Examining stylized facts and trends of FTSE/JSE TOP40: a parametric and Non-Parametric approach

Katleho Makatjane; Ntebogang Moroke; Katleho Makatjane; Ntebogang Moroke

doi:10.3934/DSFE.2022015

Data Science in Finance and Economics

2022, Volume 2, Issue 3: 294-320. doi: 10.3934/DSFE.2022015

Previous Article Next Article

Research article

Examining stylized facts and trends of FTSE/JSE TOP40: a parametric and Non-Parametric approach

Katleho Makatjane ^{1
,
,},
Ntebogang Moroke ²

1.
Department of Statistics, University of Botswana, Private Bag UB 0022, Gaborone, Botswana
2.
Department of Statistics and Operations Research, North-West University, Private Bag X2046, Mmabatho, Republic of South Africa

Received: 10 July 2022 Revised: 03 August 2022 Accepted: 09 August 2022 Published: 07 September 2022
JEL Codes: C24, D53, E32, E44

It is critical in risk and portfolio management to identify groups or classes of financial returns. Portfolio diversification is one of the first decisions made during the portfolio construction phase, and it entails allocating assets among various asset class groups to maximize the risk/reward trade-off. Therefore, this research provides a detailed examination of empirical analysis concerning the characterization of financial markets. In this study, we use parametric and non-parametric approaches to look at stylized facts and patterns of the FTSE/JSE Top40, which comprises the top 40 holdings companies in the South African financial market. To the best of our knowledge, this is the first time a model of this type has been used to create a map that characterizes this index. Our findings indicated that the majority of the properties of the data were valid including among others, clustering volatility, monthly seasonal effects and significant autocorrelation (or serial correlation) on logarithmic returns. Moreover, we found that intra-week trend effects exist, whereas the weekend effect has practically vanished in the FTSE/JSE Top40. With regard to the transition probabilities of the MS(2)-GJR-GARCH (1,1) model, the FTSE/JSE Top40 index had a 98.8% chance of exhibiting long memory, while the volatility had a 99.6% chance of exhibiting long memory.
- anomalies,
- Fat-Tail,
- markov-switching,
- seasonality,
- South Africa,
- volatility clustering
Citation: Katleho Makatjane, Ntebogang Moroke. Examining stylized facts and trends of FTSE/JSE TOP40: a parametric and Non-Parametric approach[J]. Data Science in Finance and Economics, 2022, 2(3): 294-320. doi: 10.3934/DSFE.2022015

Related Papers:

Abstract

It is critical in risk and portfolio management to identify groups or classes of financial returns. Portfolio diversification is one of the first decisions made during the portfolio construction phase, and it entails allocating assets among various asset class groups to maximize the risk/reward trade-off. Therefore, this research provides a detailed examination of empirical analysis concerning the characterization of financial markets. In this study, we use parametric and non-parametric approaches to look at stylized facts and patterns of the FTSE/JSE Top40, which comprises the top 40 holdings companies in the South African financial market. To the best of our knowledge, this is the first time a model of this type has been used to create a map that characterizes this index. Our findings indicated that the majority of the properties of the data were valid including among others, clustering volatility, monthly seasonal effects and significant autocorrelation (or serial correlation) on logarithmic returns. Moreover, we found that intra-week trend effects exist, whereas the weekend effect has practically vanished in the FTSE/JSE Top40. With regard to the transition probabilities of the MS(2)-GJR-GARCH (1,1) model, the FTSE/JSE Top40 index had a 98.8% chance of exhibiting long memory, while the volatility had a 99.6% chance of exhibiting long memory.

