共 60 条
Unit root modeling for trending stock market series
被引:26
作者:
Salisu, Afees A.
[1
,2
]
Ndako, Umar B.
[3
]
Oloko, Tirimisiyu F.
[2
]
Akanni, Lateef O.
[4
]
机构:
[1] Fed Univ Agr, Dept Econ, Abeokuta, Nigeria
[2] Univ Ibadan, CEAR, Ibadan, Nigeria
[3] Cent Bank Nigeria, Monetary Policy Dept, Abuja, Nigeria
[4] Univ Lagos, Dept Econ, Lagos, Nigeria
关键词:
Trend;
Structural break;
Conditional heteroscedasticity;
Unit root;
Stock market;
D O I:
10.1016/j.bir.2016.05.001
中图分类号:
F8 [财政、金融];
学科分类号:
0202 ;
摘要:
In this paper, we examine how the unit root for stock market series should be modeled. We employ the Narayan and Liu (2015) trend GARCH-based unit root and its variants in order to more carefully capture the inherent statistical behavior of the series. We utilize daily, weekly and monthly data covering nineteen countries across the regions of America, Asia and Europe. We find that the nature of data frequency matters for unit root testing when dealing with stock market data. Our evidence also suggests that stock market data is better modeled in the presence of structural breaks, conditional heteroscedasticity and time trend. Copyright (C) 2016, Borsa Istanbul Anonim Sirketi. Production and hosting by Elsevier B.V.
引用
收藏
页码:82 / 91
页数:10
相关论文