Previous Articles     Next Articles

Model Averaging Multistep Prediction in an Infinite Order Autoregressive Process

YUAN Huifang1,2, LIN Peng3, JIANG Tao1,4, XU Jinfeng5   

  1. 1. School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou 310018, China;
    2. School of Mathematics and Statistics, Zaozhuang University, Zaozhuang 277000, China;
    3. School of Mathematics and Statistics, Shandong University of Technology, Zibo 255000, China;
    4. Hangzhou College of Commerce, Zhejiang Gongshang University, Tonglu 311599, China;
    5. Department of Statistics and Actuarial Science, The University of Hong Kong, HongKong 999077, China
  • Received:2020-12-06 Revised:2021-12-23 Online:2022-10-25 Published:2022-10-12
  • Supported by:
    This research was supported by the National Natural Science Foundation of China under Grant No.11971433,First Class Discipline of Zhejiang-A (Zhejiang Gongshang University-Statistics),the Characteristic&Preponderant Discipline of Key Construction Universities in Zhejiang Province (Zhejiang Gongshang University-Statistics),Collaborative Innovation Center of Statistical Data Engineering Technology&Application.

YUAN Huifang, LIN Peng, JIANG Tao, XU Jinfeng. Model Averaging Multistep Prediction in an Infinite Order Autoregressive Process[J]. Journal of Systems Science and Complexity, 2022, 35(5): 1875-1901.

The key issue in the frequentist model averaging is the choice of weights.In this paper,the authors advocate an asymptotic framework of mean-squared prediction error (MSPE) and develop a model averaging criterion for multistep prediction in an infinite order autoregressive (AR (∞)) process.Under the assumption that the order of the candidate model is bounded,this criterion is proved to be asymptotically optimal,in the sense of achieving the lowest out of sample MSPE for the samerealization prediction.Simulations and real data analysis further demonstrate the effectiveness and the efficiency of the theoretical results.
[1] Hannan E J, The estimation of mixed moving averaging autoregressive systems, Biometrika, 1969, 56:579-593.
[2] Box G and Jenkins G, Time Series Analysis:Forecasting and Control, Holden-Day, San Francisco, 1970.
[3] Parzen E, Some recent advances in time series modeling, IEEE Trans. Automatic Control, 1974, 19(6):723-730.
[4] Anderson T, Estimation for autoregressive moving average models in the time and frequency domains, The Annals of Statistics, 1977, 5(5):842-865.
[5] Hamilton J D, Time Series Analysis, Princeton University Press, Princeton, 1994.
[6] Shibata R, Asymptotically efficient selection of the order of the model for estimating parameters of a linear process, The Annals of Statistics, 1980, 8(1):147-164.
[7] Burnham K P and Anderson D R, Model Selection and Multimodel Inference:A Practical Information-Theoretic Approach, Springer, New York, 2002.
[8] Ing C K and Wei C Z, Order selection for same-realization predictions in autoregressive processes, The Annals of Statistics, 2005, 33(5):2423-2474.
[9] Akaike H, Fitting autoregressive models for prediction, Annals of the Institute of Statistical Mathematics, 1969, 21(1):243-247.
[10] Akaike H, A new look at the statistical model identification, IEEE Trans. Automatic Control, 1974, 19(6):716-723.
[11] Ing C K, Multistep prediction in autoregressive processes, Econometric Theory, 2003, 19(2):254-279.
[12] Ing C K and Wei C Z, On same-realization prediction in an infinite-order autoregressive process, Journal of Multivariate Analysis, 2003, 85(1):130-155.
[13] Buckland S T, Burnham K P, and Augustin N H, Model selection:An intergral part of inference, Biometrika, 1997, 53:603-618.
[14] Hansen B E, Least squares model averaging, Econometrica, 2007, 75(4):1175-1189.
[15] Hansen B E and Racine J S, Jackknife model averaging, Journal of Econometrics, 2012, 167(1):38-46.
[16] Zhang X Y, Yu D L, Zou G H, et al., Optimal model averaging estimation for generalized linear models and generalized linear mixed-effects models, Journal of the American Statistical Association, 2016, 111:1775-1790.
[17] Gao Y and Zhang X Y, Model averaging based on leave-subject-out cross-validation, Journal of Econometrics, 2016, 192(1):139-151.
[18] Jankar J, Mandal A, and Jie Y, Optimal crossover designs for generalized linear models, J. Stat. Theory Pract., 2020, 14(2):23-50.
[19] Gao Y, Zhang X Y, and Wang S Y, Frequentist model averaging for threshold models, Annals of the Institute of Statistical Mathematics, 2019, 71(2):275-306.
[20] Chen X P, Cai G H, Gao Y, et al., Asymptotic optimality of the nonnegative Garrote estimator under heteroscedastic errors, Journal of Systems Science&Complexity, 2020, 33(2):545-562.
[21] Shangwei Z, Yanyuan M, Wan A T K, et al., Model averaging in a multiplicative heteroscedastic model, Econometric Reviews, 2020, 39:1100-1124.
[22] Wan A T K, Zhang X Y, and Zou G H, Least squares model averaging by Mallows criterion, Journal of Econometrics, 2010, 156(2):277-283.
[23] Hansen B E, Least-squares forecast averaging, Journal of Econometrics, 2008, 146(2):342-350.
[24] Liao J, Zou G H, Gao Y, and et al., Model averaging prediction for time series models with a diverging number of parameters, Journal of Econometrics, 2020, 223(1):190-221.
[26] Diebold F X and Mariano R S, Comparing predictive accuracy, Journal of Business and Economic Statistics, 1995, 13(3):253-263.
[27] Findley D F and Wei C Z, AIC overfitting principles and the boundedness of moments of inverse matrices for vector autogressions and related models, Journal of Multivariate Analysis, 2002, 83:415-450.
[1] LIU Yue, ZOU Jiahui, ZHAO Shangwei, YANG Qinglong. Model Averaging Estimation for Varying-Coefficient Single-Index Models [J]. Journal of Systems Science and Complexity, 2022, 35(1): 264-282.
[2] Bernard BERCU. AN EXPONENTIAL INEQUALITY FOR AUTOREGRESSIVE PROCESSES INADAPTIVE TRACKING [J]. Journal of Systems Science and Complexity, 2007, 20(2): 243-250.
[3] Lai Sheng WEI. THE ASYMPTOTICALLY OPTIMAL EMPIRICAL BAYES ESTIMATION IN ONE WAY ANOVA MODEL [J]. Journal of Systems Science and Complexity, 1999, 12(1): 13-022.
Full text