References

[1]	Alemohammad N, Rezakhah S, Alizadeh SH (2020) Markov-switching Asymmetric GARCH model: Stability and Forecasting. Stat Pap 61: 1309–1333. https://doi.org/10.1007/s00362-018-0992-2 doi: 10.1007/s00362-018-0992-2
[2]	Aquilina M, Budish E, O'Neill P (2021) Quantifying the High-frequency Trading "Arms Race". Q J Econ 137: 493–564. https://doi.org/10.1093/qje/qjab032 doi: 10.1093/qje/qjab032
[3]	Ardia D, Bluteau K, Boudt K, et al. (2019) Markov-switching GARCH Models in R: The MSGARCH Package. J Stat Software 91. https://dx.doi.org/10.2139/ssrn.2845809 doi: 10.2139/ssrn.2845809
[4]	Arora H (2017) Stylized Facts and Trends of High-frequency Data in Financial Markets. Asian J Res Bus Econ Manage 7: 303–317. https://doi.rog/10.5958/2249-7307.2017.00115.3 doi: 10.5958/2249-7307.2017.00115.3
[5]	Arratia A, Lopez-Barrantes AX (2021) Do Google Trends Forecast Bitcoins? Stylized Facts and Statistical Evidence. J Banking Financ Technol 5: 45–57. https://doi.org/10.1007/s42786-021-00027-4 doi: 10.1007/s42786-021-00027-4
[6]	Atsin JA, Ocran MK (2015) Calendar Effects and Market Anomalies on the Johannesburg Stock Exchange. MPRA Paper No. 87448. Munich: University Library of Munich. Available from: https://mpra.ub.uni-muenchen.de/87448/
[7]	Bariviera AF, Basgall MJ, Hasperué W (2017) Some Stylized Facts of the Bitcoin Market. Physica A 484: 82–90. https://doi.org/10.1016/j.physa.2017.04.159 doi: 10.1016/j.physa.2017.04.159
[8]	Bee M, Trapin L (2018) Estimating and Forecasting Conditional Risk Measures with Extreme Value Theory: A Review. Risks 6: 1–16. https://doi.org/10.3390/risks6020045 doi: 10.3390/risks6020045
[9]	Beytell D, The Effect of Extreme Value Distributions on Market Risk Estimation. MCom. (Financial Economics), Faculty of Finance and Economic Science: University of Johannesburg, 2016. Available from: https://ujcontent.uj.ac.za/vital/access/manager/Index?sitename=Research%20Output
[10]	Bilgili F, Ulucak R, Koçak E, et al. (2020) Does Globalization Matter for Environmental Sustainability? Empirical Investigation for Turkey by Markov Regime Switching Models. Environ Sci Pollut Res 27: 1087–1100. https://doi.org/10.1007/s11356-019-06996-w doi: 10.1007/s11356-019-06996-w
[11]	Boer PH, Munapo E, Chanza M, et al. (2019) Exchange market pressure in South Africa and Kenya: An analysis using parametric and non-parametric extreme value theory. J Econo Financ Sci 12: 1–15. https://doi.org/10.4102/jef.v12i1.202 doi: 10.4102/jef.v12i1.202
[12]	Bruce P, Bruce A, Gedeck P (2020) Practical Statistics for Data Scientists: 50+ Essential Concepts using R and Python. Second ed. O'Reilly Media. http://oreilly.com/
[13]	Cavalli F, Naimzada A, Pecora N (2017) Real and Financial Market Interactions in a Multiplier-accelerator Model: Non-linear Dynamics, Multi-stability and Stylized Facts. Chaos: An Interdiscip J Non-linear Sci 27: 103120. https://doi.org/10.1063/1.4994617 doi: 10.1063/1.4994617
[14]	Cavicchioli M (2021) Markov Switching Garch Models: Higher Order Moments, Kurtosis Measures, and Volatility Evaluation in Recessions and Pandemic. J Bus Econ Stat 1–12. https://doi.org/10.1080/07350015.2021.1974459 doi: 10.1080/07350015.2021.1974459
[15]	Chen YF, Ling XM, Liu MM, et al. (2018) Statistical Distribution of Hydraulic Conductivity of Rocks in Deep-incised Valleys, Southwest China. J Hydrol 566: 216–226. https://doi.org/10.1016/j.jhydrol.2018.09.016 doi: 10.1016/j.jhydrol.2018.09.016
[16]	Cox V (2017) Translating Statistics to Make Decisions: A Guide for the Non-statistician. New York: Apress. https://doi.org/10.1007/978-1-4842-2256-0
