This paper studies the model selection problem in a large class of causal time series models, which includes both the ARMA or AR($\infty $) processes, as well as the GARCH or ARCH($\infty $), APARCH, ARMA-GARCH and many others processes. To tackle this issue, we consider a penalized contrast based on the quasi-likelihood of the model. We provide sufficient conditions for the penalty term to ensure the consistency of the proposed procedure as well as the consistency and the asymptotic normality of the quasi-maximum likelihood estimator of the chosen model. We also propose a tool for diagnosing the goodness-of-fit of the chosen model based on a Portmanteau test. Monte-Carlo experiments and numerical applications on illustrative examples are performed to highlight the obtained asymptotic results. Moreover, using a data-driven choice of the penalty, they show the practical efficiency of this new model selection procedure and Portemanteau test.
References
[1] H Akaike, Information theory and an extension of the maximum likelihood principle, Proceedings of the 2nd international symposium on information, Akademiai Kiado, Budapest (1973). 0283.62006[1] H Akaike, Information theory and an extension of the maximum likelihood principle, Proceedings of the 2nd international symposium on information, Akademiai Kiado, Budapest (1973). 0283.62006
[2] D.M. Allen, The relationship between variable selection and data agumentation and a method for prediction, Technometrics 16 (1974), no. 1, 125–127. 0286.62044 10.1080/00401706.1974.10489157[2] D.M. Allen, The relationship between variable selection and data agumentation and a method for prediction, Technometrics 16 (1974), no. 1, 125–127. 0286.62044 10.1080/00401706.1974.10489157
[3] P. Alquier and O. Wintenberger, Model selection for weakly dependent time series forecasting, Bernoulli 18 (2012), no. 3, 883–913. 1243.62117 10.3150/11-BEJ359 euclid.bj/1340887007[3] P. Alquier and O. Wintenberger, Model selection for weakly dependent time series forecasting, Bernoulli 18 (2012), no. 3, 883–913. 1243.62117 10.3150/11-BEJ359 euclid.bj/1340887007
[4] O. Arkoun, J.-Y. Brua, and S. Pergamenshchikov, Sequential model selection method for nonparametric autoregression, Sequential Anal. 38 (2019), no. 4, 437–460. 1430.62075 10.1080/07474946.2019.1686883[4] O. Arkoun, J.-Y. Brua, and S. Pergamenshchikov, Sequential model selection method for nonparametric autoregression, Sequential Anal. 38 (2019), no. 4, 437–460. 1430.62075 10.1080/07474946.2019.1686883
[6] S. Arlot and P. Massart, Data-driven calibration of penalties for least-squares regression, Journal of Machine learning research 10 (2009), 245–279.[6] S. Arlot and P. Massart, Data-driven calibration of penalties for least-squares regression, Journal of Machine learning research 10 (2009), 245–279.
[7] J.-M. Bardet, Y. Boularouk, and K. Djaballah, Asymptotic behavior of the laplacian quasi-maximum likelihood estimator of affine causal processes, Electronic journal of statistics 11 (2017), no. 1, 452–479. 06702351 10.1214/17-EJS1241[7] J.-M. Bardet, Y. Boularouk, and K. Djaballah, Asymptotic behavior of the laplacian quasi-maximum likelihood estimator of affine causal processes, Electronic journal of statistics 11 (2017), no. 1, 452–479. 06702351 10.1214/17-EJS1241
[8] J.-M. Bardet, W.C. Kengne, and O. Wintenberger, Detecting multiple change-points in general causal time series using penalized quasi-likelihood, Electronic journal of statistics 6 (2012), 435–477. 1337.62210 10.1214/12-EJS680[8] J.-M. Bardet, W.C. Kengne, and O. Wintenberger, Detecting multiple change-points in general causal time series using penalized quasi-likelihood, Electronic journal of statistics 6 (2012), 435–477. 1337.62210 10.1214/12-EJS680
[9] J.-M. Bardet and O. Wintenberger, Asymptotic normality of the quasi-maximum likelihood estimator for multidimensional causal processes, The Annals of Statistics 37 (2009), no. 5B, 2730–2759. 1173.62063 10.1214/08-AOS674 euclid.aos/1247836667[9] J.-M. Bardet and O. Wintenberger, Asymptotic normality of the quasi-maximum likelihood estimator for multidimensional causal processes, The Annals of Statistics 37 (2009), no. 5B, 2730–2759. 1173.62063 10.1214/08-AOS674 euclid.aos/1247836667
