Continuous time modeling of panel data: SEM versus filter techniques

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.

[1]  Gerhard Arminger,et al.  Linear Stochastic Differential Equation Models for Panel Data with Unobserved Variables , 1986 .

[2]  Alʹbert Nikolaevich Shiri︠a︡ev,et al.  Statistics of random processes , 1977 .

[3]  R. Shumway,et al.  AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHM , 1982 .

[4]  T. W. Anderson,et al.  An Introduction to Multivariate Statistical Analysis , 1959 .

[5]  A. Bergstrom.  The History of Continuous-Time Econometric Models , 1988, Econometric Theory.

[6]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[7]  Hermann Singer.  The aliasing‐phenomenon in visual terms , 1992 .

[8]  M. Bartlett.  On the Theoretical Specification and Sampling Properties of Autocorrelated Time‐Series , 1946 .

[9]  Hermann Singer.  Continuous panel models with time dependent parameters , 1998 .

[10]  Hermann Singer,et al.  Stochastic Differential Equation Models with Sampled Data. , 2006 .

[11]  W. Wothke.  Longitudinal and multigroup modeling with missing data. , 2000 .

[12]  R. K. Mehra,et al.  Identification of stochastic linear dynamic systems using Kalman filter representation , 1971 .

[13]  Fred C. Schweppe,et al.  Evaluation of likelihood functions for Gaussian signals , 1965, IEEE Trans. Inf. Theory.

[14]  Peter C. M. Molenaar,et al.  Dynamic factor analysis of nonstationary multivariate time series , 1992 .

[15]  David S. Stoffer,et al.  Time series analysis and its applications , 2000 .

[16]  Hermann Singer.  Analytical Score Function for Irregularly Sampled Continuous Time Stochastic Processes with Control Variables and Missing Values , 1995, Econometric Theory.

[17]  T. W. Anderson.  An Introduction to Multivariate Statistical Analysis , 1959 .

[18]  Hermann Singer,et al.  Problems with the estimation of stochastic differential equations using structural equations models , 1991 .

[19]  J. Oud,et al.  Continuous time state space modeling of panel data by means of sem , 2000 .

[20]  Karl G. Jöreskog,et al.  Lisrel 8: User's Reference Guide , 1997 .

[21]  A. Hamerle,et al.  Identification and Estimation of Continuous Time Dynamic Systems With Exogenous Variables Using Panel Data , 1993, Econometric Theory.

[22]  Johan H. L. Oud,et al.  SEM state space modeling of panel data in discrete and continuous time and its relationship to traditional state space modeling , 2004 .

[23]  Peter E. Caines,et al.  Maximum likelihood estimation of parameters in multivariate Gaussian stochastic processes (Corresp.) , 1974, IEEE Trans. Inf. Theory.

[24]  Hermann Singer,et al.  CONTINUOUS-TIME DYNAMICAL SYSTEMS WITH SAMPLED DATA, ERRORS OF MEASUREMENT AND UNOBSERVED COMPONENTS , 1993 .

[25]  Johan H. L. Oud,et al.  7. Nonstationary Longitudinal LISREL Model Estimation from Incomplete Panel Data Using EM and the Kalman Smoother , 1996 .

[26]  P. Caines,et al.  Linear system identification from non-stationary cross-sectional data , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[27]  Steven M. Boker,et al.  Latent Differential Equation Modeling with Multivariate Multi-Occasion Indicators , 2004 .

[28]  Richard H. Jones,et al.  Longitudinal Data with Serial Correlation : A State-Space Approach , 1994 .

[29]  J. Oud.  Comparison of four procedures to estimate the damped linear differential oscillator for panel , 2007 .

[30]  S. Wu,et al.  Modeling of Continuous Stochastic Processes from Discrete Observations with Application to Sunspots Data , 1974 .

[31]  Richard H. Jones.  5 Time series analysis with unequally spaced data , 1985 .

[32]  Peter C. M. Molenaar,et al.  A dynamic factor model for the analysis of multivariate time series , 1985 .

[33]  Giancarlo Gandolfo,et al.  Continuous-Time Econometrics , 1993 .

[34]  G. Arminger,et al.  Specification and Estimation of Mean- and Covariance-Structure Models , 1995 .

[35]  B. Øksendal.  Stochastic Differential Equations , 1985 .

[36]  A. Dembo,et al.  Parameter estimation of partially observed continuous time stochastic processes via the EM algorithm , 1992 .

[37]  A. Bergstrom.  CONTINUOUS TIME STOCHASTIC MODELS AND ISSUES OF AGGREGATION OVER TIME , 1984 .

[38]  Giancarlo Gandolfo,et al.  Continuous-time econometrics has come of age , 1993 .