Nonlinear network autoregression. (English) Zbl 1539.62261
Summary: We study general nonlinear models for time series networks of integer and continuous-valued data. The vector of high-dimensional responses, measured on the nodes of a known network, is regressed nonlinearly on its lagged value and on lagged values of the neighboring nodes by employing a smooth link function. We study stability conditions for such multivariate process and develop quasi-maximum likelihood inference when the network dimension is increasing. In addition, we study linearity score tests by treating separately the cases of identifiable and nonidentifiable parameters. In the case of identifiability, the test statistic converges to a chi-square distribution. When the parameters are not identifiable, we develop a supremum-type test whose \(p\)-values are approximated adequately by employing a feasible bound and bootstrap methodology. Simulations and data examples support further our findings.
MSC:
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
| 62J02 | General nonlinear regression |
| 62F12 | Asymptotic properties of parametric estimators |
References:
| [1] | AHMAD, A. and FRANCQ, C. (2016). Poisson QMLE of count time series models. J. Time Series Anal. 37 291-314. Digital Object Identifier: 10.1111/jtsa.12167 Google Scholar: Lookup Link MathSciNet: MR3512959 · Zbl 1381.62244 · doi:10.1111/jtsa.12167 |
| [2] | ANDREWS, D. W. K. (1987). Consistency in nonlinear econometric models: A generic uniform law of large numbers. Econometrica 55 1465-1471. Digital Object Identifier: 10.2307/1913568 Google Scholar: Lookup Link MathSciNet: MR0923471 · Zbl 0646.62101 · doi:10.2307/1913568 |
| [3] | ANDREWS, D. W. K. (1992). Generic uniform convergence. Econometric Theory 8 241-257. Digital Object Identifier: 10.1017/S0266466600012780 Google Scholar: Lookup Link MathSciNet: MR1179512 · doi:10.1017/S0266466600012780 |
| [4] | ANDREWS, D. W. K. (1993). Tests for parameter instability and structural change with unknown change point. Econometrica 61 821-856. Digital Object Identifier: 10.2307/2951764 Google Scholar: Lookup Link MathSciNet: MR1231678 · doi:10.2307/2951764 |
| [5] | ANDREWS, D. W. K. and PLOBERGER, W. (1994). Optimal tests when a nuisance parameter is present only under the alternative. Econometrica 62 1383-1414. Digital Object Identifier: 10.2307/2951753 Google Scholar: Lookup Link MathSciNet: MR1303238 · Zbl 0815.62033 · doi:10.2307/2951753 |
| [6] | ARMILLOTTA, M. and FOKIANOS, K. Count network autoregression. J. Time Series Anal. To appear. Available at https://arxiv.org/abs/2104.06296. |
| [7] | ARMILLOTTA, M. and FOKIANOS, K. (2023). Supplement to “Nonlinear Network Autoregression.” https://doi.org/10.1214/23-AOS2345SUPP |
| [8] | ARMILLOTTA, M., FOKIANOS, K. and GUIZZARDI, A. (2023). Unveiling Venice’s hotels competition networks from dynamic pricing digital market. J. Roy. Statist. Soc. Ser. A. qnad085. Digital Object Identifier: 10.1093/jrsssa/qnad085 Google Scholar: Lookup Link · doi:10.1093/jrsssa/qnad085 |