[10] J.-P. Baudry, C. Maugis, and B. Michel, Slope heuristics: overview and implementation, Statistics and Computing 22 (2012), no. 2, 455–470. 1322.62007 10.1007/s11222-011-9236-1[10] J.-P. Baudry, C. Maugis, and B. Michel, Slope heuristics: overview and implementation, Statistics and Computing 22 (2012), no. 2, 455–470. 1322.62007 10.1007/s11222-011-9236-1
[12] I. Berkes, L. Horváth, and P. Kokoszka, GARCH processes: structure and estimation, Bernoulli 9 (2003), 201–227. 1064.62094 10.3150/bj/1068128975 euclid.bj/1068128975[12] I. Berkes, L. Horváth, and P. Kokoszka, GARCH processes: structure and estimation, Bernoulli 9 (2003), 201–227. 1064.62094 10.3150/bj/1068128975 euclid.bj/1068128975
[13] L. Birgé and P. Massart, Gaussian model selection, Journal of the European Mathematical Society 3 (2001), no. 3, 203–268. 1037.62001 10.1007/s100970100031[13] L. Birgé and P. Massart, Gaussian model selection, Journal of the European Mathematical Society 3 (2001), no. 3, 203–268. 1037.62001 10.1007/s100970100031
[14] L. Birgé and P. Massart, Minimal penalties for gaussian model selection, Probability theory and related fields 138 (2007), no. 1-2, 33–73. 1112.62082 10.1007/s00440-006-0011-8[14] L. Birgé and P. Massart, Minimal penalties for gaussian model selection, Probability theory and related fields 138 (2007), no. 1-2, 33–73. 1112.62082 10.1007/s00440-006-0011-8
[16] Z. Ding, C. Granger, and R.F. Engle, A long memory property of stock market returns and a new model, Journal of empirical finance 1 (1993), no. 1, 83–106.[16] Z. Ding, C. Granger, and R.F. Engle, A long memory property of stock market returns and a new model, Journal of empirical finance 1 (1993), no. 1, 83–106.
[17] P. Doukhan and O. Wintenberger, Weakly dependent chains with infinite memory, Stochastic Processes and their Applications 118 (2008), no. 11, 1997–2013. 1166.60031 10.1016/j.spa.2007.12.004[17] P. Doukhan and O. Wintenberger, Weakly dependent chains with infinite memory, Stochastic Processes and their Applications 118 (2008), no. 11, 1997–2013. 1166.60031 10.1016/j.spa.2007.12.004
[18] P. Duchesne and C. Francq, On diagnostic checking time series models with portmanteau test statistics based on generalized inverses and, COMPSTAT 2008, Springer, 2008, pp. 143–154. 1151.62069[18] P. Duchesne and C. Francq, On diagnostic checking time series models with portmanteau test statistics based on generalized inverses and, COMPSTAT 2008, Springer, 2008, pp. 143–154. 1151.62069
[19] C. Francq and J.-M. Zakoïan, Maximum likelihood estimation of pure garch and arma-garch processes, Bernoulli 10 (2004), 605–637. 1067.62094 10.3150/bj/1093265632 euclid.bj/1093265632[19] C. Francq and J.-M. Zakoïan, Maximum likelihood estimation of pure garch and arma-garch processes, Bernoulli 10 (2004), 605–637. 1067.62094 10.3150/bj/1093265632 euclid.bj/1093265632
[20] C. Francq and J.-M. Zakoian, Garch models: structure, statistical inference and financial applications, John Wiley & Sons, 2010. MR3186556 1431.62004[20] C. Francq and J.-M. Zakoian, Garch models: structure, statistical inference and financial applications, John Wiley & Sons, 2010. MR3186556 1431.62004
[21] J. Gao and H. Tong, Semiparametric non-linear time series model selection, Journal of the Royal Statistical Society: Series B 66 (2004), no. 2, 321–336. 1062.62175 10.1111/j.1369-7412.2004.05303.x[21] J. Gao and H. Tong, Semiparametric non-linear time series model selection, Journal of the Royal Statistical Society: Series B 66 (2004), no. 2, 321–336. 1062.62175 10.1111/j.1369-7412.2004.05303.x
[22] United States government, Particulate matter (pm) pollution, http://www.epa.gov/pm-pollution/particulate-matter-pm-basics, 2017.[22] United States government, Particulate matter (pm) pollution, http://www.epa.gov/pm-pollution/particulate-matter-pm-basics, 2017.
