×

Continuous time modeling of panel data: SEM versus filter techniques. (English) Zbl 1151.62074

Summary: Although convincing arguments have been put forward for continuous-time modeling, its use in panel research is rare. In one approach, classical \(N = 1\) state-space modeling procedures are adapted for panel analysis to estimate the exact discrete model (EDM) by means of filter techniques. Based on earlier less satisfactory indirect methods, a more recent approach uses structural equation modeling (SEM) to get the maximum likelihood estimate of the EDM by the direct method. After an introduction into continuous-time state-space modeling for panel data and the EDM, a thorough comparison is made between the two distinct approaches with quite different histories by means of Monte Carlo simulation studies. The model used in the simulation studies is the damped linear oscillator with and without random subject effects.

MSC:

62M20 Inference from stochastic processes and prediction
65C05 Monte Carlo methods

Software:

LISREL; LSDE
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Anderson T. W., An introduction to multivariate statistical analysis (1958) · Zbl 0083.14601
[2] Arminger G, Sociological methodology pp 187– (1986)
[3] Arnold L., Stochastic differential equations (1974) · Zbl 0278.60039
[4] Bartlett M. S., Journal of the Royal Statistical Society (Supplement) 7 pp 27– (1946)
[5] Bergstrom A. R, Handbook of econometrics pp 1145– (1984)
[6] Bergstrom A. R., Econometric Theory 4 pp 365– (1988)
[7] Boker S., Recent developments on structural equation models: theory and applications pp 151– (2004)
[8] Browne M. W, Handbook of statistical modeling for the social and behavioral sciences pp 185– (1995)
[9] Caines P. E., IEEE Transactions on Information Theory 20 pp 102– (1974)
[10] Coleman J. S, Methodology in social research pp 428– (1968)
[11] DOI: 10.1016/0304-4149(86)90018-9 · Zbl 0608.62095
[12] Gandolfo G, Continuous time econometrics pp 1– (1993)
[13] Goodrich R. L., IEEE Transactions on Automatic Control 24 pp 403– (1979)
[14] Hamerle A., Journal of Mathematical Sociology 16 pp 201– (1991)
[15] Hamerle A., Econometric Theory 9 pp 283– (1993)
[16] Jazwinski A. H., Stochastic processes and filtering theory (1970) · Zbl 0203.50101
[17] Jones R. H, Handbook of statistics pp 157– (1985)
[18] Jones R. H., Longitudinal data with serial correlation: a state space approach (1993) · Zbl 0851.62059
[19] Joreskog K. G, Structural equation models in the social sciences pp 85– (1973)
[20] Joreskog K. G, LISREL III: estimation of linear structural equation systems by maximum likelihood methods: a FORTRAN IV program (1976)
[21] Joreskog K. G., LISREL 8: User’s reference guide (1996)
[22] Liptser R. S, Statistics of random processes (1978)
[23] Mehra R. K., AIAA Journal 9 pp 28– (1971)
[24] DOI: 10.1007/BF02294246 · Zbl 0603.62099
[25] DOI: 10.1007/BF02295422 · Zbl 0825.92165
[26] Neale M. C, Modeling longitudinal and multilevel data pp 219– (2000)
[27] Neale M. C., Mx: Statistical Modeling (1999)
[28] Oud J. H. L, Systeem-methodologie in sociaal-wetenschappelijk onderzoek [Systems methodology in social science research] (1978)
[29] J. H. L. Oud, K. Van Montfort, J. Oud, and A. Satorra(2004 ), SEM state space modeling of panel data in discrete and continuous time and its relationship to traditional state space modeling , in: (eds.),Recent developments on structural equation models: theory and applications, Kluwer Academic Publishers, Dordrecht, 13 -40 . · Zbl 05196645
[30] Oud J. H. L, Data analytic techniques for dynamical systems pp 87– (2007)
[31] Oud J. H. L, Longitudinal models in the behavioral and related sciences pp 19– (2007)
[32] Oud J. H. L., Analysis of change: advanced techniques in panel data analysis pp 135– (1996)
[33] DOI: 10.1007/BF02294374 · Zbl 1291.62240
[34] Oud J. H. L., Advances in longitudinal and multivariate analysis in the behavioral sciences pp 3– (1993)
[35] DOI: 10.2307/2285651 · Zbl 0289.62058
[36] Phillips P. C. B, Models, methods, and applications of econometrics pp 12– (1993)
[37] DOI: 10.1109/TIT.1965.1053737 · Zbl 0127.10805
[38] Shumway R. H., Journal of Time Series Analysis 3 pp 253– (1982) · Zbl 0566.62058
[39] Shumway R. H., Time series analysis and its applications (2000) · Zbl 0942.62098
[40] Singer H., Parameterschatzung in zeitkontinuierlichen dynamischen Systemen [Parameter estimation in continuous time dynamic systems] (1990)
[41] H. Singer(1991 ),LSDE - a program package for the simulation, graphical display, optimal filtering and maximum likelihood estimation of linear stochastic differential equations: User’s guide, Author, Meersburg.
[42] Singer H., Zeitkontinuierliche dynamische Systeme [Continuous time dynamic systems] (1992)
[43] Singer H., Journal of Mathematical Sociology 17 pp 39– (1992)
[44] Singer H., Journal of Time Series Analysis 14 pp 527– (1993)
[45] Singer H., Econometric Theory 11 pp 721– (1995)
[46] Singer H., Journal of Mathematical Sociology 23 pp 77– (1998)
[47] Singer H., SEM - linear structural equation models with arbitrary nonlinear parameter restrictions (2004)
[48] Singer H., Longitudinal models in the behavioral and related sciences pp 73– (2007)
[49] Tuma N. B., Social dynamics (1984)
[50] Wothke W, Modeling longitudinal and multilevel data pp 219– (2000)
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.