Abstract
MARM (Multivariate Autoregressive Modular) processes constitute a versatile class of multidimensional stochastic sequences which can exactly fit arbitrary multi-dimensional empirical histograms and approximately fit the leading empirical autocorrelations and cross-correlations. A companion paper (Part I) presented the general theory of MARM processes. This paper (Part II) proposes practical MARM modeling and forecasting methodologies of considerable generality, suitable for implementation on a computer. The purpose of Part II is twofold: (1) to specialize the general class of MARM processes to a practical subclass, called Empirically-Based MARM (EB-MARM) processes, suitable for modeling of empirical vector-valued time series, and devise the corresponding fitting and forecasting algorithms; and (2) to illustrate the efficacy of the EB-MARM fitting and forecasting algorithms. Specifically, we shall consider MARM processes with iid step-function innovation densities and distortions based on an empirical multi-dimensional histogram, as well as empirical autocorrelation and cross-correlation functions. Finally, we illustrate the efficacy of these methodologies with an example of a three-dimension time series vector, using a software environment, called MultiArmLab, which supports MARM modeling and forecasting.
Similar content being viewed by others
References
Bazaraa MS, Sherali HD, Shetty CM (1993) Nonlinear programming: theory and applications. Wiley, New York
Jagerman DL, Melamed B (1992) The transition and autocorrelation structure of TES processes part II: special cases. Stoch Models 8(3):499–527
Jagerman DL, Melamed B (1994) The spectral structure of TES process. Stoch Models 10(3):599–618
Jelenkovic PR, Melamed B (1995a) “Automated TES modeling of compressed video”, Proceedings of IEEE INFOCOM’95. Boston, Massachusetts, pp 746–752
Jelenkovic PR, Melamed B (1995b) Algorithmic modeling of TES processes. IEEE Trans Autom Control 40(7):1305–1312
Massart P (2007) Concentration inequalities and model selection, Springer
Melamed B (1991) TES: a class of methods for generating autocorrelated uniform variates. ORSA J Comput 3(4):317–329
Melamed B (1993) An overview of TES processes and modeling methodology. In: Donatiello L, Nelson R (eds) Performance evaluation of computer and communications systems. Lecture Notes in Computer Science, Springer, pp 359–393
Melamed B (1997) The empirical TES processes methodology: modeling empirical time series. J Appl Math Stoch Anal 10(4):333–353
Melamed B (1999) ARM processes and modeling methodology. Stoch Models 15(5):903–929
Melamed B, Zhao X (2011) “MARM processes part I: general theory”, Methodology and computing in applied probability, forthcoming
Shumway RH, Stoffer DS (2007) Time series analysis and its applications: with R examples, second edition, Springer
Vapnik VN (1998) Statistical learning theory, Wiley
Yahoo (2009) http://finance.yahoo.com
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Melamed, B., Zhao, X. MARM Processes Part II: The Empirically-Based Subclass. Methodol Comput Appl Probab 15, 37–83 (2013). https://doi.org/10.1007/s11009-011-9210-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11009-011-9210-6
Keywords
- MARM processes
- Empirically-based MARM processes
- EB-MARM fitting methodology
- EB-MARM forecasting methodology