There are many studies dealt with univariate time series data, but the analysis of multivariate time series are rarely discussed. This article discusses the theoretical and numerical aspects of different techniques that analyze the multivariate time series data. These techniques are ANN, ARIMA, GLM and VARS models. All techniques are used to analyze the data that obtained from Egypt Stock Exchange Market. R program with many packages are used. These packages are the "neuralnet, nnet, forecast, MTS and vars". The process of measuring the accuracy of forecasting are investigated using the measures ME, ACF, MAE, MPE, RMSE, MASE, and MAPE. This is done for seasonal and non-seasonal time series data. Best ARIMA model with minimum error is constructed and tested. The lags order of the model are identified. Granger test for causality indicated that Exchange rate is useful for forecasting another time series. Also, the Instant test indicated that there is instantaneous causality between Exchange rate and other time series. For non-seasonal data, the NNAR() model is equivalent to ARIMA() model. Also, for seasonal data, the NNAR(p,P,0)[m] model is equivalent to an ARIMA(p,0,0)(P,0,0)[m] model. For these data, we concluded that the ANN and GLMs of fitting multivariate seasonal time series is better than multivariate non-seasonal time series. The transactions of Finance, Household and Chemicals sectors are significant for Exchange rate in non-seasonal time series case. The forecasts that based on stationary time series data are more smooth and accurate. VARS model is more accurate rather than VAR model for ARIMA (0,0,1). Forecasts of VAR values are predicted over short horizon, because the prediction over long horizon becomes unreliable or uniform.
| Published in | American Journal of Theoretical and Applied Statistics (Volume 10, Issue 1) |
| DOI | 10.11648/j.ajtas.20211001.18 |
| Page(s) | 72-88 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2021. Published by Science Publishing Group |
ANN, GLM, ARIMA, VARS, Backpropagation, RMSE, Causality Test, Instant Test
| [1] | Intrator, O. and Intrator, N. (1993). Using neural nets for interpretation of nonlinear models. Proceedings of the Statistical Computing Section, pages 244-249. San Francisco: American Statistical Society (eds). |
| [2] | Zhang, G. et al. (1998). Forecasting with artificial neural networks: The State of the Art. International Journal of Forecasting, 14, pages 35-62. |
| [3] | Al-Shawadfi, G. (2003). A comparison between neural network and Box-Jenkins Forecasting techniques with application to real data. King Saud University, King Fahd National Library Cataloging-in-Publication Data. |
| [4] | Hothorn, et al. (2005). The design and analysis of benchmark experiments. Journal of Computational and Graphical Statistics, 14 (3), pages 675-699. doi/abs/10.1198/106186005X59630. |
| [5] | LiHongHu, GuanHuaChen, G and Raymond Ming-WahChau (2006). A neural networks-based drug discovery approach and its application for designing aldose reductase inhibitors. Journal of Molecular Graphics and Modelling, 24 (4), pages 244–253. https://doi.org/10.1016/j.jmgm.2005.09.002 |
| [6] | Zou, C. and Zhou, L. (2007). QSAR study of oxazolidinone antibacterial agents using artificial neural networks. Molecular Simulation, 33 (6), pages 517–530. doi/abs/10.1080/08927020601188528. |
| [7] | Eugster M., Hothorn, T. and Leisch, F. (2008). Exploratory and inferential analysis of benchmark experiments. Technical Report Number 030, Dept. of Statistics, University of Munich. https://epub.ub.uni-muenchen.de/4134/1/tr030.pdf |
| [8] | Kose, E. (2008). Modelling of color perception of different age groups using artificial neural networks. Expert Systems with Applications, vol. 34, no. 3, pages 2129-2139. doi.org/10.1016/j.eswa.2007.02.036. |
| [9] | Alshawadfi, G. and Hagag, A. (2013). Artificial intelligence and time series analysis. The Scientific Journal of the Faculties of Commerce Sector, Al-Azhar University 10, pages 572-612. |
| [10] | Rostampour, V. et al. (2013). Using artificial neural network (ANN) technique for prediction of apple bruise damage. Austrial Journal of Crop Secience, 7 (10), pages 1442-1448. www.cropj.com/rostampour_7_10_2013_1442_1448.pdf |
| [11] | Doreswamy and Chanabasayya (2013). Performance analysis of neural network models for Oxazolines and Oxazoles derivatives descriptor dataset. International Journal of Information Sciences and Techniques, 13 (6). DOI: 10.5121/ijist.2013.3601. |