| [9] | ARMILLOTTA, M., LUATI, A. and LUPPARELLI, M. (2022). Observation-driven models for discrete-valued time series. Electron. J. Stat. 16 1393-1433. Digital Object Identifier: 10.1214/22-ejs1989 Google Scholar: Lookup Link MathSciNet: MR4387846 · Zbl 1493.62546 · doi:10.1214/22-ejs1989 |
| [10] | ARMILLOTTA, M., TSAGRIS, M. and FOKIANOS, K. Inference for network count time series with the R package PNAR. R J.. To appear. Available at https://arxiv.org/abs/2211.02582. |
| [11] | CHAN, K.-S. and TONG, H. (2001). Chaos: A Statistical Perspective. Springer Series in Statistics. Springer, New York. Digital Object Identifier: 10.1007/978-1-4757-3464-5 Google Scholar: Lookup Link MathSciNet: MR1851668 · Zbl 0977.62002 · doi:10.1007/978-1-4757-3464-5 |
| [12] | CHRISTOU, V. and FOKIANOS, K. (2014). Quasi-likelihood inference for negative binomial time series models. J. Time Series Anal. 35 55-78. Digital Object Identifier: 10.1111/jtsa.12050 Google Scholar: Lookup Link MathSciNet: MR3148248 · Zbl 1301.62084 · doi:10.1111/jtsa.12050 |
| [13] | CHRISTOU, V. and FOKIANOS, K. (2015). Estimation and testing linearity for non-linear mixed Poisson autoregressions. Electron. J. Stat. 9 1357-1377. Digital Object Identifier: 10.1214/15-EJS1044 Google Scholar: Lookup Link MathSciNet: MR3360730 · Zbl 1327.62456 · doi:10.1214/15-EJS1044 |
| [14] | CLARK, N. J. and DIXON, P. M. (2021). A class of spatially correlated self-exciting statistical models. Spat. Stat. 43 Paper No. 100493, 18. Digital Object Identifier: 10.1016/j.spasta.2021.100493 Google Scholar: Lookup Link MathSciNet: MR4219886 · doi:10.1016/j.spasta.2021.100493 |
| [15] | DAVIES, R. B. (1987). Hypothesis testing when a nuisance parameter is present only under the alternative. Biometrika 74 33-43. Digital Object Identifier: 10.1093/biomet/74.1.33 Google Scholar: Lookup Link MathSciNet: MR885917 · Zbl 0612.62023 · doi:10.1093/biomet/74.1.33 |
| [16] | DAVIS, R. A., DUNSMUIR, W. T. M. and STREETT, S. B. (2003). Observation-driven models for Poisson counts. Biometrika 90 777-790. Digital Object Identifier: 10.1093/biomet/90.4.777 Google Scholar: Lookup Link MathSciNet: MR2024757 · Zbl 1436.62418 · doi:10.1093/biomet/90.4.777 |
| [17] | DAVIS, R. A. and LIU, H. (2016). Theory and inference for a class of nonlinear models with application to time series of counts. Statist. Sinica 26 1673-1707. MathSciNet: MR3586234 · Zbl 1356.62137 |
| [18] | DAVIS, R. A. and WU, R. (2009). A negative binomial model for time series of counts. Biometrika 96 735-749. Digital Object Identifier: 10.1093/biomet/asp029 Google Scholar: Lookup Link MathSciNet: MR2538769 · Zbl 1170.62062 · doi:10.1093/biomet/asp029 |
| [19] | DE JONG, R. M. (1996). A strong law of large numbers for triangular mixingale arrays. Statist. Probab. Lett. 27 1-9. Digital Object Identifier: 10.1016/0167-7152(95)00036-4 Google Scholar: Lookup Link MathSciNet: MR1394169 · Zbl 0859.60029 · doi:10.1016/0167-7152(95)00036-4 |
| [20] | DEBALY, Z. M. and TRUQUET, L. (2021). A note on the stability of multivariate non-linear time series with an application to time series of counts. Statist. Probab. Lett. 179 Paper No. 109196, 7. Digital Object Identifier: 10.1016/j.spl.2021.109196 Google Scholar: Lookup Link MathSciNet: MR4293765 · Zbl 1473.62304 · doi:10.1016/j.spl.2021.109196 |
