The exact Gaussian likelihood estimation of time-dependent VARMA models. (English) Zbl 1466.62017
Summary: An algorithm for the evaluation of the exact Gaussian likelihood of an \(r\)-dimensional vector autoregressive-moving average (VARMA) process of order \((p,q)\), with time-dependent coefficients, including a time dependent innovation covariance matrix, is proposed. The elements of the matrices of coefficients and those of the innovation covariance matrix are deterministic functions of time and assumed to depend on a finite number of parameters. These parameters are estimated by maximizing the Gaussian likelihood function. The advantages of that approach is that the Gaussian likelihood function can be computed exactly and efficiently. The algorithm is based on the Cholesky decomposition method for block-band matrices. It is shown that the number of operations as a function of \(p\), \(q\) and \(n\), the size of the series, is barely doubled with respect to a VARMA model with constant coefficients. A detailed description of the algorithm followed by a data example is provided.
MSC:
| 62-08 | Computational methods for problems pertaining to statistics |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
| 62P20 | Applications of statistics to economics |
References:
| [1] | Alj, A.; Azrak, R.; Mélard, G., Asymptotic for tdvarma models, (Azrak, R.; Mélard, G., Time Dependent Models for Time Series, (2014)), (in preparation) |
| [2] | Ansley, C. F., An algorithm for the exact likelihood of a mixed autoregressive moving average process, Biometrika, 66, 59-65, (1979) · Zbl 0411.62059 |
| [3] | Ansley, C. F., Computation of the theoretical autocovariance function for a vector ARMA process, J. Stat. Comput. Simul., 12, 15-24, (1980) · Zbl 0445.62099 |
| [4] | Azrak, R.; Mélard, G., Exact quasi-likelihood of time-dependent ARMA models, J. Statist. Plann. Inference, 68, 1, 31-45, (1998) · Zbl 0937.62087 |
| [5] | Azrak, R.; Mélard, G., Asymptotic properties of quasi-likelihood estimators for ARMA models with time-dependent coefficients, Stat. Inference Stoch. Process., 9, 279-330, (2006) · Zbl 1125.62093 |
| [6] | Brockwell, P. J.; Davis, R. A., Time series: theory and methods, (1991), Springer-Verlag New York · Zbl 0709.62080 |
| [7] | Caines, P. E., Linear stochastic systems, (1988), Wiley New York · Zbl 0658.93003 |
| [8] | Chen, Y.-H.; Hsu, N.-J., A frequency domain test for detecting nonstationary time series, Comput. Statist. Data Anal., 75, 179-189, (2014) · Zbl 1506.62042 |
| [9] | Coleman, T.; Branch, M. A.; Grace, A., Optimization toolbox: user’s guide, (1999), The MathWorks, Inc. Natic, MA |
| [10] | Hall, A. D.; Nicholls, D. F., The evaluation of exact maximum likelihood estimates for VARMA models, J. Stat. Comput. Simul., 10, 251-262, (1980) · Zbl 0433.62062 |
| [11] | Hallin, M., Mixed autoregressive-moving average multivariate processes with time-dependent coefficients, J. Multivariate Anal., 8, 567-572, (1978) · Zbl 0394.62067 |
| [12] | Hallin, M., Non-stationary \(q\)-dependent processes and time-varying moving average models: invertibility properties and the forecasting problem, Adv. Appl. Probab., 18, 170-210, (1986) · Zbl 0597.62096 |
| [13] | Hannan, E. J.; Deistler, M., The statistical theory of linear systems, (1988), Wiley New York · Zbl 0641.93002 |
| [14] | Hannan, E. J.; Quinn, B. G., The determination of the order of an autoregression, J. R. Stat. Soc. Ser. B Stat. Methodol, 41, 190-195, (1979) · Zbl 0408.62076 |
| [15] | Hindrayanto, I.; Koopman, S. J.; Ooms, M., Exact maximum likelihood estimation for non-stationary periodic time series models, Comput. Statist. Data Anal., 54, 2641-2654, (2010) · Zbl 1284.91588 |
