Skip to main content
SpringerLink
Log in

Model Specification and Model Performance

  • Chapter
  • First Online:
Bayesian Inference of State Space Models

Part of the book series: Springer Texts in Statistics ((STS))

  • 2553 Accesses

Abstract

The topics of model, parameter specification and design are discussed in this chapter. We start by discussing model components, such us design matrices which lead to specific model specifications, such us trend and seasonal models, or dynamic-regression models. The specification and estimation of variance components is discussed in some detail: we review Bayesian conjugate estimation, discounting and estimation via the expectation-maximisation (EM) algorithm. The important topic of model decomposition is discussed in some detail by employing companion matrices. According to this a complex state space model, exhibiting trend, autoregressive and seasonal components can be decomposed into simple components state space models. Prior specification and the effect of choosing a weakly informative prior are discussed. The chapter concludes by developing and implementing a sequential model monitoring technique as a means of continuously assessing model performance.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 139.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  • Anderson, B. D. O., & Moore, J. B. (1979). Optimal filtering. Englewood Cliffs, NJ: Prentice Hall.

    MATH  Google Scholar 

  • Anderson, O. D. (1976). Time series analysis and forecasting: The Box-Jenkins approach. Butterworths. Series R.

    Google Scholar 

  • Atkinson, A. C., Koopman, S. J., & Shephard, N. (1997). Detecting shocks: Outliers and breaks in time series. Journal of Econometrics, 80(2), 387–422.

    Article  MathSciNet  MATH  Google Scholar 

  • Beck, N. (1983). Time-varying parameter regression models. American Journal of Political Science, 27, 557–600.

    Article  Google Scholar 

  • Bersimis, S., Psarakis, S., & Panaretos, J. (2007). Multivariate statistical process control charts: an overview. Quality and Reliability Engineering International, 23(5), 517–543.

    Article  Google Scholar 

  • Bingham, N. H., & Fry, J. M. (2010). Regression: Linear models in statistics. New York: Springer.

    Book  MATH  Google Scholar 

  • Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (2008). Time series analysis: Forecasting and control (4th ed.). New York: Wiley.

    Book  MATH  Google Scholar 

  • Brockwell, P. J., & Davis, R. A. (1991). Time series: Theory and methods (2nd ed.). New York: Springer.

    Book  MATH  Google Scholar 

  • Brown, R. G. (1962). Smoothing, forecasting and prediction of discrete time series. Englewood Cliffs, NJ: Prentice-Hall.

    Google Scholar 

  • Chan, S. W., Goodwin, G. C., & Sin, K. S. (1984). Convergence properties of the Riccati difference equation in optimal filtering of nonstabilizable systems. IEEE Transactions in Automatic Control, 29, 10–18.

    MathSciNet  MATH  Google Scholar 

  • Chib, S., & Tiwari, R. C. (1994). Outlier detection in the state space model. Statistics and Probability Letters, 20(2), 143–148.

    Article  MathSciNet  MATH  Google Scholar 

  • Cobb, G. W. (1978). The problem of the Nile: conditional solution to a change-point problem. Biometrika, 65, 243–251.

    Article  MathSciNet  MATH  Google Scholar 

  • Commandeur, J. J. F., & Koopman, S. J. (2007). An introduction to state space time series analysis. Oxford: Oxford University Press.

    MATH  Google Scholar 

  • Cooper, J. D., & Harrison, P. J. (1997). A Bayesian approach to modelling the observed bovine spongiform encephalopathy epidemic. Journal of Forecasting, 16, 355–374.

    Article  Google Scholar 

  • Davis, H. T. (1941). The analysis of economic time series, cowles commission monograph no. 6. Bloomington, Indiana: Principia Press.

    Google Scholar 

  • De Jong, P., & Penzer, J. R. (1998). Diagnosing shocks in time series. Journal of the American Statistical Association, 93, 796–806.

    Article  MathSciNet  MATH  Google Scholar 

  • De Jong, P., & Penzer, J. R. (2004). The ARMA model in state space form. Statistics and Probability Letters, 70, 119–125.

    Article  MathSciNet  MATH  Google Scholar 

  • Durbin, J., & Koopman, S. J. (2012). Time series analysis by state space methods (2nd ed.). Oxford: Oxford University Press.

    Book  MATH  Google Scholar 

  • Dyke, P. P. G. (1999). An introduction to Laplace transforms and Fourier series. New York: Springer.

    MATH  Google Scholar 

  • Gamerman, D., & Lopes, H. F. (2006). Markov chain Monte Carlo: Stochastic simulation for Bayesian inference (2nd ed.). New York: Chapman and Hall.

    Book  MATH  Google Scholar 

  • Godolphin, E. J., & Harrison, P. J. (1975). Equivalence theorems for polynomial projecting predictors. Journal of the Royal Statistical Society Series B, 37, 205–215.

    MathSciNet  MATH  Google Scholar 

  • Godolphin, E. J., & Johnson, S. E. (2003). Decomposition of time series dynamic linear models. Journal of Time Series Analysis, 24, 513–527.

