Abstract
We discuss stationary AR and ARMA time series models for sequences of integer-valued random variables and continuous random variables. Stationary distribution of these models is non-Gaussian. Such models can be broadly described as extensions of Gaussian ARMA models, which have been very widely discussed in the time series literature. These non-Gaussian AR models share two important properties with a linear AR(1) model: (i) the conditional expectation of \(X_t\) is a linear function of the past observation and (ii) the auto-correlation function (ACF) has an exponential decay. However, the conditional variance of an observation is frequently a function of the past observations. These models are formed so as to have a specific form of the stationary distribution. Stationary distributions include standard discrete distributions such as binomial, geometric, Poisson, and continuous distributions such as exponential, Weibull, gamma, inverse Gaussian, and Cauchy. In some cases, maximum likelihood estimation is tractable. In other cases, regularity conditions are not met. Estimation is then carried out based on properties of the marginal distribution of the process and mixing properties such as strong or \(\phi \)-mixing are useful to derive properties of the estimators.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abraham, B., Balakrishna, N.: Inverse gaussian autoregressive models. J. Time Ser. Anal. 20, 605–618 (1999)
Adke, S.R., Balakrishna, N.: Estimation of the mean in some stationary Markov sequences. Commun. Stat. Theor. Methods 21, 137–160 (1992)
Al-Osh, M.A., Alzaid, A.A.: First order integer valued auto-regressive (INAR(1)) process. J. Time Ser. Anal. 8, 261–275 (1987)
Al-Osh, M.A., Alzaid, A.A.: Integer valued moving average (INMA) process. Statistical Hefte 29, 281–300 (1988)
Al-Osh, M.A., Alzaid, A.A.: Binomial auto-regressive moving average models. Commun. Stat. Stoch. Model 7, 261–282 (1991)
Al-Osh, M.A., Alzaid, A.A.: First order auto-regressive time series with negative binomial and geometric marginals. Commun. Stat. Theor. Methods 21, 2483–2492 (1992)
Alzaid, A.A., Al-Osh, M.A.: An integer-valued p-th order auto-regressive structure(INAR(p)) process. J. Appl. Probab. 27, 314–324 (1990)
Arnold, B.C., Hallett, J.T.: A characterization of the pareto process among stationary stochastic processes of the form \(X_n= min(X_{n-1}, Y_n)\). Stat. Probab. Lett. 8, 377–380 (1989)
Athreya, K.B., Pantula, G.S.: Mixing properties of harris chains and auto-regressive processes. J. Appl. Probab. 23, 880–892 (1986a)
Athreya, K.B., Pantula, G.S.: A note on strong mixing ARMA processes. Stat. Probab. Lett. 4, 187–190 (1986b)
Balakrishna, N., Jacob, T.M.: Parameter estimation in minification processes. Commun. Stat. Theor. Methods. 32, 2139–2152 (2003)
Balakrishna, N., Lawrence, A.J.: Development of product autoregressive models. J. Indian Stat. Assoc. 50, 1–22 (2012)
Balakrishna, N., Nampoothiri, K.: A cauchy auto-regressive model and its applications. J. Indian Stat. Assoc. 41, 143–156 (2003)
Balakrishna, N., Shiji, K.: A markovian weibull sequence generated by product autoregressive model and its statistical analysis. J. Indian Soc. Probab. Stat. 12, 53–67 (2010)
Benjamin, M., Rigby, R., Stasinopoulos, M.: Generalized autoregressive moving average models. J. Am. Stat. Assoc. 98, 214–223 (2003)
Berchtold, A., Raftery, A.E.: Mixture transition distribution model for high-order markov chains and non-gaussian time series. Stat. Sci. 17, 328–356 (2002)
Block, H.W., Langberg, N.A., Stoffer, D.S.: Time series models for non-gaussian processes, In: Topics in Statistical Dependence, Lecture Notes-Monograph Series, vol. 16, pp. 69–83. Institute of Mathematical, Statistics, Hayward (1990).
Brockwell, P.J., Davis, R.A.: Time Series: Theory and Methods. Springer, New York (1987)
Cappé, O., Moulines, E., Ryden, T.: Inference in Hidden Markov Models. Springer, New York (2005)
Drost, F.C., van den Akker, R., Werker, B.J.M.: Efficient estimation of auto-regressive parameters and innovation distribution for semi-parametric integer-valued AR(p) processes. J. Roy. Stat. Soc.: Ser. B, 71, 467–485 (2009).
