Lee S. Dewald
ABSTRACT
In many practical cases in time series analysis, marginal distributions in stationary situations are not Gaussian. It is therefore necessary to be able to generate and analyze non-Gaussian time series. Several non-Gaussian time series models are discussed in this paper. The marginal distributions are Laplace or l-Laplace distributions, and the correlation structure of the processes mimics that of the standard additive, linear, constant coefficient ARMA(p,q) models.
- DewaId, L.S. and Lewis, P.A.W. (1985). A New Laplace Second-Order Autoregressive Time Series Model- NLAR(2). IEEE Transactions on Information Theory, Vol. IT-31, 645- 652.Google Scholar
Cross Ref
- Gastwirth, J.L. and Wolff, S.S, (1965). A Characterization of the Laplace Distribution. John Hopkins University Department of Statistics Report ~8.Google Scholar
- Gujar, V. G. and Kavanagh, R. J. Generation of random signals with specified probability density functions and power density spectra, fEEE Transactions on Automatic Control. Vol. AC-13, 716-719.Google Scholar
- Haddad, A.H. and Valis~lo, P.E. (1970). Generation of random time series through hybrid computation. In: Proceedings Sixth International Hybrid Computation Meetings, 193-200.Google Scholar
- Hsu, D.A. (1979). Long-tailed distributions for position errors in navigation. Journal of the Royal Statistical Society, C, Vol. 28, 62-72.Google Scholar
- Hugus, D.K. (1982). Extensions of some models for positivevalued time series. Ph.D. Thesis, Naval Postgraduate School, Monterey, CA.Google Scholar
- Lawrance, A.J. and Lewis, P.A.W. (1981). A new autoregressive time series model in exponential variables (NEAR(l)), Advances in Applied Probability, Vol. 13, 826-845.Google ScholarCross Ref
- Lawrance, A.J. and Lewis, P.A.W. (1985). Modelling and residual analysis of nonlinear autoregressive time series in exponential variables, Journal of the Royal Statistical Society, Yol. B47~ 165-202.Google Scholar
- Lawrance, A.J. and Lewis, P.A.W. (1987). Higher-Order residual analysis for nonlinear time series with autoregressive correlation structures. International S~atisfical Review, Vol. 55, 1, 21-35.Google Scholar
- Lewis, P.A.W. (1981). Simple multivariate time series for simulation of complex systems. In: Proceedings Winter Simulation Conference, Ed. T. T. Ores, C. M. Delfosse and C. M. Shub. New York: IEEE Press, 389-390. Google ScholarDigital Library
- Lewis, P.A.W., McKenzie, E., and Hugus, D.K. (1986). Gamma processes. Naval Postgraduate School Technical Report NPS- 55-86-002. Submitted for publication.Google Scholar
- Li, S.T. and Hammond, J.L. (1975). Generation of pseudorandom numbers with specified univariate distributions and correlation coefficients. {EEE Transactions on Systems, Man, Cyberneties~ Vol. SMC-5, 557-561.Google Scholar
- Liu, B. and Munson, D.C. (1982). Generation of random sequence having a jointly specified marginal distribution and autocovariance. IEEE Transactions on Acoustics and Speech, Signal Processing. Vol. ASSP-30, 973-983.Google Scholar
- Mallows, C. (1967). Linear processes are nearly Gaussian. Journal o/Applied Probability, Vol. lO, 181-189.Google Scholar
- McKenzie, E. (1985). An autoregressive process for beta random variables. Management Science, "Vol. 31, 8, 988-997.Google Scholar
- Nicholls, D.F. and Quinn, B.G. (1982). Random coefficient autoregressive models: an introduction. Springer verlag, Berlin.Google Scholar
- Sondhi, M.M. (1983). Random processes with specified spectral density and first-order probability density. Bell System Technical Journal, Vol. 62~ no. 3, 679-701.Google ScholarCross Ref
Index Terms
- Marginally specific alternatives to normal ARMA processes
Recommendations
The beta generalized half-normal distribution
For the first time, we propose the so-called beta generalized half-normal distribution, which contains some important distributions as special cases, such as the half-normal and generalized half-normal (Cooray and Ananda, 2008) distributions. We derive ...
EM-estimation and modeling of heavy-tailed processes with the multivariate normal inverse Gaussian distribution
The heavy-tailed multivariate normal inverse Gaussian (MNIG) distribution is a recent variance-mean mixture of a multivariate Gaussian with a univariate inverse Gaussian distribution. Due to the complexity of the likelihood function, parameter ...
Empirical Study Based on ARMA-GARCH Tempered Stable Lévy Processes: Evidence from Chinese Financial Markets
ICMECG '12: Proceedings of the 2012 International Conference on Management of e-Commerce and e-GovernmentThis paper develops the ARMA-GARCH model and obtain the historical filtered noise sequence based on time series analysis of Shanghai Composite Index (SHI). Then, it estimates the parameters of noise using method of moments estimation and simulates TS ...
Comments