Simulation-based estimation of threshold moving average models with contemporaneous shock asymmetry and an application to Turkish business cycles


TAŞTAN H.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, vol.46, no.5, pp.3870-3891, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 46 Issue: 5
  • Publication Date: 2017
  • Doi Number: 10.1080/03610918.2015.1035447
  • Journal Name: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.3870-3891
  • Keywords: Contemporaneous asymmetry, Efficient method of moments, Persistence of shocks, Threshold moving average models, Turkish business cycles, TIME-SERIES, PERSISTENCE, MOMENTS
  • Yıldız Technical University Affiliated: Yes

Abstract

Persistence of shocks to economic time series may differ depending on the sign of the shock or on a threshold value. Threshold moving average (TMA) models, by explicitly taking into account threshold behavior, can help discriminate whether there exists persistence asymmetry. This article considers TMA models in which both contemporaneous and lagged asymmetric effects are both present and examines the properties of simulation-based efficient method of moments estimation using Monte Carlo simulation experiments. The model is applied to analyze the persistence properties of shocks to growth rates of gross domestic product and industrial production index in Turkish economy.