An Assessment of Alternative State Space Models for Count Time Series
AbstractThis paper compares two alternative models for autocorrelated count time series. The first model can be viewed as a 'single source of error' discrete state space model, in which a time-varying parameter is specified as a function of lagged counts, with no additional source of error introduced. The second model is the more conventional 'dual source of error' discrete state space model, in which the time-varying parameter is driven by a random autocorrelated process. Using the nomenclature of the literature, the two representations can be viewed as observation-driven and parameter-driven respectively, with the distinction between the two models mimicking that between analogous models for other non-Gaussian data such as financial returns and trade durations. The paper demonstrates that when adopting a conditional Poisson specification, the two models have vastly different dispersion/correlation properties, with the dual source model having properties that are a much closer match to the empirical properties of observed count series than are those of the single source model. Simulation experiments are used to measure the finite sample performance of maximum likelihood (ML) estimators of the parameters of each model, and ML-based predictors, with ML estimation implemented for the dual source model via a deterministic hidden Markov chain approach. Most notably, the numerical results indicate that despite the very different properties of the two models, predictive accuracy is reasonably robust to misspecification of the state space form.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by Monash University, Department of Econometrics and Business Statistics in its series Monash Econometrics and Business Statistics Working Papers with number 4/07.
Length: 28 pages
Date of creation: May 2007
Date of revision:
Contact details of provider:
Postal: PO Box 11E, Monash University, Victoria 3800, Australia
Web page: http://www.buseco.monash.edu.au/depts/ebs/
More information through EDIRC
Find related papers by JEL classification:
- C13 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General - - - Estimation: General
- C22 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models &bull Diffusion Processes
- C46 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Specific Distributions
- C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods
This paper has been announced in the following NEP Reports:
- NEP-ALL-2007-05-12 (All new papers)
- NEP-ECM-2007-05-12 (Econometrics)
- NEP-ETS-2007-05-12 (Econometric Time Series)
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- HEINEN, Andréas, 2003.
"Modelling time series count data: an autoregressive conditional Poisson model,"
CORE Discussion Papers
2003062, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
- Heinen, Andreas, 2003. "Modelling Time Series Count Data: An Autoregressive Conditional Poisson Model," MPRA Paper 8113, University Library of Munich, Germany.
- B.P.M. McCabe & G.M. Martin & R.K. Freeland, 2004.
"Testing for Dependence in Non-Gaussian Time Series Data,"
Monash Econometrics and Business Statistics Working Papers
13/04, Monash University, Department of Econometrics and Business Statistics.
- Keith Freeland & Brendan McCabe & Gael Martin, 2004. "Testing for Dependence in Non-Gaussian Time Series Data," Econometric Society 2004 Australasian Meetings 313, Econometric Society.
- Sangjoon Kim & Neil Shephard, 1994.
"Stochastic volatility: likelihood inference and comparison with ARCH models,"
3., Economics Group, Nuffield College, University of Oxford.
- Kim, Sangjoon & Shephard, Neil & Chib, Siddhartha, 1998. "Stochastic Volatility: Likelihood Inference and Comparison with ARCH Models," Review of Economic Studies, Wiley Blackwell, vol. 65(3), pages 361-93, July.
- Sangjoon Kim, Neil Shephard & Siddhartha Chib, . "Stochastic volatility: likelihood inference and comparison with ARCH models," Economics Papers W26, revised version of W, Economics Group, Nuffield College, University of Oxford.
- Sangjoon Kim & Neil Shephard & Siddhartha Chib, 1996. "Stochastic Volatility: Likelihood Inference And Comparison With Arch Models," Econometrics 9610002, EconWPA.
- J. Durbin & S. J. Koopman, 2000.
"Time series analysis of non-Gaussian observations based on state space models from both classical and Bayesian perspectives,"
Journal of the Royal Statistical Society Series B,
Royal Statistical Society, vol. 62(1), pages 3-56.
- Durbin, J. & Koopman, S.J.M., 1998. "Time Series Analysis of Non-Gaussian Observations Based on State Space Models from Both Classical and Bayesian Perspectives," Discussion Paper 1998-142, Tilburg University, Center for Economic Research.
- Freeland, R. K. & McCabe, B. P. M., 2004. "Forecasting discrete valued low count time series," International Journal of Forecasting, Elsevier, vol. 20(3), pages 427-434.
