 |
 |
 |
 |
 |
 |
Sains Malaysiana 54(11)(2025):
2797-2808
http://doi.org/10.17576/jsm-2025-5411-18
An
Innovative Approach to Financial Market Analysis: Hybrid ARFIMA with Sieve and
Moving Block Bootstrap
(Pendekatan Inovatif untuk Analisis Pasaran Kewangan: Hibrid ARFIMA dengan Saringan dan Butstrap Blok Bergerak)
ALSHAIMAA ELWASIFY1,2 &
ZAIDI ISA1,2*
1School of Mathematical Sciences, Faculty of Sciences &
Technology, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
2Applied Statistics Department, Faculty of Commerce, Damietta
University, 34511 Damietta, Egypt
Received: 14 April 2025/Accepted: 24 October 2025
Abstract
This paper aims to develop the field of
financial time series analysis by focusing on the Egyptian stock market, EGX 30
in particular, using innovative modeling and forecasting techniques. Our study
explores the application of ARFIMA models either independently or in
combination with advanced bootstrap techniques to improve the accuracy of
parameter estimation and forecasting. The study includes four main
methodologies: the traditional ARFIMA model, ARFIMA with Sieve Bootstrap (SB),
ARFIMA with Moving Block Bootstrap (MBB), and the proposed model that combines
the two bootstrap techniques with the ARFIMA model. The proposed model aims to
address the time complexities in the financial series, including long term and
short-term dependencies. The results show that the proposed model significantly
outperforms other traditional and combined models in terms of forecasting
accuracy and estimation reliability. This improved performance underscores the
importance of integrating advanced bootstrap techniques with traditional models
to better understand the complex characteristics of financial data. Our paper
contributes to scientific literature by introducing a new approach that has not
been applied before in financial markets. It also offers practical applications
for investors and financial analysts by providing a robust framework for
forecasting and supporting decision-making in dynamic and volatile market
environments, with a focus on the Egyptian market. This study represents a
basis for applying similar methodologies in other emerging markets.
Keywords: ARFIMA;
bootstrap; MBB; Reisen
method; sieve bootstrap
Abstrak
Kertas ini bertujuan untuk membangunkan bidang analisis siri masa kewangan dengan memberi tumpuan kepada pasaran saham Mesir, khususnya EGX 30, menggunakan teknik pemodelan dan ramalan yang inovatif. Penyelidikan kami meneroka penggunaan model ARFIMA sama ada secara bebas atau digabungkan dengan teknik butstrap lanjutan untuk meningkatkan ketepatan anggaran dan ramalan parameter.
Kajian ini merangkumi empat metod utama:
model ARFIMA tradisional, ARFIMA dengan Butstrap Saringan (SB),
ARFIMA dengan Butstrap Blok Bergerak (MBB) dan model yang dicadangkan yang menggabungkan dua teknik butstrap dengan model ARFIMA. Model yang dicadangkan bertujuan untuk menangani kerumitan masa dalam siri kewangan, termasuk kebergantungan jangka panjang dan jangka pendek. Keputusan menunjukkan bahawa model yang dicadangkan mengatasi model tradisional dan gabungan lain dengan ketara dari segi ketepatan ramalan dan kebolehpercayaan anggaran. Prestasi yang dipertingkatkan ini menggariskan kepentingan mengintegrasikan teknik butstrap lanjutan dengan model tradisional untuk lebih memahami ciri kompleks data kewangan. Kertas kami ini menyumbang kepada kepustakaan saintifik dengan memperkenalkan pendekatan baharu yang belum pernah digunakan sebelum ini dalam pasaran kewangan. Ia juga menawarkan aplikasi praktikal untuk pelabur dan penganalisis kewangan dengan menyediakan rangka kerja yang mantap untuk membuat ramalan dan menyokong proses membuat keputusan dalam persekitaran pasaran yang dinamik dan tidak menentu dengan tumpuan kepada pasaran Mesir. Kajian ini merupakan asas untuk mengaplikasikan metod yang serupa dalam pasaran baharu lain yang muncul.
Kata kunci:
ARFIMA; butstrap; butstrap saringan; kaedah Reisen; MBB
REFERENCES
Aladag, C.H., Egrioglu, E. & Kadilar, C. 2012.
Improvement in forecasting accuracy using the hybrid model of ARFIMA and feed
forward neural network. American Journal of Intelligent Systems 2(2): 12-17.
Brockwell, P.J. & Davis, R.A. 1990. Time Series:
Theory and Methods. 2nd ed. Springer Series in Statistics - Springer.
Bühlmann, P. 1997. Sieve bootstrap for time series. Bernoulli 3(2): 123-148.
Carlstein, E. 1986. The use of subseries values for
estimating the variance of a general statistic from a stationary sequence. The
Annals of Statistics 14(3): 1171-1179.
Dingari, M., Reddy, D.M. & Sumalatha, V. 2019. Time
series analysis for long memory process of air traffic using ARFIMA. International
Journal of Scientific and Technology Research 8(10): 395-400.
Efron, B. 1979. Bootstrap methods: Another look at the jackknife. The Annals of Statistics 7(1): 1-26.
