Testing for nonlinearity in G7 macroeconomic time series


Yavuz N., Yilanci V.

Romanian Journal of Economic Forecasting, cilt.15, sa.3, ss.69-79, 2012 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 15 Sayı: 3
  • Basım Tarihi: 2012
  • Dergi Adı: Romanian Journal of Economic Forecasting
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Social Sciences Citation Index (SSCI), Scopus
  • Sayfa Sayıları: ss.69-79
  • İstanbul Üniversitesi Adresli: Evet

Özet

In this study, we test the linearity of G7 macroeconomic time series over the period 1959Q1-1999Q4. The stationarity properties of this dataset was before tested by Aksoy and Ledesma (2008) employing unit root tests which are based on linear and nonlinear models. Aksoy and Ledesma (2008) concluded that the variables have uncertain order of integration. Therefore, by employing a recently introduced linearity test of Harvey et al. (2008), which is a powerful test even the order of integration is not certain, we test the linearity of this dataset to determine which kind of unit root test should have been used. We also show that more than half of the series are nonlinear which indicates the importance of testing the nonlinearity of macroeconomic time series.