High-Order Self-excited Threshold Integer-Valued Autoregressive Model: Estimation and Testing

Abstract

Motivated by the need of modeling and inference for high-order integer-valued threshold time series models, this paper introduces a pth-order two-regime self-excited threshold integer-valued autoregressive (SETINAR(2, p)) model. Basic probabilistic and statistical properties of the model are discussed. The parameter estimation problem is addressed by means of conditional least squares and conditional maximum likelihood methods. The asymptotic properties of the estimators, including the threshold parameter, are obtained. A method to test the nonlinearity of the underlying process is provided. Some simulation studies are conducted to show the performances of the proposed methods. Finally, an application to the number of people suffering from meningococcal disease in Germany is provided.

Keywords

Integer-valued time series / SETINAR(2 /  p) process / Threshold autoregressive model / Nonlinearity test

References

[1] Al-Osh MA, Alzaid AA. First-order integer-valued autoregressive (INAR(1)) process. J. Time Ser. Anal.. 1987, 8 261-275

[2] Billingsley P. Statistical Inference for Markov Processes. 1961 Chicago: The University of Chicago Press

[3] Chen CWS, Lee S. Bayesian causality test for integer-valued time series models with applications to climate and crime data. J. R. Stat. Soc. Ser. C. 2017, 66 797-814

[4] Davis RA, Fokianos K, Holan SH, Joe H, Livsey J, Lund R, Pipiras V, Ravishanker N. Count time series: a methodological review. J. Am. Stat. Assoc.. 2021, 116 1533-1547

[5] Doukhan P, Latour A, Oraichi D. A simple integer-valued bilinear time series model. Adv. Appl. Probab.. 2006, 38 559-578

[6] Du JG, Li Y. The integer-valued autoregressive (INAR($p$)) model. J. Time Ser. Anal.. 1991, 12 129-142

[7] Franke, J., Seligmann, T.: Conditional Maximum Likelihood Estimates for INAR(1) Processes and their Application to Modeling Epileptic Seizure Counts. In: SubbaRao, T. (ed.) Developments in Time Series Analysis. pp. 310–330 (1993)

[8] Ferland R, Latour A, Oraichi D. Integer-valued GARCH process. J. Time Ser. Anal.. 2006, 27 923-942

[9] Fokianos K, Rahbek A, Tjøstheim D. Poisson autoregression. J. Am. Stat. Assoc.. 2009, 104 1430-1439

[10] Hall A, Scotto MG, Cruz JP. Extremes of integer-valued moving average sequences. TEST. 2010, 19 359-374

[11] Jung RC, Kukuk M, Liesenfeld R. Time series of count data: modelling and estimation and diagnostics. Comput. Stat. Data Anal.. 2006, 51 2350-2364

[12] Klimko LA, Nelson PI. On conditional least squares estimation for stochastic processes. Ann. Stat.. 1978, 6 629-42

[13] Latour A. Existence and stochastic structure of a non-negative integer-valued autoregressive process. J. Time Ser. Anal.. 1998, 19 439-455

[14] Li H, Yang K, Wang D. Quasi-likelihood inference for self-exciting threshold integer-valued autoregressive processes. Comput. Stat.. 2017, 32 1597-1620

[15] Li H, Yang K, Zhao S, Wang D. First-order random coefficients integer-valued threshold autoregressive processes. AStA-Adv. Stat. Anal.. 2018, 102 305-331

[16] Liu M, Li Q, Zhu F. Self-excited hysteretic negative binomial autoregression. AStA Adv. Stat. Anal.. 2020, 104 385-415

[17] Monteiro M, Scotto MG, Pereira I. Integer-valued self-exciting threshold autoregressive processes. Commun. Stat. Theory Methods. 2012, 140 2717-2737

[18] Möller TA, Silva ME, Weiß CH, Scotto MG, Pereira I. Self-exciting threshold binomial autoregressive processes. AStA Adv. Stat. Anal.. 2016, 100 369-400

[19] Pedeli X, Davison AC, Fokianos K. Likelihood estimation for the INAR($p$) model by saddlepoint approximation. J. Am. Stat. Assoc.. 2015, 110 1229-1238

[20] Scotto MG, Weiß CH, Gouveia S. Thinning-based models in the analysis of integer-valued time series: a review. Stat. Model.. 2015, 15 590-618

[21] Thyregod P, Carstensen J, Madsen H. Integer valued autoregressive models for tipping bucket rainfall measurements. Environmetrics. 1999, 10 395-411

[22] Tong H, Lim KS. Threshold autoregression, limit cycles and cyclical data. J. Roy. Stat. Soc. B. 1980, 42 245-292

[23] Wang ZK. Stochastic Process. 1982 Beijing: Scientific Press

[24] Wang C, Liu H, Yao J, Davis RA, Li WK. Self-excited threshold Poisson autoregression. J. Am. Stat. Assoc.. 2014, 109 776-787

[25] Wang X, Wang D, Yang K, Xu D. Estimation and testing for the integer-valued threshold autoregressive models based on negative binomial thinning. Commun. Stat. Simul. Comput.. 2021, 50 1622-1644

[26] Weiß CH. Thinning operations for modeling time series of counts: a survey. AStA Adv. Stat. Anal.. 2008, 92 319-343

[27] Yang K, Li H, Wang D. Estimation of parameters in the self-exciting threshold autoregressive processes for nonlinear time series of counts. Appl. Math. Model.. 2018, 57 226-247

[28] Yang K, Wang D, Jia B, Li H. An integer-valued threshold autoregressive process based on negative binomial thinning. Stat. Pap.. 2018, 59 1131-1160

[29] Yang K, Li H, Wang D, Zhang C. Random coefficients integer-valued threshold autoregressive processes driven by logistic regression. AStA-Adv. Stat. Anal.. 2021, 105 533-557

[30] Yang K, Yu X, Zhang Q, Dong X. On MCMC sampling in self-exciting integer-valued threshold time series models. Comput. Stat. Data Anal.. 2022

Funding

National Natural Science Foundation of China(11901053)

Natural Science Foundation of Jilin Province(20210101149)

Scientific Research Project of Jilin Provincial Department of Education(JJKH20220671KJ)