Forecasting transaction counts with integer-valued GARCH models

被引:8
作者
Aknouche, Abdelhakim [1 ,2 ]
Almohaimeed, Bader S. [1 ]
Dimitrakopoulos, Stefanos [3 ]
机构
[1] Qassim Univ, Coll Sci, Dept Math, POB 707, Buraydah 51431, Saudi Arabia
[2] Univ Sci & Technol Houari Boumediene, Fac Math, Bab Ezzouar, Algeria
[3] Univ Leeds, Leeds Univ Business Sch, Econ Div, Leeds LS2 9JT, W Yorkshire, England
关键词
count time series; forecasting; INGARCH models; MCMC; QUASI-LIKELIHOOD INFERENCE; TIME-SERIES; POISSON;
D O I
10.1515/snde-2020-0095
中图分类号
F [经济];
学科分类号
02 ;
摘要
Using numerous transaction data on the number of stock trades, we conduct a forecasting exercise with INGARCH models, governed by various conditional distributions; the Poisson, the linear and quadratic negative binomial, the double Poisson and the generalized Poisson. The model parameters are estimated with efficient Markov Chain Monte Carlo methods, while forecast evaluation is done by calculating point and density forecasts.
引用
收藏
页码:529 / 539
页数:11
相关论文
共 29 条
[1]   Poisson QMLE of Count Time Series Models [J].
Ahmad, Ali ;
Francq, Christian .
JOURNAL OF TIME SERIES ANALYSIS, 2016, 37 (03) :291-314
[2]   COUNT AND DURATION TIME SERIES WITH EQUAL CONDITIONAL STOCHASTIC AND MEAN ORDERS [J].
Aknouche, Abdelhakim ;
Francq, Christian .
ECONOMETRIC THEORY, 2021, 37 (02) :248-280
[3]   Negative Binomial Quasi-Likelihood Inference for General Integer-Valued Time Series Models [J].
Aknouche, Abdelhakim ;
Bendjeddou, Sara ;
Touche, Nassim .
JOURNAL OF TIME SERIES ANALYSIS, 2018, 39 (02) :192-211
[4]   An adaptive version for the Metropolis Adjusted Langevin algorithm with a truncated drift [J].
Atchade, Yves F. .
METHODOLOGY AND COMPUTING IN APPLIED PROBABILITY, 2006, 8 (02) :235-254
[5]   Bayesian Forecasting of Many Count-Valued Time Series [J].
Berry, Lindsay R. ;
West, Mike .
JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2020, 38 (04) :872-887
[6]  
Cameron C., 2013, Regression Analysis of Count Data
[7]   Autoregressive conditional negative binomial model applied to over-dispersed time series of counts [J].
Chen, Cathy W. S. ;
So, Mike K. P. ;
Li, Jessica C. ;
Sriboonchitta, Songsak .
STATISTICAL METHODOLOGY, 2016, 31 :73-90
[8]  
Chib S., 2001, Handbook of Econometrics, V5, P3569, DOI [10.1016/S1573-4412(01)05010-3, 10.1016/S1573-4412(01)05010-3volume5, DOI 10.1016/S1573-4412(01)05010-3]
[9]   QUASI-LIKELIHOOD INFERENCE FOR NEGATIVE BINOMIAL TIME SERIES MODELS [J].
Christou, Vasiliki ;
Fokianos, Konstantinos .
JOURNAL OF TIME SERIES ANALYSIS, 2014, 35 (01) :55-78
[10]   THEORY AND INFERENCE FOR A CLASS OF NONLINEAR MODELS WITH APPLICATION TO TIME SERIES OF COUNTS [J].
Davis, Richard A. ;
Liu, Heng .
STATISTICA SINICA, 2016, 26 (04) :1673-1707