Kybernetika 53 no. 6, 985-991, 2017

On random processes as an implicit solution of equations

Petr LachoutDOI: 10.14736/kyb-2017-6-0985

Abstract:

Random processes with convenient properties are often employed to model observed data, particularly, coming from economy and finance. We will focus our interest in random processes given implicitly as a solution of a functional equation. For example, random processes AR, ARMA, ARCH, GARCH are belonging in this wide class. Their common feature can be expressed by requirement that stated random process together with incoming innovations must fulfill a functional equation. Functional dependence is linear for AR, ARMA. We consider a general functional dependence, but, existence of a forward and a backward equivalent rewritings of the given functional equation is required. We present a concept of solution construction giving uniqueness of assigned solution. We introduce a class of implicit models where forward and backward equivalent rewritings exist. Illustrative examples are included.

Keywords:

econometric models, ARMA process, implicit definition

Classification:

62M10, 91B70

References:

  1. G. E. P. Box and G. M. Jenkins: Time-series Analysis Forecasting and Control. Holden-Day, San Francisco 1976.   CrossRef
  2. P. J. Brockwell and R. A. Davis: Time-series: Theory and Methods. Springer-Verlag, New York 1987.   DOI:10.1007/978-1-4899-0004-3
  3. J. Durbin and S. J. Koopman: Time Series Analysis by State Space Models. Oxford University Press, Oxford 2001.   CrossRef
  4. C. Hommes: Financial markets as nonlinear adaptive evolutionary systems. Quantitative Finance 1 (2001), 1, 149-167.   DOI:10.1088/1469-7688/1/1/311
  5. P. Lachout: On functional definition of time-series models. In: Proc. 32th International Conference on Mathematical Methods in Economics, Olomouc (J. Talašová, J. Stoklasa and T. Talášek, eds.), Palacký University, Olomouc 2014, pp. 560-565.   CrossRef
  6. P. Lachout: Discussion on implicit econometric models. In: Proc. 34th International Conference on Mathematical Methods in Economics, (A. Kocourek and M. Vavroušek, eds.), Technical University of Liberec 2016, pp. 501-505.   CrossRef
  7. H.-E. Liao and W. A. Sethares: Suboptimal identification of nonlinear ARMA models using an orthogonality approach. IEEE Trans. Circuits and Systems 42 (1995), 1, 14-22.   DOI:10.1109/81.350792
  8. J. Liu and K. Susko: On strict stationarity and ergodicity of a non-linear ARMA model. J. Appl. Probab. 29 (1992), 2, 363-373.   DOI:10.1017/s0021900200043114
  9. E. Masry and D. Tjøstheim: Nonparametric estimation and identification of nonlinear ARCH time-series. Econometr. Theory 11 (1995), 1, 258-289.   DOI:10.1017/s0266466600009166
  10. M. B. Priestley: Non-Linear and Non-Stationary time-series. Academic Press, London 1988.   CrossRef
  11. R. H. Shumway and D. S. Stoffer: Time Series Analysis and Its Applications - With R Examples. EZ Green Edition, 2015.   CrossRef