[23] E.J. Hannan, The estimation of the order of an arma process, The Annals of Statistics 8 (1980), no. 5, 1071–1081. 0451.62068 10.1214/aos/1176345144 euclid.aos/1176345144[23] E.J. Hannan, The estimation of the order of an arma process, The Annals of Statistics 8 (1980), no. 5, 1071–1081. 0451.62068 10.1214/aos/1176345144 euclid.aos/1176345144
[25] A.E. Hoerl and R.W. Kennard, Ridge regression: Biased estimation for nonorthogonal problems, Technometrics 12 (1970), no. 1, 55–67. 0202.17205 10.1080/00401706.1970.10488634[25] A.E. Hoerl and R.W. Kennard, Ridge regression: Biased estimation for nonorthogonal problems, Technometrics 12 (1970), no. 1, 55–67. 0202.17205 10.1080/00401706.1970.10488634
[26] H.-L. Hsu, C.-K. Ing, and H. Tong, On model selection from a finite family of possibly misspecified time series models, The Annals of Statistics 47 (2019), no. 2, 1061–1087. 1418.62333 10.1214/18-AOS1706 euclid.aos/1547197248[26] H.-L. Hsu, C.-K. Ing, and H. Tong, On model selection from a finite family of possibly misspecified time series models, The Annals of Statistics 47 (2019), no. 2, 1061–1087. 1418.62333 10.1214/18-AOS1706 euclid.aos/1547197248
[27] C.M. Hurvich and C.-L. Tsai, Regression and time series model selection in small samples, Biometrika 76 (1989), no. 2, 297–307. 0669.62085 10.1093/biomet/76.2.297[27] C.M. Hurvich and C.-L. Tsai, Regression and time series model selection in small samples, Biometrika 76 (1989), no. 2, 297–307. 0669.62085 10.1093/biomet/76.2.297
[28] C.-K. Ing, Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series, The Annals of Statistics 35 (2007), no. 3, 1238–1277. MR2341705 1118.62097 10.1214/009053606000001550 euclid.aos/1185304005[28] C.-K. Ing, Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series, The Annals of Statistics 35 (2007), no. 3, 1238–1277. MR2341705 1118.62097 10.1214/009053606000001550 euclid.aos/1185304005
[29] C.-K. Ing, C.-Y. Sin, and S.-H. Yu, Model selection for integrated autoregressive processes of infinite order, Journal of Multivariate Analysis 106 (2012), 57–71. 1236.62105 10.1016/j.jmva.2011.10.008[29] C.-K. Ing, C.-Y. Sin, and S.-H. Yu, Model selection for integrated autoregressive processes of infinite order, Journal of Multivariate Analysis 106 (2012), 57–71. 1236.62105 10.1016/j.jmva.2011.10.008
[30] C.-K. Ing and C.-Z. Wei, Order selection for same-realization predictions in autoregressive processes, The Annals of Statistics 33 (2005), no. 5, 2423–2474. 1086.62105 10.1214/009053605000000525 euclid.aos/1132936568[30] C.-K. Ing and C.-Z. Wei, Order selection for same-realization predictions in autoregressive processes, The Annals of Statistics 33 (2005), no. 5, 2423–2474. 1086.62105 10.1214/009053605000000525 euclid.aos/1132936568
[32] G. Kapetanios, Model selection in threshold models, Journal of Time Series Analysis 22 (2001), no. 6, 733–754. 0985.62071 10.1111/1467-9892.00251[32] G. Kapetanios, Model selection in threshold models, Journal of Time Series Analysis 22 (2001), no. 6, 733–754. 0985.62071 10.1111/1467-9892.00251
[33] A.B. Kock, Consistent and conservative model selection with the adaptive lasso in stationary and nonstationary autoregressions, Econometric Theory 32 (2016), no. 1, 243–259. 06544684 10.1017/S0266466615000304[33] A.B. Kock, Consistent and conservative model selection with the adaptive lasso in stationary and nonstationary autoregressions, Econometric Theory 32 (2016), no. 1, 243–259. 06544684 10.1017/S0266466615000304
[34] E.G. Kounias and T. Weng, An inequality and almost sure convergence, The Annals of Mathematical Statistics 40 (1969), no. 3, 1091–1093. 0176.48003 10.1214/aoms/1177697615 euclid.aoms/1177697615[34] E.G. Kounias and T. Weng, An inequality and almost sure convergence, The Annals of Mathematical Statistics 40 (1969), no. 3, 1091–1093. 0176.48003 10.1214/aoms/1177697615 euclid.aoms/1177697615