| [12] | Hanjouri, M. and Abu Qamar, A. (2018). A comparative study of the ANN and ARIMA models for predicting global sugar prices. Al-Azhar University Journal, Gaza, Public Human Series, 20, special issue A, pages 212-230. |
| [13] | Mills, C. (1990). Time series techniques for economists. Cambridge University Press. |
| [14] | Box, P. and Jenkins, M., and Reinsel, C. (1994) Time Series Analysis Forecasting and Control, 3rd edition. Prentice -Hall Inc., New Jersey. http://www.sciepub.com/reference/40199 |
| [15] | Englewood Cliffs, NJ: Prentice-Hal l, page 151. |
| [16] | Asteriou, D. and Hall, G. (2011). ARIMA models and the Box–Jenkins methodology. Applied Econometrics (2nd ed). Palgrave MacMillan. pages 265–286. doi: 10.12691/jfe-3-1-4. |
| [17] | Hyndman, R. and Athanasopoulos, G. (2015). Seasonal ARIMA models. Forecasting: principles and practice. |
| [18] | Swain, S et al. (2018). Development of an ARIMA model for monthly rainfall forecasting over Khordha District, Odisha, India. Advances in Intelligent Systems and Computing, 708, pages 325–331. doi.org/10.1007/978-981-10-8636-6_34. |
| [19] | Riedmiller, M. and Braun, H. (1993). A direct adaptive method for faster back-propagation learning: The RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks (ICNN), pages 586-591. San Francisco. |
| [20] | Murata, N., Yoshizawa, S. and Amari, S. (1994). Network information criterion - determining the number of hidden units for an artificial neural network model. IEEE Transactions on Neural Networks, 5 (6), pages 865-872. DOI: 10.1109/72.329683. |
| [21] | Riedmiller, M. (1994). Description and implementation details. Technical Report. University of Karlsruhe. |
| [22] | Anastasiadis, A., Magoulas, G. and Vrahatis, M. (2005). New globally convergent training scheme based on the resilient propagation algorithm. Neuro computing 64, pages 253-270. doi.org/10.1016/j.neucom.2004.11.016. |
| [23] | Hyndman, J. and Khandakar, Y. (2008). Automatic time series forecasting: Package "forecast" for R. Journal of Statistical Software, 27 (3), pages 1–23. doi: 10.18637/jss.v000.i00. |
| [24] | Frauke, G. and Fritsch, S. (2010). Package "neuralnet": Training of Neural Networks. The R Journal, 2 (1), pages 30-38. https://journal.r-project.org/archive/2010-1/R |
| [25] | Fritsch, S. and Guenther, F. (2019). Package "neuralnet ": Training of Neural Networks: R package, version 1.44.2. cran.r-project.org/web/packages/neuralnet/neuralnet.pdf |
| [26] | Hyndman, R. et al. (2020). Package "forecast": Forecasting functions for time series and linear models. R package, version 8.13. https://cloud.r-project.org/package=forecast |
| [27] | Ripley, B. and William Venables, W, (2021). Package "nnet": Feed-Forward Neural Networks and Multinomial Log-Linear Models. package, version 7.3-15. https://cran.r-project.org/web/packages/nnet/nnet.pdf |
| [28] | Granger, C. (1969). Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37 (3), pages 424–438. |
| [29] | Lütkepohl, H. (2005). New introduction to multiple time series analysis (3rd ed.). Berlin: Springer. pages. 41–51. ISBN 978-3-540-27752-1. |
| [30] | Makridakis, S. (1993). Accuracy measures: theoretical and practical concerns. International Journal of Forecasting. 9 (4), pages 527–529. DOI: 10.1016/0169-2070(93)90079-3. |
| [31] | Diebold, X. and Mariano, R. (1995). Comparing predictive accuracy. Journal of Business and Economic Statistics, 13 (3), pages 253–265. doi/abs/10.1080/07350015.1995.10524599 |
| [32] | Hyndman, J. and Koehler B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22 (4), pages 679-688. https://robjhyndman.com/publications/another-look |
| [33] | Franses, Ph. H. B. F. (2015). A note on the Mean Absolute Scaled Error. International Journal of Forecasting, 32, pages 20–22. doi: 10.1016/j.ijforecast.2015.03.008. |
APA Style
Ahmed Mohamed Mohamed Elsayed. (2021). Studying Changes on Stock Market Transactions Using Different Techniques for Multivariate Time Series. American Journal of Theoretical and Applied Statistics, 10(1), 72-88. https://doi.org/10.11648/j.ajtas.20211001.18
ACS Style
Ahmed Mohamed Mohamed Elsayed. Studying Changes on Stock Market Transactions Using Different Techniques for Multivariate Time Series. Am. J. Theor. Appl. Stat. 2021, 10(1), 72-88. doi: 10.11648/j.ajtas.20211001.18
AMA Style
Ahmed Mohamed Mohamed Elsayed. Studying Changes on Stock Market Transactions Using Different Techniques for Multivariate Time Series. Am J Theor Appl Stat. 2021;10(1):72-88. doi: 10.11648/j.ajtas.20211001.18
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajtas.20211001.18,