| [21] | DOUC, R., DOUKHAN, P. and MOULINES, E. (2013). Ergodicity of observation-driven time series models and consistency of the maximum likelihood estimator. Stochastic Process. Appl. 123 2620-2647. Digital Object Identifier: 10.1016/j.spa.2013.04.010 Google Scholar: Lookup Link MathSciNet: MR3054539 · Zbl 1285.62104 · doi:10.1016/j.spa.2013.04.010 |
| [22] | DOUC, R., FOKIANOS, K. and MOULINES, E. (2017). Asymptotic properties of quasi-maximum likelihood estimators in observation-driven time series models. Electron. J. Stat. 11 2707-2740. Digital Object Identifier: 10.1214/17-EJS1299 Google Scholar: Lookup Link MathSciNet: MR3679907 · Zbl 1366.62173 · doi:10.1214/17-EJS1299 |
| [23] | Doukhan, P. (1994). Mixing: Properties and Examples. Lecture Notes in Statistics 85. Springer, New York. Digital Object Identifier: 10.1007/978-1-4612-2642-0 Google Scholar: Lookup Link MathSciNet: MR1312160 · Zbl 0801.60027 · doi:10.1007/978-1-4612-2642-0 |
| [24] | DOUKHAN, P., FOKIANOS, K. and LI, X. (2012). On weak dependence conditions: The case of discrete valued processes. Statist. Probab. Lett. 82 1941-1948. Digital Object Identifier: 10.1016/j.spl.2012.06.020 Google Scholar: Lookup Link MathSciNet: MR2970296 · Zbl 1254.60036 · doi:10.1016/j.spl.2012.06.020 |
| [25] | DOUKHAN, P., FOKIANOS, K. and TJØSTHEIM, D. (2012). On weak dependence conditions for Poisson autoregressions. Statist. Probab. Lett. 82 942-948. Digital Object Identifier: 10.1016/j.spl.2012.01.015 Google Scholar: Lookup Link MathSciNet: MR2910041 · Zbl 1241.62109 · doi:10.1016/j.spl.2012.01.015 |
| [26] | Erdős, P. and Rényi, A. (1959). On random graphs. I. Publ. Math. Debrecen 6 290-297. MathSciNet: MR0120167 · Zbl 0092.15705 |
| [27] | FAN, J. and YAO, Q. (2003). Nonlinear Time Series: Nonparametric and Parametric Methods. Springer Series in Statistics. Springer, New York. Digital Object Identifier: 10.1007/b97702 Google Scholar: Lookup Link MathSciNet: MR1964455 · Zbl 1014.62103 · doi:10.1007/b97702 |
| [28] | FOKIANOS, K. (2024). Multivariate count time series modelling. Econometrics and Statistics. To appear. Available at Digital Object Identifier: 10.1016/j.ecosta.2021.11.006 Google Scholar: Lookup Link · doi:10.1016/j.ecosta.2021.11.006 |
| [29] | FOKIANOS, K., RAHBEK, A. and TJØSTHEIM, D. (2009). Poisson autoregression. J. Amer. Statist. Assoc. 104 1430-1439. With electronic supplementary materials available online. Digital Object Identifier: 10.1198/jasa.2009.tm08270 Google Scholar: Lookup Link MathSciNet: MR2596998 · Zbl 1205.62130 · doi:10.1198/jasa.2009.tm08270 |
| [30] | FOKIANOS, K., STØVE, B., TJØSTHEIM, D. and DOUKHAN, P. (2020). Multivariate count autoregression. Bernoulli 26 471-499. MathSciNet: MR4036041 · Zbl 1456.62155 |
| [31] | FOKIANOS, K. and TJØSTHEIM, D. (2012). Nonlinear Poisson autoregression. Ann. Inst. Statist. Math. 64 1205-1225. Digital Object Identifier: 10.1007/s10463-012-0351-3 Google Scholar: Lookup Link MathSciNet: MR2981620 · Zbl 1253.62058 · doi:10.1007/s10463-012-0351-3 |