[35] M. Lerasle, Optimal model selection for density estimation of stationary data under various mixing conditions, The Annals of Statistics 39 (2011), no. 4, 1852–1877. 1227.62018 10.1214/11-AOS888 euclid.aos/1311688538[35] M. Lerasle, Optimal model selection for density estimation of stationary data under various mixing conditions, The Annals of Statistics 39 (2011), no. 4, 1852–1877. 1227.62018 10.1214/11-AOS888 euclid.aos/1311688538
[36] G. Li and W.K. Li, Least absolute deviation estimation for fractionally integrated autoregressive moving average time series models with conditional heteroscedasticity, Biometrika 95 (2008), no. 2, 399–414. 05563403 10.1093/biomet/asn014[36] G. Li and W.K. Li, Least absolute deviation estimation for fractionally integrated autoregressive moving average time series models with conditional heteroscedasticity, Biometrika 95 (2008), no. 2, 399–414. 05563403 10.1093/biomet/asn014
[37] W.K. Li, On the asymptotic standard errors of residual autocorrelations in nonlinear time series modelling, Biometrika 79 (1992), no. 2, 435–437. 0751.62042 10.1093/biomet/79.2.435[37] W.K. Li, On the asymptotic standard errors of residual autocorrelations in nonlinear time series modelling, Biometrika 79 (1992), no. 2, 435–437. 0751.62042 10.1093/biomet/79.2.435
[38] W.K. Li and T.K. Mak, On the squared residual autocorrelations in non-linear time series with conditional heteroskedasticity, Journal of Time Series Analysis 15 (1994), no. 6, 627–636. 0807.62070 10.1111/j.1467-9892.1994.tb00217.x[38] W.K. Li and T.K. Mak, On the squared residual autocorrelations in non-linear time series with conditional heteroskedasticity, Journal of Time Series Analysis 15 (1994), no. 6, 627–636. 0807.62070 10.1111/j.1467-9892.1994.tb00217.x
[39] S. Ling and W.-K. Li, Diagnostic checking of nonlinear multivariate time series with multivariate arch errors, Journal of Time Series Analysis 18 (1997), no. 5, 447–464. 0882.62081 10.1111/1467-9892.00061[39] S. Ling and W.-K. Li, Diagnostic checking of nonlinear multivariate time series with multivariate arch errors, Journal of Time Series Analysis 18 (1997), no. 5, 447–464. 0882.62081 10.1111/1467-9892.00061
[42] A. McQuarrie and C.L. Tsai, Regression and time series model selection, World Scientific Pub Co Inc, 1998. 0907.62095[42] A. McQuarrie and C.L. Tsai, Regression and time series model selection, World Scientific Pub Co Inc, 1998. 0907.62095
[44] Y. Ren and X. Zhang, Subset selection for vector autoregressive processes via adaptive lasso, Statistics & probability letters 80 (2010), no. 23-24, 1705–1712. 1202.62122 10.1016/j.spl.2010.07.013[44] Y. Ren and X. Zhang, Subset selection for vector autoregressive processes via adaptive lasso, Statistics & probability letters 80 (2010), no. 23-24, 1705–1712. 1202.62122 10.1016/j.spl.2010.07.013
[45] G. Schwarz, Estimating the dimension of a model, The Annals of Statistics 6 (1978), 461–464. 0379.62005 10.1214/aos/1176344136 euclid.aos/1176344136[45] G. Schwarz, Estimating the dimension of a model, The Annals of Statistics 6 (1978), 461–464. 0379.62005 10.1214/aos/1176344136 euclid.aos/1176344136
[46] Q. Shao and L. Yang, Oracally efficient estimation and consistent model selection for auto-regressive moving average time series with trend, Journal of the Royal Statistical Society: Series B 79 (2017), no. 2, 507–524. 1414.62380 10.1111/rssb.12170[46] Q. Shao and L. Yang, Oracally efficient estimation and consistent model selection for auto-regressive moving average time series with trend, Journal of the Royal Statistical Society: Series B 79 (2017), no. 2, 507–524. 1414.62380 10.1111/rssb.12170
[47] P. Shi and C.-L. Tsai, Regression model selection-a residual likelihood approach, Journal of the Royal Statistical Society: Series B 64 (2002), no. 2, 237–252. 1059.62074 10.1111/1467-9868.00335[47] P. Shi and C.-L. Tsai, Regression model selection-a residual likelihood approach, Journal of the Royal Statistical Society: Series B 64 (2002), no. 2, 237–252. 1059.62074 10.1111/1467-9868.00335
