Maximum likelihood estimation of varma models using a state-space em algorithm

被引:28
|
作者
Metaxoglou, Konstantinos [1 ]
Smith, Aaron [1 ]
机构
[1] Univ Calif Davis, Dept Ag & Resource Econ, Davis, CA 95616 USA
关键词
vector autoregressive moving average; Kalman filter; missing data; closed form;
D O I
10.1111/j.1467-9892.2007.00529.x
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
We introduce a state-space representation for vector autoregressive moving-average models that enables maximum likelihood estimation using the EM algorithm. We obtain closed-form expressions for both the E- and M-steps; the former requires the Kalman filter and a fixed-interval smoother, and the latter requires least squares-type regression. We show via simulations that our algorithm converges reliably to the maximum, whereas gradient-based methods often fail because of the highly nonlinear nature of the likelihood function. Moreover, our algorithm converges in a smaller number of function evaluations than commonly used direct-search routines. Overall, our approach achieves its largest performance gains when applied to models of high dimension. We illustrate our technique by estimating a high-dimensional vector moving-average model for an efficiency test of California's wholesale electricity market.
引用
收藏
页码:666 / 685
页数:20
相关论文
共 50 条
  • [21] Weak VARMA representations of regime-switching state-space models
    Maddalena Cavicchioli
    [J]. Statistical Papers, 2016, 57 : 705 - 720
  • [22] State-space estimation with uncertain models
    Sayed, AH
    Subramanian, A
    [J]. TOTAL LEAST SQUARES AND ERRORS-IN-VARIABLES MODELING: ANALYSIS, ALGORITHMS AND APPLICATIONS, 2002, : 191 - 202
  • [23] THE EVALUATION OF EXACT MAXIMUM LIKELIHOOD ESTIMATES FOR VARMA MODELS
    HALL, AD
    NICHOLLS, DF
    [J]. JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 1980, 10 (3-4) : 251 - 262
  • [24] Alternative EM Algorithms for Nonlinear State-space Models
    Wahlstrom, Johan
    Jalden, Joakim
    Skog, Isaac
    Handel, Peter
    [J]. 2018 21ST INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2018, : 1260 - 1267
  • [25] Constrained maximum likelihood estimation for state space sampled-data models
    Avila, F.
    Yuz, J. I.
    Donaire, A.
    Aguero, J. C.
    [J]. 2018 22ND INTERNATIONAL CONFERENCE ON SYSTEM THEORY, CONTROL AND COMPUTING (ICSTCC), 2018, : 621 - 626
  • [26] Newton-based maximum likelihood estimation in nonlinear state space models
    Kok, Manon
    Dahlin, Johan
    Schon, Thomas B.
    Wills, Adrian
    [J]. IFAC PAPERSONLINE, 2015, 48 (28): : 398 - 403
  • [27] MAXIMUM-LIKELIHOOD-ESTIMATION FOR UNBALANCED MULTILEVEL COVARIANCE STRUCTURE MODELS VIA THE EM ALGORITHM
    RAUDENBUSH, SW
    [J]. BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY, 1995, 48 : 359 - 370
  • [28] Maximum Likelihood Estimation of State Space Models From Frequency Domain Data
    Wills, Adrian
    Ninness, Brett
    Gibson, Stuart
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2009, 54 (01) : 19 - 33
  • [29] Localizing, Forgetting, and Likelihood Filtering in State-Space Models
    Loeliger, Hans-Andrea
    Bolliger, Lukas
    Reller, Christoph
    Korl, Sascha
    [J]. 2009 INFORMATION THEORY AND APPLICATIONS WORKSHOP, 2009, : 181 - +
  • [30] An efficient implementation of maximum likelihood identification of LTI state-space models by local gradient search
    Bergboer, NH
    Verdult, V
    Verhaegen, MHG
    [J]. PROCEEDINGS OF THE 41ST IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 2002, : 616 - 621