{"title":"System Identification Based on Stepwise Regression for Dynamic Market Representation","authors":"Alexander Efremov","volume":40,"journal":"International Journal of Computer and Information Engineering","pagesStart":796,"pagesEnd":802,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/7439","abstract":"A system for market identification (SMI) is presented.\r\nThe resulting representations are multivariable dynamic demand\r\nmodels. The market specifics are analyzed. Appropriate models and\r\nidentification techniques are chosen. Multivariate static and dynamic\r\nmodels are used to represent the market behavior. The steps of the\r\nfirst stage of SMI, named data preprocessing, are mentioned. Next,\r\nthe second stage, which is the model estimation, is considered in more\r\ndetails. Stepwise linear regression (SWR) is used to determine the\r\nsignificant cross-effects and the orders of the model polynomials. The\r\nestimates of the model parameters are obtained by a numerically stable\r\nestimator. Real market data is used to analyze SMI performance.\r\nThe main conclusion is related to the applicability of multivariate\r\ndynamic models for representation of market systems.","references":"[1] P. Deschamps, Exact Small-Sample Inference in Stationary, Fully Regular,\r\nDynamic Demand Models. Journal of Econometrics, Volume 97, pp.\r\n51-91, 2000.\r\n[2] J. Gonzalo and O. Martinez, Large shocks vs. small shocks. (or does\r\nsize matter? May be so.). Journal of Econometrics, Volume 135, pp.\r\n311-347, 2006.\r\n[3] J. W. Hamister and N. C. Suresh, The impact of pricing policy on sales\r\nvariability in a supermarket retail context. Int. J. Production Economics,\r\n2007.\r\n[4] D. Hanssens and L. Parsons, Handbooks in Operations Research and\r\nManagement Science, Volume 5, J. Eliasberg and G. Lilien, Eds. Elsevier\r\nScience Publishers, 1993.\r\n[5] S. D. Fassois, MIMO LMS-ARMAX identification of vibrating structures\r\npart I: the method. Mechanical Systems and Signal Processing, Volume\r\n15, No 4, pp. 723-735, 2001.\r\n[6] M. Leskensa, L. B. M. Van Kessela and P. M. J. Van den Hof, MIMO\r\nclosed-loop identification of an MSW incinerator. Control Engineering\r\nPractice, Volume 10, pp. 315-326, 2002.\r\n[7] H. Chen, D. Levy, S. Ray and M. Bergen, Asymmetric Price Adjustment\r\nin the Small, Journal of Monetary Economics, Volume 55, pp. 728-737,\r\n2008.\r\n[8] W. H. Press, S. A. Teukolsky, W. T. Vetterling and B. P. Flannery,\r\nNumerical Recipes. The Art of Scientific Computing Third Edition,\r\nCambridge University Press, 2007.\r\n[9] J. O. Rawlings, S. G. Pantula, D. A. Dickey, Applied Regression Analysis:\r\nA Research Tool, Second Edition. Springer-Verlag New York, Inc., 1998.\r\n[10] F. Ridder, R. Pintelon, J. Schoukens and D. P. Gillikin, Modified AIC\r\nand MDL model selection criteria for short data records. IEEE Trans.\r\non Instrumentation and Measurement, Volume 54, No 1, pp. 144-150,\r\n2005.\r\n[11] L. Ljung, System Identification Toolbox. For Use with Matlab. User-s\r\nGuide. The MathWorks, Inc, MA, USA, 2004.\r\n[12] P. Gr\u252c\u00bfunwald, The Minimum Description Length Principle. MIT Press,\r\nJune 2007.\r\n[13] E. Garipov, System Identification. Part II - Identification by Discrete\r\nStochastic Regression Models. Technical University of Sofia, 2004.\r\n[14] M. Verhaegen and V. Verdult, Filtering and System Identification. A\r\nLeast Squares Approach. Cambridge University Press, 2007.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 40, 2010"}