Open AccessEstimation for nearly unit root processes with ARFIMA-GARCH errors
Author(s) -
Chen Ling-ju,
Bihua Xie
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1592/1/012036
Subject(s) - autoregressive fractionally integrated moving average , unit root , autoregressive model , autoregressive conditional heteroskedasticity , mathematics , root (linguistics) , econometrics , statistics , long memory , volatility (finance) , linguistics , philosophy
In this paper, we introduce a nearly unit root processes with ARFIMA( p; d; q )-GARCH( l;m ) errors, and establish an asymptotic theorem for the autoregressive coefficient estimation of the proposed model under very mild conditions. It’s shown that the DF-type tests are functionals of the Ornstein-Uhlenbeck process rather than those of standard Brownian motions in the unit root case.