[17]	Da Cunha CR, Da Silva R (2020) Relevant Stylized Facts About Bitcoin: Fluctuations, First Return Probability, and Natural Phenomena. Physica A 550: 124155. https://doi.org/10.1016/j.physa.2020.124155 doi: 10.1016/j.physa.2020.124155
[18]	Dias JG, Vermunt JK, Ramos S (2015) Clustering Financial Time Series: New Insights from an Extended Hidden Markov Model. Eur J Oper Res 243: 852–864. https://doi.org/10.1016/j.ejor.2014.12.041 doi: 10.1016/j.ejor.2014.12.041
[19]	Dufreno G, Matsuki T (2021) Recent Econometric Techniques for Macroeconomic and Financial Data. Berlin Springer. https://doi.org/10.1007/978-3-030-54252-8
[20]	Duong T (2022) Ks: Kernel Density Estimation for Bivariate Data. J Stat Software. Available from: http://freebsd.yz.yamagata-u.ac.jp/pub/cran/web/packages/ks/vignettes/kde.pdf
[21]	Fama E, French K (1988) Permanent and Temporary Components of Stock Prices. J Polit Econ 96: 246–273. https://doi.org/10.1086/261535 doi: 10.1086/261535
[22]	Financial Times (2022) Coronavirus threatens India's Banking Recovery Before it Even Starts. Available from: https://www.ft.com/content/153f2922-6e15-11ea-89df-41bea055720b
[23]	Garson GD (2012) Testing Statistical Assumptions. Asheboro, NC: Stat Assoc Publishing. Available from: http://www.statisticalassociates.com/assumptions.pdf
[24]	Ha J, Kose MA, Otrok C, et al.(2020) Global Macro-financial Cycles and Spillovers. Natl Bur Econ Res. htpps://doi.org/10.3386/w26798 doi: 10.3386/w26798
[25]	Hart JD (2013) Nonparametric Smoothing and Lack-of-fit Tests, Berlin Springer. https://doi.org/10.1007/978-1-4757-2722-7
[26]	Hiebert P, Jaccard I, Schuler Y (2018) Contrasting Financial and Business Cycles: Stylized Facts and Candidate Explanations. J Financ Stab 38: 72–80. https://doi.org/10.1016/j.jfs.2018.06.002 doi: 10.1016/j.jfs.2018.06.002
[27]	Hu Y, Plonsky L (2021) Second Language Research 37: 171-184. https://doi.org/10.1177/0267658319877433
[28]	Hu AS, Parlour CA, Rajan U (2019)/ Cryptocurrencies: Stylized Facts on a New Investible Instrument. Financ Manage 48: 1049–1068. https://doi.org/10.1111/fima.12300
[29]	Jakata O, Chikobvu D (2022) Extreme Value Modelling of the Monthly South African Industrial Index (J520) Returns. Stat Optim Inf Comput 10: 383–400. https://doi.org/10.19139/soic-2310-5070-906 doi: 10.19139/soic-2310-5070-906
[30]	Jiang J (2022) Non-parametric Statistics. In Large Sample Techniques for Statistics 379–415, Springer Cham. https://doi.org/10.1007/978-3-030-91695-4_11
[31]	Jooste L (2006) Cash Flow Ratios as a Yardstick for Evaluating Financial Performance in African Businesses. Managerial Financ 32: 569-576. https://doi.org/10.1108/03074350610671566 doi: 10.1108/03074350610671566
[32]	Katahira K, Chen Y, Hashimoto G, et al. (2019) Development of an Agent-based Speculation Game for Higher Reproducibility of Financial Stylized Facts. Physica A 524: 503–518. https://doi.org/10.1016/j.physa.2019.04.157 doi: 10.1016/j.physa.2019.04.157
[33]	Katz RW (2013) Statistical methods for Non–stationary Extremes. Extremes in a changing climate. Water Science and Technology Library, 65. Dordrecht Springer. https://doi.org/10.1007/978-94-007-4479-0_2
[34]	Kim D, Shin M (2022) Volatility Models for Stylized Facts of High-Frequency Financial Data. arXiv pre-print arXiv: 2205.15808. Available from: https://doi.org/10.48550/arXiv.2205.15808
[35]	Korkpoe CH, Junior PO (2018) The Behavior of Johannesburg Stock Exchange all-share index Returns–An Asymmetric GARCH and News Impact Effects Approach. SPOUDAI J Econ Bus 68: 26–42. Available from: https://spoudai.unipi.gr/index.php/spoudai/article/view/2634.