author = {Ahmed Mohamed Mohamed Elsayed},
title = {Studying Changes on Stock Market Transactions Using Different Techniques for Multivariate Time Series},
journal = {American Journal of Theoretical and Applied Statistics},
volume = {10},
number = {1},
pages = {72-88},
doi = {10.11648/j.ajtas.20211001.18},
url = {https://doi.org/10.11648/j.ajtas.20211001.18},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20211001.18},
abstract = {There are many studies dealt with univariate time series data, but the analysis of multivariate time series are rarely discussed. This article discusses the theoretical and numerical aspects of different techniques that analyze the multivariate time series data. These techniques are ANN, ARIMA, GLM and VARS models. All techniques are used to analyze the data that obtained from Egypt Stock Exchange Market. R program with many packages are used. These packages are the "neuralnet, nnet, forecast, MTS and vars". The process of measuring the accuracy of forecasting are investigated using the measures ME, ACF, MAE, MPE, RMSE, MASE, and MAPE. This is done for seasonal and non-seasonal time series data. Best ARIMA model with minimum error is constructed and tested. The lags order of the model are identified. Granger test for causality indicated that Exchange rate is useful for forecasting another time series. Also, the Instant test indicated that there is instantaneous causality between Exchange rate and other time series. For non-seasonal data, the NNAR() model is equivalent to ARIMA() model. Also, for seasonal data, the NNAR(p,P,0)[m] model is equivalent to an ARIMA(p,0,0)(P,0,0)[m] model. For these data, we concluded that the ANN and GLMs of fitting multivariate seasonal time series is better than multivariate non-seasonal time series. The transactions of Finance, Household and Chemicals sectors are significant for Exchange rate in non-seasonal time series case. The forecasts that based on stationary time series data are more smooth and accurate. VARS model is more accurate rather than VAR model for ARIMA (0,0,1). Forecasts of VAR values are predicted over short horizon, because the prediction over long horizon becomes unreliable or uniform.},
year = {2021}
}
TY - JOUR T1 - Studying Changes on Stock Market Transactions Using Different Techniques for Multivariate Time Series AU - Ahmed Mohamed Mohamed Elsayed Y1 - 2021/02/26 PY - 2021 N1 - https://doi.org/10.11648/j.ajtas.20211001.18 DO - 10.11648/j.ajtas.20211001.18 T2 - American Journal of Theoretical and Applied Statistics JF - American Journal of Theoretical and Applied Statistics JO - American Journal of Theoretical and Applied Statistics SP - 72 EP - 88 PB - Science Publishing Group SN - 2326-9006 UR - https://doi.org/10.11648/j.ajtas.20211001.18 AB - There are many studies dealt with univariate time series data, but the analysis of multivariate time series are rarely discussed. This article discusses the theoretical and numerical aspects of different techniques that analyze the multivariate time series data. These techniques are ANN, ARIMA, GLM and VARS models. All techniques are used to analyze the data that obtained from Egypt Stock Exchange Market. R program with many packages are used. These packages are the "neuralnet, nnet, forecast, MTS and vars". The process of measuring the accuracy of forecasting are investigated using the measures ME, ACF, MAE, MPE, RMSE, MASE, and MAPE. This is done for seasonal and non-seasonal time series data. Best ARIMA model with minimum error is constructed and tested. The lags order of the model are identified. Granger test for causality indicated that Exchange rate is useful for forecasting another time series. Also, the Instant test indicated that there is instantaneous causality between Exchange rate and other time series. For non-seasonal data, the NNAR() model is equivalent to ARIMA() model. Also, for seasonal data, the NNAR(p,P,0)[m] model is equivalent to an ARIMA(p,0,0)(P,0,0)[m] model. For these data, we concluded that the ANN and GLMs of fitting multivariate seasonal time series is better than multivariate non-seasonal time series. The transactions of Finance, Household and Chemicals sectors are significant for Exchange rate in non-seasonal time series case. The forecasts that based on stationary time series data are more smooth and accurate. VARS model is more accurate rather than VAR model for ARIMA (0,0,1). Forecasts of VAR values are predicted over short horizon, because the prediction over long horizon becomes unreliable or uniform. VL - 10 IS - 1 ER -
Email: