Maximum likelihood estimation of linear SISO models subject to missing output data and missing input data

International Journal of Control

Volumn 87, Issue 11, 2014, Pages 2354-2364

  Wallin, Ragnar ^a   Hansson, Anders ^a  

^a LINKÖPING UNIVERSITY   (Sweden)

Author keywords

Maximum likelihood estimation; Missing data; System identification

Indexed keywords

COVARIANCE MATRIX; IDENTIFICATION (CONTROL SYSTEMS); MAXIMUM LIKELIHOOD;

INPUT AND OUTPUTS; MISSING DATA; MISSING INPUTS; NUMERICAL RESULTS; OUTPUT DATA; PREDICTION ERRORS; SINGLE INPUT SINGLE OUTPUT; SUB-OPTIMAL SCHEMES;

MAXIMUM LIKELIHOOD ESTIMATION;

EID: 84899468139     PISSN: 00207179     EISSN: 13665820     Source Type: Journal    
DOI: 10.1080/00207179.2014.913346     Document Type: Article

References (36)

1. Ansley, C.F., & Kohn, R. (1983). Exact likelihood of vector autoregressive-moving average with missing or aggregated data. Biometrica, 70(1), 275-278.
2. Coleman, T.F., & Li, Y. (1994). On the convergence of reflective Newton methods for large-scale nonlinear minimization subject to bounds. Mathematical Programming, 67(2), 189-224.
3. Coleman, T.F., & Li, Y. (1996). An interior, trust region approach for nonlinear minimization subject to bounds. SIAM Journal on Optimization, 6, 418-445.
4. Dempster, A.P., Laird, N.M., & Rubin, D.B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39, 1-38.
5. Ding, T., Sznaier, M., & Camps, O. (2007). A rank minimization approach to fast dynamic event detection and track matching in video sequences. Proceedings of the 46th IEEE Conference on Decision and Control. New Orleans, LA.
6. Dunsmuir, W., & Robinson, P. (1981). Estimation of time series models in the presence of missing data. Journal of the American Statistical Association, 76(375), 560-568.
7. Golub, G., & Pereyra, V. (1973). The differentiation of pseudoinverses and nonlinear least squares problemswhose variables separate. SIAM Journal on Numerical Analysis, 10(2), 413-432.
8. Golub, G.H., & vanLoan, C.F. (1996). Matrix computations (3rd ed.). Baltimore, MD: Johns Hopkins University Press.
9. Goodwin, G., & Adams, G.J. (1994).Multi-rate techniques in nonzero-order hold identification. In Preprints of the 10th IFAC Symposium on System Identification (Vol. 3, pp. 125-130). Copenhagen, Denmark.
10. Grossmann, C., Jones, C.N., & Morari, M. (2009). System identification via nuclear norm regularization for simulated bed processes from incomplete data sets. In Proceedings of the 48th IEEE Conference on Decision and Control (pp. 4692-4697). Shanghai, China.
11. Hansson, A., & Wallin, R. (2011). Maximum likelihood estimation of Gaussian models with missing data-eight equivalent formulations (Technical Report LiTH-ISY-R-3013). Linköping: Linköping University.
12. Hansson, A., & Wallin, R. (2012). Maximum likelihood estimation of Gaussian models with missing data-eight equivalent formulations. Automatica, 48(9), 1955-1962.
13. Harvey, A.C., & McKenzie, C.R. (1984). Missing observations in dynamic econometric models: A partial synthesis. In E. Parzen (Ed.), Time series analysis of irregularly observed data (pp. 108-133). New York, NY: Springer Verlag.
14. Isaksson, A.J. (1993). Identification of ARX models subject to missing data. IEEE Transactions on Automatic Control, 38(5), 813-819.
15. Isaksson, A.J., & Kaul, V. (1992). Survey of missing data identification techniques. In Proceedings of Control Systems 92 (pp. 95-99). Whistler, Canada.
16. Jones, R.H. (1980).Maximum likelihood fitting ofARMAmodels to time series with missing observations. Technometrics, 22, 389-395.
17. Kaufman, L. (1975). A variable projection method for solving separable nonlinear least squares problems. BIT Numerical Mathematics, 15, 49-57.
18. Little, R.J.A., & Rubin, D.B. (2002). Statistical Analysis with Missing Data (2nd edition). New York, NY: Wiley.
19. Liu, Z., Hansson, A., & Vandenberghe, L. (2013). Nuclear norm system identificationwithmissing inputs and outputs. Systems & Control Letters, 62, 605-612.
20. Ljung, L. (1999). System identification (2nd ed.). Upper Saddle River, NJ: Prentice Hall.
21. Markovsky, I. (2011). Data modeling using the nuclear norm heuristic (Technical Report 21936). Southampton: ECS, University of Southampton.
22. McGiffin, P.B., & Murthy, D.N. (1980). Parameter estimation for autoregressive systems with missing observations. International Journal of Systems Science, 11(9), 1021-1034.
23. McGiffin, P.B., & Murthy, D.N. (1981). Parameter estimation for autoregressive systems with missing observations-part II. International Journal of Systems Science, 12(6), 657-663.
24. Miller, R.B., & Ferreiro, O. (1984). A strategy to complete a time series with missing observations. In E. Parzen (Ed.), Time series analysis of irregularly observed data (pp. 251-275). New York, NY: Springer Verlag.
25. Penzer, J., & Shea, B. (1997). The exact likelihood of an autoregressive-moving average model with incomplete data. Biometrika, 84(4), 919-928.
26. Pillonetto, G., & Chiuso, A. (2009).ABayesian learning approach to linear system identification with missing data. In Proceedings of the Joint 48th IEEE Conference on Decision and Control and 28th Chinese Control Conference (pp. 4698-4703). Shanghai, China.
27. Pintelon, R., & Schoukens, J. (2000). Frequency domain system identification with missing data. IEEE Transactions on Automatic control, 45(2), 364-369.
28. Rosen, Y., & Porat, B. (1989). Optimal ARMA parameter estimation based on the sample covariances for data with missing observation. IEEE Transactions on Information Theory, 35(12), 342-349.
29. Sanchis, R., Sala, A., & Albertos, P. (1997). Scarce data operating conditions: Process model identification. In Preprints of the 11th IFAC Symposium on System Identification (Vol. 2, pp. 463-468). Kitakyushu, Japan.
30. Sargan, J.D., & Drettakis, E.G. (1974).Missing data in autoregressive model. International Economic Review, 15(1), 39-58.
31. Söderström, T., & Stoica, P. (1989). System identification. Upper Saddle River, NJ: Prentice Hall.
32. Stoica, P., Xu, L., & Li, J. (2005). A new type of parameter estimation algorithm for missing data problems. Statistics & Probability Letters, 75, 219-229.
33. Tanaka, M. (1996). Identification of nonlinear systems with missing data using stochastic neural network. In Proceedings of 35th IEEE Conference on Decision and Control (Vol. 1, pp. 933-934). Kobe, Japan.
34. Tanaka, M., & Katayama, T. (1990). Robust identification and smoothing for linear system with outliers and missing data. In Preprints 11th IFAC World Congress (pp. 160-165). Tallinn, Estonia, USSR.
35. Wallin, R., Isaksson, A.J., & Ljung, L. (2000). An iterative method for identification of ARX models subject to missing data. Proceedings of the 39th IEEE Conference on Decision and Control. Sydney, Australia.
36. Weinstein, E., Feder, M., & Oppenheim, A.V. (1990). Sequential algorithms for parameter estimation based on the Kullback-Leibler information measure. IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-38, 1652-1654.