[36]	Kufenko V, Geiger N (2017) Stylized Facts of the Business Cycle: Universal Phenomenon, or Institutionally Determined? J Bus Cycle Res 13: 165-187. https://doi.org/10.1007/s41549-017-0018-5 doi: 10.1007/s41549-017-0018-5
[37]	Ledl T (2016) Kernel Density Estimation: Theory and Application in Discriminant Analysis. Austrian J stat 33: 267–279.
[38]	Li Y, Abdel-Aty M, Yuan J, et al. (2020) Analyzing Traffic Violation Behavior at Urban Intersections: A Spatio-temporal Kernel Density Estimation Approach using Automated Enforcement System Data. Acci Anal Prev 141: 105509. https://doi.org/10.1016/j.aap.2020.105509 doi: 10.1016/j.aap.2020.105509
[39]	Liu Z, Shang P, Wang Y (2020) Characterization of Time Series Through Information Quantifiers. Chaos Solitons Fractals 132: 109565. https://doi.org/10.1016/j.chaos.2019.109565 doi: 10.1016/j.chaos.2019.109565
[40]	Maaziz M, Kharfouchi S (2018) Parameter Estimation of Markov-switching Bilinear Model using the (EM) Algorithm. J Stat Plan Inference 192: 35–44. https://doi.org/10.1016/j.jspi.2017.07.002 doi: 10.1016/j.jspi.2017.07.002
[41]	Morema K, Bonga-Bonga L (2020) The Impact of Oil and Gold Price Fluctuations on the South African Equity Market: Volatility Spillovers and Financial Policy Implications. Resour Policy 68: 101740. https://doi.org/10.1016/j.resourpol.2020.101740 doi: 10.1016/j.resourpol.2020.101740
[42]	Montgomery DC, Jennings CL, Kulahci M (2015) Introduction to Time Series Analysis and Forecasting, New Jersey: John Wiley and Sons. https://doi.org/10.2307/2938260
[43]	Nickl R, Ray K (2020) Non-parametric Statistical Inference for Drift Vector Fields of Multi-dimensional Diffusions. Ann Stat 48: 1383–1408. https://doi.org/10.1214/19-AOS1851 doi: 10.1214/19-AOS1851
[44]	Nystrup P, Madsen H, Lindstrom E (2015) Stylized Facts of Financial Time Series and Hidden Markov Models in Continuous Time. Quant Financ 15: 1531-1541. https://doi.org/10.1080/14697688.2015.1004801 doi: 10.1080/14697688.2015.1004801
[45]	Olbryś J, Oleszczak A (2020) Intra–day Patterns in Trading Volume. Evidence from High Frequency Data on the Polish Stock Market. In Saeed K, Dvorský J.(eds) Computer Information Systems and Industrial Management. CISIM 2020. Lecture Notes in Computer Science, 390–401. Springer Cham. https://doi.org/10.1007/978-3-030-47679-3_33
[46]	Orlando G, Zimatore G (2020) Business Cycle Modeling between Financial Crises and Black Swans: Ornstein–Uhlenbeck Stochastic Process versus Kaldor Deterministic Chaotic Model. Chaos Interdiscip J Nonlinear Sci 30: 083129. https://doi.org/10.1063/5.0015916 doi: 10.1063/5.0015916
[47]	Ozili P, Arun T (2020) Spillover of COVID-19: Impact on the Global Economy. University Library of Munich, Germany. Available from: https://mpra.ub.uni-muenchen.de/99850/
[48]	Patterson GA, Sornette D, Parisi DR (2020) Properties of Balanced Flows with Bottlenecks: Common Stylized Facts in Finance and Vibration-driven vehicles. Phy Rev E 101: 042302. https://doi.org/10.1103/PhysRevE.101.042302 doi: 10.1103/PhysRevE.101.042302
[49]	Phylaktis K, Manalis G (2013) Futures Trading and Market Micro–structure of the Underlying Security: A High-frequency Experiment at the Single Stock Future Level. Borsa Istanbul Rev 13: 79–92. https://doi.org/10.1016/j.bir.2013.10.012. doi: 10.1016/j.bir.2013.10.012
[50]	Porras ER (2017) Stylized Facts of Financial Markets and Bubbles. Bubbles and Contagion in Financial Markets, 2: 53–70. Palgrave Macmillan, London. https://doi.org/10.1057/978-1-137-52442-3_2
[51]	Raihan T (2017) Performance of Markov-Switching GARCH Model Forecasting Inflation Uncertainty. In Res-Report. Munich: University Library of Munich.
