In this paper we analyze the problem of testing for the presence of unit roots and cointegration in the case of macro-economic and financial time series. Traditional units test are not suitable for these series as they present permanent volatility shifts, so different tests have been proposed. We consider a wild bootstrap version of the M unit test. Instead of standard normal bootstrap residuals Student-t bootstrap residuals are used. Some simulations been performed comparing the results obtained using both type of bootstrap residuals. The application regards to the MSCI Equity Indices.
On Wild Bootstrap and M Unit Root Test / Schoier, Gabriella. - ELETTRONICO. - (2013), pp. 417-420. ( SIS CLADAG 2013, 9th Scientific Meeting of the Classification and Data Analysis Group of the Italian Statistical Society Modena 18-20 settembre 2013).
On Wild Bootstrap and M Unit Root Test
SCHOIER, GABRIELLA
2013-01-01
Abstract
In this paper we analyze the problem of testing for the presence of unit roots and cointegration in the case of macro-economic and financial time series. Traditional units test are not suitable for these series as they present permanent volatility shifts, so different tests have been proposed. We consider a wild bootstrap version of the M unit test. Instead of standard normal bootstrap residuals Student-t bootstrap residuals are used. Some simulations been performed comparing the results obtained using both type of bootstrap residuals. The application regards to the MSCI Equity Indices.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