| [16] | Hurvich, C. M.; Tsai, C. L., Regression and time series model selection in small samples, Biometrika, 76, 297-307, (1989) · Zbl 0669.62085 |
| [17] | Jónasson, K., Algorithm 878: exact VARMA likelihood and its gradient for complete and incomplete data with Matlab, ACM Trans. Math. Software, 35, 1, 6, (2008) |
| [18] | Jónasson, K.; Ferrando, S. E., Evaluating exact VARMA likelihood and its gradient when data are incomplete, ACM Trans. Math. Software, 35, 1, 5, (2008) |
| [19] | Kohn, R.; Ansley, C. F., A note on obtaining the theoretical autocovariances of an ARMA process, J. Stat. Comput. Simul., 15, 273-283, (1982) · Zbl 0505.62080 |
| [20] | Kwoun, G. H.; Yajima, Y., On an autoregressive model with time-dependent coefficients, Ann. Inst. Statist. Math. Part A, 38, 297-309, (1986) · Zbl 0613.62111 |
| [21] | Lanne, M.; Saikkonen, P., Noncausal vector autoregression, Econom. Theory, 29, 447-481, (2013) · Zbl 1274.62602 |
| [22] | Lütkepohl, H., New introduction to multiple time series analysis, (2005), Springer-Verlag New York · Zbl 1072.62075 |
| [23] | Mauricio, J.A., 1995. A corrected algorithm for computing the theoretical autocovariance matrices of a vector ARMA model. Working Paper 9502, Instituto Complutense de Analisis Economico, Madrid. |
| [24] | Mauricio, J. A., Algorithm AS 311: the exact likelihood function of a vector autoregressive moving average model, J. R. Stat. Soc. Ser. C. Appl. Stat., 46, 1, 157-171, (1997) · Zbl 1063.62573 |
| [25] | Mauricio, J. A., An algorithm for the exact likelihood of a stationary vector autoregressive moving average model, J. Time Ser. Anal., 23, 4, 473-486, (2002) · Zbl 1091.62080 |
| [26] | Mauricio, J. A., Exact maximum likelihood estimation of partially nonstationary vector ARMA models, Comput. Statist. Data Anal., 50, 12, 3644-3662, (2006) · Zbl 1445.62234 |
| [27] | Mélard, G., The likelihood function of a time-dependent ARMA model, (Anderson, O. D.; Perryman, M. R., Applied Time Series Analysis, (1982), North-Holland Amsterdam), 229-239 · Zbl 0502.62076 |
| [28] | Mélard, G.; Roy, R.; Saidi, A., Exact maximum likelihood estimation of structured or unit root multivariate time series models, Comput. Statist. Data Anal., 50, 11, 2957-2986, (2006) · Zbl 1445.62235 |
| [29] | Penzer, J.; Shea, B. L., The exact likelihood of an autoregressive-moving average model with incomplete data, Biometrika, 84, 4, 919-928, (1997) · Zbl 0892.62070 |
| [30] | Reinsel, G. C., Elements of multivariate time series analysis, (1998), Springer-Verlag New York |
| [31] | Rissanen, J., Modelling by shortest data description, Automatica, 14, 465-471, (1978) · Zbl 0418.93079 |
| [32] | Schwarz, G., Estimating the dimension of a model, Ann. Statist., 6, 461-464, (1978) · Zbl 0379.62005 |
| [33] | Shea, B. L., Maximum likelihood estimation of multivariate ARMA processes via the Kalman filter, (Anderson, O. D., Time Series Analysis: Theory and Practice, vol. 5, (1984), North-Holland Amsterdam), 91-101 · Zbl 0551.62068 |
| [34] | Shea, B. L., Algorithm AS 242: the exact likelihood of a vector autoregressive moving average model, J. R. Stat. Soc. Ser. C. Appl. Stat., 38, 1, 161-204, (1989) |
| [35] | Triantafyllopoulos, K.; Nason, G. P., A Bayesian analysis of moving average processes with time-varying parameters, Comput. Statist. Data Anal., 52, 1025-1046, (2007) · Zbl 1452.62683 |
| [36] | Tsay, R. S., Analysis of financial time series, (2005), John Wiley New York · Zbl 1086.91054 |
| [37] | Tunnicliffe Wilson, G., The estimation of parameters in multivariate time series models, J. R. Stat. Soc. Ser. B Stat. Methodol, 35, 76-85, (1973) · Zbl 0259.62074 |
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.