Erfani, A. & Samimi, A.J. 2009. Long memory forecasting
of stock price index using a fractionally differenced ARMA model. Journal of
Applied Sciences Research 5(10): 1721-1731.
Fokam, C.T., Jentsch, C., Lang, M. & Pauly, M. 2024. AR-sieve
bootstrap for the random forest and a simulation-based comparison with rangerts
time series prediction. https://doi.org/10.48550/arXiv.2410.00942
Franco, G.C., Lana, G.C. & Reisen, V.A. 2021. Prediction intervals
in the ARFIMA model using bootstrap. Financial Statistical Journal 4(1):
1-8.
Hall, P. 1985. Resampling a coverage pattern. Stochastic
Processes and their Applications 20(2): 231-246.
Hassler, U. 1993. Regression of spectral estimators with
fractionally integrated time series. Journal of Time Series Analysis 14(4): 369-380.
Kartikasari, P., Yasin, H. & Asih I Maruddani, D. 2020.
ARFIMA model for short term forecasting of new death cases COVID-19. E3S Web
of Conferences 202: 13007.
Kim, Y.M. & Kim, Y. 2017. Bootstrap methods for
long-memory processes: A review. Communications for Statistical Applications
and Methods 24(1): 1-13.
Kreiss, J.P. 1992. Bootstrap procedures for AR (∞) - processes.
In Bootstrapping and Related Technique. Lecture Notes in Economics and
Mathematical Systems, edited by Jöckel, K.H., Rothe, G. & Sendler, W.
Berlin, Heidelberg: Springer. 376: 107-113.
Kreiss, J.P. 1988. Asymptotic statistical inference for a
class of stochastic processes. Verlag nicht ermittelbar.
Kreiss, J.P. & Lahiri, S.N. 2012. Bootstrap methods for
time series. Time Series Analysis: Methods and Applications 30: 3-26.
Künsch, H. 1987. Statistical
aspects of self-similar processes. Proceedings of the First World Congress
of the Bernoulli Society. Utrecht: VNU Science. 1: 67-74.
Kurita, T. 2010. A forecasting model for Japan’s unemployment
rate. Eurasian Journal of Business and Economics 3(5): 127-134.
Lahiri, S.N. 2003. Resampling Methods for Dependent Data.
Springer Series in Statistics - Springer.
Lola, M.S., David, A. & Zainuddin, N.H. 2016. Bootstrap approaches
to autoregressive model on exchange rates currency. Open Journal of
Statistics 6(6): 1010-1024.
Olatayo, T.O. & Adedotun, A.F. 2014. On the test and
estimation of fractional parameter in ARFIMA model: Bootstrap approach. Applied
Mathematical Sciences 8(96): 4783-4792.
Omekara, C.O., Okereke, O.E. & Ukaegeu, L.U. 2016.
Forecasting liquidity ratio of commercial banks in Nigeria. Microeconomics
and Macroeconomics 4(1): 28-36.
Paparoditis, E. & Politis, D.N. 2002. The local bootstrap
for Markov processes. Journal of Statistical Planning and Inference 108(1-2): 301-328.
Paul, R.K. 2014. Forecasting wholesale price of pigeon pea
using long memory time-series models. Agricultural Economics Research Review 27(2): 167-176.
Reisen, V.A. 1994. Estimation of the fractional difference
parameter in the ARIMA (p, d, q) model using the smoothed periodogram. Journal
of Time Series Analysis 15(3): 335-350.
Reisen, V., Abraham, B. & Lopes, S. 2001. Estimation of
parameters in ARFIMA processes: A simulation study. Communications in
Statistics - Simulation and Computation 30(4): 787-803.
Saâdaoui, F. & Rabbouch, H. 2024. Financial forecasting
improvement with LSTM-ARFIMA hybrid models and non-Gaussian distributions. Technological
Forecasting and Social Change 206: 123539.
Safitri, D., Mustafid, Ispriyanti, D. & Sugito. 2019.
Gold price modeling in Indonesia using ARFIMA method. Journal of Physics:
Conference Series 1217: 012087.
Shang, H.L. 2023. Sieve bootstrapping the memory parameter in
long-range dependent stationary functional time series. AStA Advances in
Statistical Analysis 107(3): 421-441.
Silva, E.M., Franco, G.C., Reisen, V.A. & Cruz, F.R.B.
2006. Local bootstrap approaches for fractional differential parameter
estimation in ARFIMA models. Computational Statistics and Data Analysis 51(2): 1002-1011.
Sun, R., Chen, Y.Q. & Li, Q. 2008. The modeling and
prediction of Great Salt Lake elevation time series based on ARFIMA. 2007
Proceedings of the ASME International Design Engineering Technical Conferences
and Computers and Information in Engineering Conference, DETC2007 5 PART
B. pp. 1349-1359.
The Egyptian Exchange. 2024. EGX30.
https://www.egx.com.eg/en/indexdata.aspx?type=1&nav=1 (Accessed in 2024)
Vogel, R.M. & Shallcross, A.L. 1996. The moving blocks
bootstrap versus parametric time series models. Water Resources Research 32(6): 1875-1882.
*Corresponding author; email:
zaidiisa@ukm.edu.my
|
|||