Du, J.D., Li, Y.: The integer-valued auto-regressive (INAR(p)) model. J. Time Ser. Anal. 12, 129–142 (2001)
Elliot, R.J., Aggaoun, L., Moore, J.B.: Hidden Markov Models: Estimation and Control. Springer, New York (1995)
Fahrmeir, L., Tutz, G.: Multivariate statistical modeling based on generalized linear models. Springer, New York (2004)
Feigin, P.D., Resnick, S.I.: Estimation of autoregressive processes with positive innovation. Commun. Stat. Stoch. Models 8, 479–498 (1992)
Gaver, D.P., Lewis, P.A.W.: First-order autoregressive gamma sequences and point processes. Adv. Appl. Probab. 12, 727–745 (1980)
Jacobs, P.A., Lewis, P.A.W.: A mixed auto-regressive-moving-average exponential sequence and point process (EARMA(1,1)). Adv. Appl. Probab. 9, 87–104 (1977)
Jacobs, P.A., Lewis, P. A.W.: Discrete time series generated by mixtures I: correlational and run properties. J. Roy. Stat. Soc.: Ser. B, 40, 94–105 (1978a).
Jacobs, P.A., Lewis, P.A.W.: Discrete time series generated by mixtures II: asymptotic properties. J. Roy. Statist. Soc.: Ser. B, 40, 222–228 (1978b).
Jacobs, P.A., Lewis, P.A.W.: Stationary discrete auto-regressive-moving average time series generated by mixtures. J. Time Ser. Anal. 4, 19–36 (1983)
Lewis, P.A.W., McKenzie, E.D.: Minification processes and their transformations. J. Appl. Probab. 28, 45–57 (1991)
MacDonald, I., Zucchini, W.: Hidden Markov and Other Models for Discrete Valued Time Series. Chapman and Hall, London (1997)
McCabe, B.P.M., Martin, G.M., Harris, D.: Efficient probabilistic forecasts for counts. J. Roy. Stat. Soc.: Ser. B 73, 239–252 (2011).
McKenzie, E.: Some simple models for discrete variate time series. Water Res. Bull. 21, 645–650 (1985)
McKenzie, E.: ARMA processes with negative binomial and geometric marginals. Adv. Appl. Probab. 18, 679–705 (1986)
McKenzie, E.: Some ARMA models for dependent sequences of poisson counts. Adv. Appl. Probab. 20, 822–835 (1988)
McKenzie, E.: Discrete variate time series. In: Shanbhag, D.N., Rao, C.R. (eds.) Stochastic Processes: Modeling and Simulation Handbook of Statistics, vol. 21, pp. 573–606. North-Holland, Amsterdam (2003)
Pillai, R.N., Satheesh, S.: \(\alpha \)-inverse gaussian distributions. sankhyā A. 54, 288–290 (1992).
Raftery, A.E., Tavare, S.: Estimating and modeling repeated patterns in high order markov chains with mixture transition distribution model. Appl. Stat. 43, 179–199 (1994)
Rajarshi, M.B.: Chi-squared type goodness of fit tests for stochastic models through conditional least squared estimation. J. Ind. Statist. Assoc. 24, 65–76 (1987)
Tavares, L.V.: An exponential markovian stationary processes. J. Appl. Probab. 17, 1117–1120 (1980), Addendum. J. Appl. Probab. 18, 957 (1980)
Weiß, C.H: A new class of autoregressive models for time series of binomial counts. Commun. Stat. Theor. Methods 38, 447–460 (2009).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 The Author(s)
About this chapter
Cite this chapter
Rajarshi, M.B. (2013). Non-Gaussian ARMA Models. In: Statistical Inference for Discrete Time Stochastic Processes. SpringerBriefs in Statistics. Springer, India. https://doi.org/10.1007/978-81-322-0763-4_3
Download citation
DOI: https://doi.org/10.1007/978-81-322-0763-4_3
Published:
Publisher Name: Springer, India
Print ISBN: 978-81-322-0762-7
Online ISBN: 978-81-322-0763-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)