Adaptive quadrature for likelihood inference on dynamic latent variable models for time-series and panel data

Cagnone, Silvia and Bartolucci, Francesco (2013): Adaptive quadrature for likelihood inference on dynamic latent variable models for time-series and panel data.

Abstract

Maximum likelihood estimation of dynamic latent variable models requires to solve integrals that are not analytically tractable. Numerical approximations represent a possible solution to this problem. We propose to use the Adaptive Gaussian-Hermite (AGH) numerical quadrature approximation for a class of dynamic latent variable models for time-series and panel data. These models are based on continuous time-varying latent variables which follow an autoregressive process of order 1, AR(1). Two examples of such models are the stochastic volatility models for the analysis of financial time-series and the limited dependent variable models for the analysis of panel data. A comparison between the performance of AGH methods and alternative approximation methods proposed in the literature is carried out by simulation. Examples on real data are also used to illustrate the proposed approach.

• Item Type: MPRA Paper
• Language: English
• Keywords: AR(1); categorical longitudinal data; Gaussian-Hermite quadrature; limited dependent variable models; stochastic volatility model
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C13 - Estimation: General; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C32 - Time-Series Models ; Dynamic Quantile Regressions ; Dynamic Treatment Effect Models ; Diffusion Processes ; State Space Models; C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C33 - Panel Data Models ; Spatio-temporal Models

References

T.G. Andersen (1994) Stochastic autoregressive volatility: a framework for volatility modeling. Mathematical Finance, 4:75–102.

F. Bartolucci and G. De Luca (2001) Maximum likelihood estimation for a latent variable time series model. Applied Stochastic Models for Business and Industry, 17:5–17.

F. Bartolucci and G. De Luca (2003) Likelihood-based inference for asymmetric stochastic volatility models. Computational Statistical and Data Analysis, 42:445–449.

F. Bartolucci, S. Bacci, and F. Pennoni (2013a) Longitudinal analysis of the self-reported health status by mixture latent autoregressive models. Journal of the Royal Statistical Society-series C, page in press.

F. Bartolucci, A. Farcomeni, and F. Pennoni (2013b) Latent Markov Models for Longitudinal Data. Chapman & Hall/CRC Press, Boca Raton, FL.

T. Bollerslev (1986) Generalized autoregresive conditional heteroskedasticity. Journal of Econometrics, 31:307–327.

S. Cagnone and P. Monari (2013) Latent variable models for ordinal data by using the adaptive quadrature approximation. Computational Statistics, 28:597–619.

J. Durbin and S.J. Koopman (2002) A simple and efficient simulation smmother for space time series analyis. Biometrika, 89:603–616.

E.W. Frees (2004) Longitudinal and Panel Data: Analysis and Application in Social Sciences.

M. Fridman and L. Harris (1998) A maximum likelihood approach for non-gaussian stochastic volatility models. Journal of Business and Economic Statistics, 16:284–291.

A.C. Harvey, E. Ruiz, and N. Shephard (1994) Multivariate stochastic variance models. Review of Economic Studies, 61:247–264.

F. Heiss (2008) Sequential numerical integration in nonlinear state spece models for microeconometric panel. Journal of Applied Econometrics, 23:373–389.

E. Jacquier, N.G. Polson, and P.E. Rossi (1994) Bayesian analysis of stochastic volatility models. Journal of Business and Economic Statistics, 12:371–417.

H. Joe (2008) Accuracy of laplace approximation for discrete response mixed models. Computational Statistics and Data Analysis, 52:5066–5074.

S. Junji and T. Yoshihiko (2005) Estimation of stochastic volatility models: an approximation to the nonlinear state space representation. Communications in Statistics-Simulation and Computation, 34:429–450.

Q. Liu and D.A. Pierce (1994) A note on gauss-hermite quadrature. Biometrika, 81:624–629.

G.S. Maddala (1983) Limited Dependent and Qualitative Variables in Econometrics. Cambridge University Press.

P. McCullagh (1980) Regression models for ordinal data (with discussion). Journal of the American Statistical Society, Series B, 42:109–142.

J.C. Naylor and A.F.M. Smith (1982) Applications of a method for the efficient computation of posterior distributions. Applied Statistics, 51:214–225.

J.C. Pinheiro and D.M. Bates (1995) Approximation to the loglikelihood function in the nonlinear mixed effects model. Journal of Computational and Graphical Statistics, 4:12–35.

S. Rabe-Hesketh, A. Skrondal, and A. Pickles (2002) Reliable estimation of generalized linear mixed models using adaptive quadrature. The Stata Journal, 2:1:21.

S. Rabe-Hesketh, A. Skrondal, and A. Pickles (2005) Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects. Journal of Econometrics, 128:301–323.

D. Rizopoulus (2012) Fast fitting of joint models for longitudinal and event time data using a pseudoadaptive gaussian quadrature rule. Computational Statistics and Data Analysis, 56:491–501.

S. Schilling and R.D. Bock (2005) High-dimensional maximum marginal likelihood item factor analysis by adaptive quadrature. Psychometrika, 70:533–555.

H. Tanizaki and R.S. Mariano (1998) Nonlinear and nonnormal state-space modeling with monte-carlo stochastic simulations. Journal of Econometrics, 83:263–290.

S. Taylor (1986) Modelling Financial Time Series. New York: Wiley.

S. Taylor (1994) Modeling stochastic volatility. Mathematical Finance, pages 183–204.