[52]	Restocchi V, Mcgroarty F, Gerding E (2019) The Stylized Facts of Prediction Markets: Analysis of Price Changes. Physica A 515: 159–170. https://doi.org/10.1016/j.physa.2018.09.183 doi: 10.1016/j.physa.2018.09.183
[53]	Ruppert D, Matteson D (2015) Statistics and Data Analysis for Financial Engineering: with R examples. Berlin Springer. https://doi.org/10.1007/978-1-4939-2614-5
[54]	Schmid F (2009) High-frequency Financial Markets Data Cleaning and Stylized Facts in Financial Markets Data. Paper Presentation. Cologne: Seminar of Economic and Social Sciences at the University of Cologne. Available from: https://hughchristensen.com/papers/academic_papers/High%20frequency%20data%20analysis.pdf
[55]	Shakeel M, Srivastava B (2021) Stylized Facts of High-frequency Financial Time Series data. Global Bus Rev 22: 550–564. htpps://doi.org/10.1177/0972150918811701 doi: 10.1177/0972150918811701
[56]	Strohsal T, Proaño CR, Wolters J (2019) Characterizing the Financial Cycle: Evidence from a Frequency Domain Analysis. J Bank Financ 106: 568–591. https://doi.org/10.1016/j.jbankfin.2019.06.010 doi: 10.1016/j.jbankfin.2019.06.010
[57]	Silverman BW (2018) Density Estimation for Statistics and Data Analysis, Routledge, New York. https://doi.org/10.1201/9781315140919
[58]	Sigaukea C, Rhoda MM, Maseka L (2014) Modeling Conditional Heteroscedasticity in JSE Stock Returns using the Generalized Pareto Distribution. Afr Rev Econ Financ 6: 41–55. https://www.ajol.info/index.php/aref/issue/view/11344
[59]	Statistics South Africa, Economic growth slows in 2014, 2022, Available from: statssa.gov.za/?p=4184. [Accessed on 31 May 2022].
[60]	Sullivan R, Timmermann A, White H (2001) Dangers of Data Mining: the Case of Calendar Effects in Stock Returns. J Econometrics 105: 249–286.https://doi.org/10.1016/S0304-4076(01)00077-X doi: 10.1016/S0304-4076(01)00077-X
[61]	Tsay RS (2015) Financial time series. New Jersey: John Wiley and Sons. https://doi.org/10.1002/9781118445112.stat03545.pub2
[62]	Verma JP, Abdel-Salam ASG (2019) Testing Statistical Assumptions in Research. 1 edn, John Wiley and Sonshttps://dl.uswr.ac.ir
[63]	Wang L, Ma F, Niu T, et al.(2020) Crude Oil and BRICS Stock Markets under Extreme Shocks: New Evidence. Econ Modell 86: 54–68. https://doi.org/10.1016/j.econmod.2019.06.002 doi: 10.1016/j.econmod.2019.06.002
[64]	Washington S, Karlaftis M, Mannering F, et al. (2020) Statistical and econometric methods for transportation data analysis, Chapman and Hall/CRC. https://doi.org/10.1201/9780429244018
[65]	Wulff SS (2017) Time Series Analysis: Forecasting and Control. J Qual Technol 49: 418. https://doi.org/10.1080/00224065.2017.11918006 doi: 10.1080/00224065.2017.11918006
[66]	Xaba LD, Moroke ND, Metsileng LD (2021) Performance of MS-GARCH models: Bayesian MCMC-based Estimation. Handbook of Research on Emerging Theories, Models, and Applications of Financial Econometrics 323–356. Berlin: Springer. https://doi.org/10.1007/978-3-030-54108-8_14
[67]	Xaba D, Moroke ND, Rapoo I (2019) Modeling Stock Market Returns of BRICS with a Markov-switching Dynamic Regression Model. J Econ Behav Stud 11: 10–22. https://doi.org/10.22610/jebs.v11i3(J).2865 doi: 10.22610/jebs.v11i3(J).2865
[68]	Zhai L, Wu Y, Yang J, et al. (2020) Characterizing Initiation of Gas–liquid Churn flows using Coupling Analysis of Multivariate Time Series. Physica A 540: 123099. https://doi.org/10.1016/j.physa.2019.123099 doi: 10.1016/j.physa.2019.123099
[69]	Zumbach GO, Müller U (2000) Operators on in Homogeneous Time Series. Olsen Associates Working Paper No. 324. http://dx.doi.org/10.2139/ssrn.208278

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)