| [32] | FRANCQ, C., HORVATH, L. and ZAKOÏAN, J.-M. (2010). Sup-tests for linearity in a general nonlinear \(\operatorname{AR}(1)\) model. Econometric Theory 26 965-993. Digital Object Identifier: 10.1017/S0266466609990430 Google Scholar: Lookup Link MathSciNet: MR2660290 · Zbl 1294.62200 · doi:10.1017/S0266466609990430 |
| [33] | Francq, C. and Zakoïan, J.-M. (2010). GARCH Models: Structure, Statistical Inference and Financial Applications. Wiley, Chichester. Digital Object Identifier: 10.1002/9780470670057 Google Scholar: Lookup Link MathSciNet: MR3186556 · doi:10.1002/9780470670057 |
| [34] | Gao, J., King, M., Lu, Z. and TjØstheim, D. (2009). Specification testing in nonlinear and nonstationary time series autoregression. Ann. Statist. 37 3893-3928. Digital Object Identifier: 10.1214/09-AOS698 Google Scholar: Lookup Link MathSciNet: MR2572447 · Zbl 1191.62148 · doi:10.1214/09-AOS698 |
| [35] | Gilbert, E. N. (1959). Random graphs. Ann. Math. Stat. 30 1141-1144. Digital Object Identifier: 10.1214/aoms/1177706098 Google Scholar: Lookup Link MathSciNet: MR0108839 · Zbl 0168.40801 · doi:10.1214/aoms/1177706098 |
| [36] | Giné, E. and Zinn, J. (1990). Bootstrapping general empirical measures. Ann. Probab. 18 851-869. MathSciNet: MR1055437 · Zbl 0706.62017 |
| [37] | GORGI, P. (2020). Beta-negative binomial auto-regressions for modelling integer-valued time series with extreme observations. J. R. Stat. Soc. Ser. B. Stat. Methodol. 82 1325-1347. MathSciNet: MR4176345 · Zbl 07554794 |
| [38] | HANSEN, B. E. (1996). Inference when a nuisance parameter is not identified under the null hypothesis. Econometrica 64 413-430. MathSciNet: MR1375740 · Zbl 0862.62090 |
| [39] | HANSEN, B. E. (1996). Stochastic equicontinuity for unbounded dependent heterogeneous arrays. Econometric Theory 12 347-359. Digital Object Identifier: 10.1017/S0266466600006629 Google Scholar: Lookup Link MathSciNet: MR1395036 · doi:10.1017/S0266466600006629 |
| [40] | HANSEN, B. E. (1999). Testing for linearity. J. Econ. Surv. 13 551-576. |
| [41] | HEYDE, C. C. (1997). Quasi-Likelihood and Its Application: A General Approach to Optimal Parameter Estimation. Springer Series in Statistics. Springer, New York. Digital Object Identifier: 10.1007/b98823 Google Scholar: Lookup Link MathSciNet: MR1461808 · Zbl 0879.62076 · doi:10.1007/b98823 |
| [42] | KNIGHT, M., LEEMING, K., NASON, G. and NUNES, M. (2020). Generalized network autoregressive processes and the GNAR package. J. Stat. Softw. 96 1-36. |
| [43] | Kolaczyk, E. D. and Csárdi, G. (2014). Statistical Analysis of Network Data with R. Use R! Springer, New York. Digital Object Identifier: 10.1007/978-1-4939-0983-4 Google Scholar: Lookup Link MathSciNet: MR3288852 · Zbl 1290.62002 · doi:10.1007/978-1-4939-0983-4 |
| [44] | LIM, K. S. and TONG, H. (1980). Threshold autoregressions, limit cycles, and data. J. Roy. Statist. Soc. Ser. B 42 245-92. · Zbl 0473.62081 |