- Ord, J.K. & Koehler, A. & Snyder, R.D., 1995. "Estimation and Prediction for a Class of Dynamic Nonlinear Statistical Models," Monash Econometrics and Business Statistics Working Papers 4/95, Monash University, Department of Econometrics and Business Statistics.
- Bauwens, Luc & Veredas, David, 2004.
"The stochastic conditional duration model: a latent variable model for the analysis of financial durations,"
Journal of Econometrics,
Elsevier, vol. 119(2), pages 381-412, April.
- BAUWENS, Luc & VEREDAS, David, . "The stochastic conditional duration model: a latent variable model for the analysis of financial durations," CORE Discussion Papers RP -1688, Université catholique de Louvain, Center for Operations Research and Econometrics (CORE).
- Strickland, Chris M. & Forbes, Catherine S. & Martin, Gael M., 2006.
"Bayesian analysis of the stochastic conditional duration model,"
Computational Statistics & Data Analysis,
Elsevier, vol. 50(9), pages 2247-2267, May.
- Chris M. Strickland & Catherine S. Forbes & Gael M. Martin, 2003. "Bayesian Analysis of the Stochastic Conditional Duration Model," Monash Econometrics and Business Statistics Working Papers 14/03, Monash University, Department of Econometrics and Business Statistics.
- Richard A. Davis, 2003. "Observation-driven models for Poisson counts," Biometrika, Biometrika Trust, vol. 90(4), pages 777-790, December.
- Harvey,Andrew C., 1990.
"Forecasting, Structural Time Series Models and the Kalman Filter,"
Cambridge University Press, number 9780521321969.
- Harvey,Andrew C., 1991. "Forecasting, Structural Time Series Models and the Kalman Filter," Cambridge Books, Cambridge University Press, number 9780521405737.
- R. K. Freeland & B. P. M. McCabe, 2004. "Analysis of low count time series data by poisson autoregression," Journal of Time Series Analysis, Wiley Blackwell, vol. 25(5), pages 701-722, 09.
- McCabe, B.P.M. & Martin, G.M., 2005. "Bayesian predictions of low count time series," International Journal of Forecasting, Elsevier, vol. 21(2), pages 315-330.
- Durbin, James & Koopman, Siem Jan, 2001.
"Time Series Analysis by State Space Methods,"
Oxford University Press, number 9780198523543, October.
- Tom Doan, . "SEASONALDLM: RATS procedure to create the matrices for the seasonal component of a DLM," Statistical Software Components RTS00251, Boston College Department of Economics.
- Rong Zhu & Harry Joe, 2006. "Modelling Count Data Time Series with Markov Processes Based on Binomial Thinning," Journal of Time Series Analysis, Wiley Blackwell, vol. 27(5), pages 725-738, 09.
- Harvey, Andrew C & Fernandes, C, 1989. "Time Series Models for Count or Qualitative Observations," Journal of Business & Economic Statistics, American Statistical Association, vol. 7(4), pages 407-17, October.
- Jung, Robert C. & Kukuk, Martin & Liesenfeld, Roman, 2006. "Time series of count data: modeling, estimation and diagnostics," Computational Statistics & Data Analysis, Elsevier, vol. 51(4), pages 2350-2364, December.
- Sylvia Fr�Hwirth-Schnatter & Helga Wagner, 2006. "Auxiliary mixture sampling for parameter-driven models of time series of counts with applications to state space modelling," Biometrika, Biometrika Trust, vol. 93(4), pages 827-841, December.
- Jung, Robert & Kukuk, Martin & Liesenfeld, Roman, 2005. "Time Series of Count Data : Modelling and Estimation," Economics Working Papers 2005,08, Christian-Albrechts-University of Kiel, Department of Economics.
- Scott I. White & Adam E. Clements & Stan Hurn, 2004. "Discretised Non-Linear Filtering for Dynamic Latent Variable Models: with Application to Stochastic Volatility," Econometric Society 2004 Australasian Meetings 46, Econometric Society.
- Neil Shephard, 1995. "Generalized linear autoregressions," Economics Papers 8., Economics Group, Nuffield College, University of Oxford.
- Engle, Robert F, 1982. "Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation," Econometrica, Econometric Society, vol. 50(4), pages 987-1007, July.
- Ralph D. Snyder & Adrian Beaumont, 2007. "A Comparison of Methods for Forecasting Demand for Slow Moving Car Parts," Monash Econometrics and Business Statistics Working Papers 15/07, Monash University, Department of Econometrics and Business Statistics.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Simone Grose).
If references are entirely missing, you can add them using this form.