[48] R. Shibata, Asymptotically efficient selection of the order of the model for estimating parameters of a linear process, The Annals of Statistics (1980), 147–164. 0425.62069 10.1214/aos/1176344897 euclid.aos/1176344897[48] R. Shibata, Asymptotically efficient selection of the order of the model for estimating parameters of a linear process, The Annals of Statistics (1980), 147–164. 0425.62069 10.1214/aos/1176344897 euclid.aos/1176344897
[49] C.-Y. Sin and H. White, Information criteria for selecting possibly misspecified parametric models, Journal of Econometrics 71 (1996), no. 1-2, 207–225. 0843.62089 10.1016/0304-4076(94)01701-8[49] C.-Y. Sin and H. White, Information criteria for selecting possibly misspecified parametric models, Journal of Econometrics 71 (1996), no. 1-2, 207–225. 0843.62089 10.1016/0304-4076(94)01701-8
[50] M. Stone, Cross-validatory choice and assessment of statistical predictions, Journal of the royal statistical society. Series B (1974), 111–147. 0308.62063 10.1111/j.2517-6161.1974.tb00994.x[50] M. Stone, Cross-validatory choice and assessment of statistical predictions, Journal of the royal statistical society. Series B (1974), 111–147. 0308.62063 10.1111/j.2517-6161.1974.tb00994.x
[51] D. Straumann and T. Mikosch, Quasi-maximum-likelihood estimation in conditionally heteroscedastic time series: A stochastic recurrence equations approach, The Annals of Statistics 34 (2006), no. 5, 2449–2495. 1108.62094 10.1214/009053606000000803 euclid.aos/1169571804[51] D. Straumann and T. Mikosch, Quasi-maximum-likelihood estimation in conditionally heteroscedastic time series: A stochastic recurrence equations approach, The Annals of Statistics 34 (2006), no. 5, 2449–2495. 1108.62094 10.1214/009053606000000803 euclid.aos/1169571804
[52] R. Tibshirani, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society. Series B (1996), 267–288. 0850.62538 10.1111/j.2517-6161.1996.tb02080.x[52] R. Tibshirani, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society. Series B (1996), 267–288. 0850.62538 10.1111/j.2517-6161.1996.tb02080.x
[53] R.S. Tsay, Order selection in nonstationary autoregressive models, The Annals of Statistics 12 (1984), no. 4, 1425–1433. 0554.62075 10.1214/aos/1176346801 euclid.aos/1176346801[53] R.S. Tsay, Order selection in nonstationary autoregressive models, The Annals of Statistics 12 (1984), no. 4, 1425–1433. 0554.62075 10.1214/aos/1176346801 euclid.aos/1176346801
[54] Y.K. Tse and X.L. Zuo, Testing for conditional heteroscedasticity: Some monte carlo results, Journal of Statistical Computation and Simulation 58 (1997), no. 3, 237–253. 1102.62342 10.1080/00949659708811833[54] Y.K. Tse and X.L. Zuo, Testing for conditional heteroscedasticity: Some monte carlo results, Journal of Statistical Computation and Simulation 58 (1997), no. 3, 237–253. 1102.62342 10.1080/00949659708811833
[55] H. White, Maximum likelihood estimation of misspecified models, Econometrica (1982), 1–25. 0478.62088 10.2307/1912526[55] H. White, Maximum likelihood estimation of misspecified models, Econometrica (1982), 1–25. 0478.62088 10.2307/1912526
[56] H. Zou, The adaptive lasso and its oracle properties, Journal of the American Statistical Association 101 (2006), no. 476, 1418–1429. 1171.62326 10.1198/016214506000000735[56] H. Zou, The adaptive lasso and its oracle properties, Journal of the American Statistical Association 101 (2006), no. 476, 1418–1429. 1171.62326 10.1198/016214506000000735
[57] H. Zou and T. Hastie, Regularization and variable selection via the elastic net, Journal of the Royal Statistical Society: Series B 67 (2005), no. 2, 301–320. 1069.62054 10.1111/j.1467-9868.2005.00503.x[57] H. Zou and T. Hastie, Regularization and variable selection via the elastic net, Journal of the Royal Statistical Society: Series B 67 (2005), no. 2, 301–320. 1069.62054 10.1111/j.1467-9868.2005.00503.x
