High-order self-excited multiple thresholds generalized integer-valued autoregressive model

Year 2025, Volume: 54 Issue: 5, 1905 - 1934, 29.10.2025

Mohamed Sadoun

https://doi.org/10.15672/hujms.1650968

Abstract

This work proposes an integer threshold autoregressive model with multiple regimes $\left( K\geq2\right)$, based on a generalized thinning operator (hereafter referred to as $SET-GINAR\left( K;p\right)$). This model will be useful for analyzing the number of certain arrivals in a fixed time interval with non-linear behavior. First, we study the probabilistic structure of our model through the stationarity issue and the moments structure. Second, we provide two statistical inference procedures, namely two estimation methods including the conditional least squares and the conditional maximum likelihood. In addition, the asymptotic properties of the estimators, including consistency and normality, are established. Finally, the performance of the obtained inference procedures will be evaluated through an intensive simulation study and application on real data.

Keywords

Conditional least squares estimator , conditional maximum likelihood estimator , count integer-valued process , nonlinearity time series , $SET-GINAR\left( K;p\right)$ model

References

• [1] M. Al-Osh and A.A. Alzaid, First order integer-valued autoregressive (INAR(1)) processes, J. Time Ser. Anal. 8, 261 − 275, 1987.
• [2] S. Bendjeddou and M. Sadoun, Non-parametric estimation for locally stationary integer-valued processes, Commun. Stat. Simul. Comput. 54 (1), 283 − 301, 2025.
• [3] M. Bentarzi and M. Sadoun, Efficient estimation in semiparametric self-exciting threshold INAR processes, Commun. Stat. Simul. Comput. 52 (6), 2592 − 2614, 2021.
• [4] M.L. Diop and W. Kengne, Testing parameter change in general integer-valued time series, J. Time Ser. Anal. 38 (6), 880-894, 2017.
• [5] P. Doukhan, A. Latour and D. Oraichi, A simple integer-valued bilinear time series model, Adv. Appl. Probab. 38 (2), 559 − 578, 2006.
• [6] C. Drost, R. van den Akker and B. Werker, Local asymptotic normality and efficient estimation for INAR(p) models, J. Time Ser. Anal. 29, 783 − 801, 2008
• [7] C. Drost, R. van den Akker and B. Werker, Efficient estimation of auto-regression parameters and innovation distributions for semiparametric integer-valued AR(p) models, J. R. Stat. Soc. B 71 (2), 467 − 485, 2009.
• [8] J.G. Du and Y. Li, The integer-valued autoregressive (INAR(p)) model, J. Time Ser. Anal. 12 (2), 129 − 142, 1991.
• [9] Š. Hudecová, Structural changes in autoregressive models for binary time series, J. Stat. Plan. Inference 143, 1744 − 1752, 2013.
• [10] A.S. Kashikar, N. Rohan and T.V. Ramanathan, Integer autoregressive models with structural breaks, J. Appl. Stat. 40 (12), 2653 − 2669, 2013.
• [11] Y. Kang, D. Sheng and J. Yue, Threshold integer-valued autoregressive model with serially dependent innovation, J. Stat. Comput. Simul. 94 (17), 38263863, 2024.
• [12] A. Klimko and P.I. Nelson, On conditional least squares estimation in stochastic processes, Ann. Stat. 6 (3), 629 − 642, 1978.
• [13] A. Latour, The multivariate GINAR(p) process, Adv. Appl. Probab. 29, 228 − 248, 1997.
• [14] A. Latour, Existence and stochastic structure of a non-negative integer-valued autoregressive process, J. Time Ser. Anal. 19, 439 − 455, 1998.
• [15] D. Li and H. Tong, Nested sub-sample search algorithm for estimation of threshold models, Stat. Sin. 26, 1543 − 1554, 2016.
• [16] M. Monteiro, M.G. Scotto and I. Pereira, Integer-valued self-exciting threshold autoregressive process, Commun. Stat. Theory Methods 41, 2717 − 2737, 2012.
• [17] A.S. Nastić and M.M. Ristić, Some geometric mixed integer-valued autoregressive (INAR) models, Stat. Probab. Lett. 82, 805 − 811, 2012.
• [18] M. Sadoun, Locally asymptotically efficient estimation and testing in periodic integervalued time series models: parametric and semi-parametric cases, Thesis, USTHB, 2020.
• [19] M. Sadoun and M. Bentarzi, Locally asymptotically efficient estimation for parametric PINAR(p) models, Stat. Neerl. 75 (3), 257 − 289, 2021.
• [20] M. Sadoun and M. Bentarzi, Local asymptotic normality and optimal estimation for self-excited threshold generalized INAR(p) models, J. Korean Stat. Soc. 1 − 46, 2025.
• [21] D. Sheng, C. Liu and Y. Kang, Change-point analysis for binomial autoregressive model with application to price stability counts, J. Comput. Appl. Math. 451, 116079, 2024.
• [22] P. Thyregod, J. Carstensen, H. Madsen and K. Arnbjerg-Nielsen, Integer valued autoregressive models for tipping bucket rainfall measurements, Environmetrics. 10, 395 − 411, 1999.
• [23] R.S. Tsay, Testing and modeling threshold autoregressive processes, J. Am. Stat. Assoc. 84, 231 − 240, 1989.
• [24] C. Wang, H. Liu, J. F. Yao, R.A. Davis and W.K. Li, Self-excited threshold poisson autoregression, J. Am. Stat. Assoc. 109 (506), 777 − 787, 2014.
• [25] X. Wang, D. Wang, K. Yang and D. Xu, Estimation and testing for the integer-valued threshold autoregressive models based on negative binomial thinning, Commun. Stat. Simul. Comput. 50 (6), 1622 − 1644, 2019.
• [26] K.Yang, D. Wang and H. Li, An integer-valued threshold autoregressive process based on negative binomial thinning, Stat. Pap. 59 (3), 1131 − 1160, 2018.
• [27] K.Yang, D. Wang and H. Li, Threshold autoregression analysis for finite range time series of counts with an application on measles data, J. Stat. Comput. Simul. 88, 597 − 614, 2018.
• [28] K.Yang, A. Li, H. Li and X. Dong, High-order self-excited threshold integer-valued autoregressive model: estimation and testing, Commun. Math. Stat. 13 (1), 233−260, 2022.
• [29] C. Zhang, D. Wang, K. Yang, H. Li and X. Wang, Generalized Poisson integer-valued autoregressive processes with structural changes, J. Appl. Stat. 49 (11), 2717 − 2739, 2022.