PYTHAGORAS : Jurnal Matematika dan Pendidikan Matematika
Keywords
neural network, seleksi model, time series multivariat, R^2 increment, uji Wald
Document Type
Article
Abstract
Dalam makalah ini akan dibahas tentang seleksi model neural network untuk peramalan time series multivariat melalui pendekatan statistika inferensial. Pembahasan mencakup dua kajian, yaitu kajian teoritis tentang sifat asimtotis dari penduga parameter model NN dan distribusi dari statistik uji yang digunakan, dan kajian empiris berupa penerapan teori untuk membentuk prosedur pemilihan model NN untuk peramalan time series multivariat. Prosedur yang diusulkan merupakan kombinasi dari metode forward berdasarkan pada inferensia statistik kontribusi penambahan R2 increment dan metode backward dengan uji Wald. Untuk melihat efektivitas dari prosedur digunakan data simulasi. Hasil simulasi menunjukkan bahwa prosedur seleksi model dapat secara efektif diterapkan untuk pemodelan multivariat time series.
Page Range
91-103
Issue
2
Volume
4
Digital Object Identifier (DOI)
10.21831/pg.v4i2.564
Source
https://journal.uny.ac.id/index.php/pythagoras/article/view/564
Recommended Citation
Wustqa, D. U. (2008). Seleksi Model Neural Network Menggunakan Inferensi Statistik dari R^2 Increment dan Uji Wald untuk Peramalan Time Series Multivariat. PYTHAGORAS : Jurnal Matematika dan Pendidikan Matematika, 4(2), 91-103. https://doi.org/10.21831/pg.v4i2.564
References
Anders, U., & Korn, O. 1999. Model Selection in Neural Network. Neural Networks, Vol. 12, pp. 309–323.
Brockwell, P.J. & Davis, R.A. 1996. Introducion to Time Series and Forecasting. New York: Springer Verlag.
Kaashoek, J.F. & Van Dijk, H.K. 2001. Neural Networks as Econometric Tool. Report EI 2001–05, Econometric Institute Erasmus University Rotterdam.
Kaashoek, J.F., & Van Dijk, H.K. 2002. Neural Network Pruning Applied to Real Exchange Rate Analysis. Journal of Forecasting, 21, pp. 559-577.
Ruchjana, B.N. 2002. Curve Modeling of Oil Production by Using Generalized S-TAR Model. Forum Statistika dan Komputasi, Special Edition, IPB, Bogor.
Lopuhaa H.P. & Borovkova, S. 2005. Asymptotic properties of least squares estimators in generalized STAR models. Technical report. Delft University of Technology.
Medeiros, M. C., Terasvirta, T., & Rech, G. 2006. Building Neural network for Time series: A Statistical Approach. Journal of Forecasting, Vol. 3, pp. 75-115.
Ripley, B.D. 1993. Statistical Aspects of Neural Networks, in O.E. Barndorff-Nielsen, J.L. Jensen and W.S. Kendall, eds., Networks and Chaos: Statistical and Probabilistic Aspects, Chapman & Hall.
Suhartono, Subanar & Guritno, S. 2006. Model Selection in Neural Networks by Using
Inference of R2Incremental, PCA, and SIC Criteria for Time Series Forecasting, JOURNAL OF QUANTITATIVE METHODS: Journal Devoted to The
Mathematical and Statistical Application in Various Fields, Vol. 2, No. 1, 41-57.
Suhartono, Subanar & Guritno, S. 2007. Asymptotic Normality and Model Selection in Neural Networks by Using Inference Of R2 Incremental and Wald Test for Time Series Forecasting. Part of Desertation, Presented at SEAMS Conference, Gadjah Mada University, Yogyakarta.
White, H. 1989. Learning in Artificial Neural Networks: A Statistical Perspective. Neural Computation, Vol.1, pp. 425 –464.
White, H. 1999. Asymptotic Theory for Econometricians. New York: Academic Press.
Zang G., Eddy Patuwo B., & Hu, M.Y. 1998. Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting. Vol. 14. pp. 35 – 62.