| [45] | MCCULLAGH, P. and NELDER, J. A. (1989). Generalized Linear Models. Monographs on Statistics and Applied Probability. CRC Press, London. Second edition [of MR0727836]. Digital Object Identifier: 10.1007/978-1-4899-3242-6 Google Scholar: Lookup Link MathSciNet: MR3223057 · Zbl 0744.62098 · doi:10.1007/978-1-4899-3242-6 |
| [46] | Nowicki, K. and Snijders, T. A. B. (2001). Estimation and prediction for stochastic blockstructures. J. Amer. Statist. Assoc. 96 1077-1087. Digital Object Identifier: 10.1198/016214501753208735 Google Scholar: Lookup Link MathSciNet: MR1947255 zbMATH: 1072.62542 · Zbl 1072.62542 · doi:10.1198/016214501753208735 |
| [47] | PEDELI, X. and KARLIS, D. (2011). A bivariate \(\operatorname{INAR}(1)\) process with application. Stat. Model. 11 325-349. Digital Object Identifier: 10.1177/1471082X1001100403 Google Scholar: Lookup Link MathSciNet: MR2906704 · Zbl 1420.62393 · doi:10.1177/1471082X1001100403 |
| [48] | PEDELI, X. and KARLIS, D. (2013). On composite likelihood estimation of a multivariate INAR(1) model. J. Time Series Anal. 34 206-220. Digital Object Identifier: 10.1111/jtsa.12003 Google Scholar: Lookup Link MathSciNet: MR3028367 · Zbl 1274.62376 · doi:10.1111/jtsa.12003 |
| [49] | PEDELI, X. and KARLIS, D. (2013). Some properties of multivariate INAR(1) processes. Comput. Statist. Data Anal. 67 213-225. Digital Object Identifier: 10.1016/j.csda.2013.05.019 Google Scholar: Lookup Link MathSciNet: MR3079598 · Zbl 1471.62158 · doi:10.1016/j.csda.2013.05.019 |
| [50] | POLLARD, D. (1990). Empirical Processes: Theory and Applications. NSF-CBMS Regional Conference Series in Probability and Statistics 2. IMS. MathSciNet: MR1089429 · Zbl 0741.60001 |
| [51] | SEBER, G. A. F. (2008). A Matrix Handbook for Statisticians. Wiley Series in Probability and Statistics. Wiley-Interscience, Hoboken. MathSciNet: MR2365265 · Zbl 1143.15001 |
| [52] | TANIGUCHI, M. and KAKIZAWA, Y. (2000). Asymptotic Theory of Statistical Inference for Time Series. Springer Series in Statistics. Springer, New York. Digital Object Identifier: 10.1007/978-1-4612-1162-4 Google Scholar: Lookup Link MathSciNet: MR1785484 · Zbl 0955.62088 · doi:10.1007/978-1-4612-1162-4 |
| [53] | TERÄSVIRTA, T. (1994). Specification, estimation, and evaluation of smooth transition autoregressive models. J. Amer. Statist. Assoc. 89 208-218. · Zbl 1254.91686 |
| [54] | TERÄSVIRTA, T., TJØSTHEIM, D. and GRANGER, C. W. J. (1994). Aspects of modelling nonlinear time series. In Handbook of Econometrics, Vol. IV. Handbooks in Econom. 2 2917-2957. North-Holland, Amsterdam. MathSciNet: MR1315983 · Zbl 1305.62010 |
| [55] | Teräsvirta, T., TjØstheim, D. and Granger, C. W. J. (2010). Modelling Nonlinear Economic Time Series. Advanced Texts in Econometrics. Oxford Univ. Press, Oxford. Digital Object Identifier: 10.1093/acprof:oso/9780199587148.001.0001 Google Scholar: Lookup Link MathSciNet: MR3185399 · Zbl 1305.62010 · doi:10.1093/acprof:oso/9780199587148.001.0001 |
| [56] | TONG, H. (1990). Nonlinear Time Series. Oxford Statistical Science Series 6. Clarendon, New York. A dynamical system approach, With an appendix by K. S. Chan, Oxford Science Publications. MathSciNet: MR1079320 · Zbl 0716.62085 |
