicated. On the ground that, Mariano e Murasawa presented a new methodology, in which this information is aggregated, and the quarterly variable is assumed as a latent variable observed just every three months. In this fashion, is implicitly assumed that the monthly GDP not observed represents the state of industrial economy. Usually a common factor is imposed, as in the Stock-Watson
 approach. Another possible approach more attractive is not to impose any common factor and instead, like Mariano e Murosawa, to build a mixed frequency VAR model without common factor.
 In this work we compare the performance in-sample of the mixed frequency VAR model for building coincident indicator with others approaches, dating the business cycle for industrial activity with Bry-Boschan procedure.

Ficha do documento

Tipo

Estudo

Ano

2006

Instituição

Instituto de Pesquisa Econômica Aplicada (Ipea)

Fonte

Repositório do Ipea

Idioma

Português

Acesso

Acesso aberto

Identificador

oai:repositorio.ipea.gov.br:11058/2120

Licença

Licença Comum

Temas

Dados

Palavras-chave

Indicadores coincidentesMetodologias VAR de construção de indicadores coincidentesAtividade industrialCiclos de crescimento/recessão da atividade industrial