| [57] | TSAGRIS, M., ARMILLOTTA, M. and FOKIANOS, K. (2023). PNAR: Poisson network autoregressive models. R package version 1.6. Available at https://CRAN.R-project.org/package=PNAR. |
| [58] | WANG, C., LIU, H., YAO, J., DAVIS, R. A. and LI, W. K. (2014). Self-excited threshold Poisson autoregression. J. Amer. Statist. Assoc. 109 777-787. Digital Object Identifier: 10.1080/01621459.2013.872994 Google Scholar: Lookup Link MathSciNet: MR3223749 · Zbl 1367.62267 · doi:10.1080/01621459.2013.872994 |
| [59] | Wang, Y. J. and Wong, G. Y. (1987). Stochastic blockmodels for directed graphs. J. Amer. Statist. Assoc. 82 8-19. MathSciNet: MR0883333 · Zbl 0613.62146 |
| [60] | WASSERMAN, S., FAUST, K. et al. (1994). Social Network Analysis: Methods and Applications 8. Cambridge Univ. Press, Cambridge. · Zbl 0926.91066 |
| [61] | WOODARD, D. B., MATTESON, D. S. and HENDERSON, S. G. (2011). Stationarity of generalized autoregressive moving average models. Electron. J. Stat. 5 800-828. Digital Object Identifier: 10.1214/11-EJS627 Google Scholar: Lookup Link MathSciNet: MR2824817 · Zbl 1274.62628 · doi:10.1214/11-EJS627 |
| [62] | YASKOV, P. (2015). Variance inequalities for quadratic forms with applications. Math. Methods Statist. 24 309-319. Digital Object Identifier: 10.3103/S1066530715040055 Google Scholar: Lookup Link MathSciNet: MR3437388 · Zbl 1334.60096 · doi:10.3103/S1066530715040055 |
| [63] | ZHOU, J., HUANG, D. and WANG, H. (2017). A dynamic logistic regression for network link prediction. Sci. China Math. 60 165-176. Digital Object Identifier: 10.1007/s11425-015-0807-8 Google Scholar: Lookup Link MathSciNet: MR3585056 · Zbl 1366.91129 · doi:10.1007/s11425-015-0807-8 |
| [64] | ZHOU, J., LI, D., PAN, R. and WANG, H. (2020). Network GARCH model. Statist. Sinica 30 1723-1740. Digital Object Identifier: 10.5705/ss.202018.0234 Google Scholar: Lookup Link MathSciNet: MR4260742 · Zbl 1464.62398 · doi:10.5705/ss.202018.0234 |
| [65] | ZHU, X. and PAN, R. (2020). Grouped network vector autoregression. Statist. Sinica 30 1437-1462. Digital Object Identifier: 10.5705/ss.202017.0533 Google Scholar: Lookup Link MathSciNet: MR4257540 · Zbl 1453.62654 · doi:10.5705/ss.202017.0533 |
| [66] | Zhu, X., Pan, R., Li, G., Liu, Y. and Wang, H. (2017). Network vector autoregression. Ann. Statist. 45 1096-1123. Digital Object Identifier: 10.1214/16-AOS1476 Google Scholar: Lookup Link MathSciNet: MR3662449 · Zbl 1381.62256 · doi:10.1214/16-AOS1476 |
| [67] | Zhu, X., Wang, W., Wang, H. and Härdle, W. K. (2019). Network quantile autoregression. J. Econometrics 212 345-358. Digital Object Identifier: 10.1016/j.jeconom.2019.04.034 Google Scholar: Lookup Link MathSciNet: MR3994021 · Zbl 1452.62688 · doi:10.1016/j.jeconom.2019.04.034 |
| [68] | ZIVOT, E. and WANG, J. (2003). Modeling Financial Time Series with \(S-Plus^Ⓡ\). Springer, New York. Digital Object Identifier: 10.1007/978-0-387-21763-5 Google Scholar: Lookup Link MathSciNet: MR2000944 · Zbl 1038.91071 · doi:10.1007/978-0-387-21763-5 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