    Article  MathSciNet  MATH  Google Scholar 

  • Godolphin, E. J., & Stone, J. M. (1980). On the structural representation for polynomial-projecting predictor models based on the Kalman filter. Journal of the Royal Statistical Society Series B, 42, 35–45.

    MathSciNet  MATH  Google Scholar 

  • Godolphin, E. J., & Triantafyllopoulos, K. (2006). Decomposition of time series models in state-space form. Computational Statistics and Data Analysis, 50, 2232–2246.

    Article  MathSciNet  MATH  Google Scholar 

  • Hannan, E. J., & Deistler, M. (1988). The statistical theory of linear systems. New York: Wiley.

    MATH  Google Scholar 

  • Harrison, P. J. (1965). Short-term sales forecasting. Applied Statistics, 15, 102–139.

    Article  Google Scholar 

  • Harrison, P. J., & Stevens, C. (1976). Bayesian forecasting (with discussion). Journal of the Royal Statistical Society Series B, 38, 205–247.

    MathSciNet  MATH  Google Scholar 

  • Harvey, A. C. (1989). Forecasting, structural time series and the Kalman filter. Cambridge: Cambridge University Press.

    Google Scholar 

  • Harvey, A. C. (2004). Tests for cycles. In A. C. Harvey, S. J. Koopman, & N. Shephard (Eds.), State space and unobserved component models: Theory and applications (pp. 102–119). Cambridge: Cambridge University Press.

    Chapter  Google Scholar 

  • Harvey, A. C., & Koopman, S. J. (1992). Diagnostic checking of unobserved-components time series models. Journal of Business and Economic Statistics, 10(4), 377–389.

    Google Scholar 

  • Haykin, S. (2001). Adaptive filter theory (4th ed.). New Jersey: Prentice Hall.

    MATH  Google Scholar 

  • Hilmer, S. C., & Tiao, G. C. (1982). An arima-model-based approach to seasonal adjustment. Journal of the American Statistical Association, 77, 63–70.

    Article  MathSciNet  MATH  Google Scholar 

  • Horn, R. A., & Johnson, C. R. (2013). Matrix analysis (2nd ed.). Cambridge: Cambridge University Press.

    MATH  Google Scholar 

  • Jacobson, N. (1953). Lectures in abstract Algebra. New York: Van Nostrand.

    Book  MATH  Google Scholar 

  • Jazwinski, A. H. (1970). Stochastic processes and filtering theory. New York: Academic Press.

    MATH  Google Scholar 

  • Kalaba, R., & Tesfatsion, L. (1988). The flexible least squares approach to time-varying linear regression. Journal of Economic Dynamics and Control, 12, 43–48.

    Article  MATH  Google Scholar 

  • Kitagawa, G., & Gersch, W. (1996). Smoothness priors analysis of time series. New York: Springer.

    Book  MATH  Google Scholar 

  • Koopman, S. J. (1997). Exact initial Kalman filtering and smoothing for non-stationary time series models. Journal of the American Statistical Association, 92, 1630–1638.

    Article  MathSciNet  MATH  Google Scholar 

  • Lundbergh, S., Teräsvirta, T., & van Dijk, D. (2003). Time-varying smooth transition autoregressive models. Journal of Business and Economic Statistics, 21, 104–121.

    Article  MathSciNet  Google Scholar 

  • McCulloch, R. E., & Tsay, R. S. (1993). Bayesian inference and prediction for mean and variance shifts in autoregressive time series. Journal of the American Statistical Association, 88(423), 968–978.

    Article  MATH  Google Scholar 

  • Molinari, D. A. (2009). Monitoring and adaptation in time series models, MSc thesis, School of Mathematics and Statistics, University of Sheffield.

    Google Scholar 

  • Montana, G., Triantafyllopoulos, K., & Tsagaris, T. (2009). Flexible least squares for temporal data mining and statistical arbitrage. Expert Systems with Applications, 36, 2819–2830.

    Article  Google Scholar 

  • Pankratz, A. (1991). Forecasting with dynamic regression models. New York: Wiley.

    Book  Google Scholar 

  • Petris, G. (2010). An R package for dynamic linear models. Journal of Statistical Software, 36, 1–16.

    Article  Google Scholar 

  • Petris, G., Petrone, S., & Campagnoli, P. (2009). Dynamic linear models with R. New York: Springer.

    Book  MATH  Google Scholar 

  • Pole, A., West, M., & Harrison, P. J. (1994). Applied Bayesian forecasting and time series analysis. New York: Chapman and Hall.

    Book  MATH  Google Scholar 

  • Prado, R., & West, M. (2010). Time series: Modeling, computation, and inference. New York: Chapman and Hall.

    Book  MATH  Google Scholar 

  • Rao, M. J. M. (2000). Estimating time-varying parameters in linear regression models using a two-part decomposition of the optimal control formulation. Sankhyā Series B, 62, 433–447.

    MathSciNet  MATH  Google Scholar 

  • Rudin, W. (1976). Principles of mathematical analysis (3rd ed.). New York: McGraw-Hill.

    MATH  Google Scholar 

  • Salvador, M., & Gargallo, P. (2003). Automatic selective intervention in dynamic linear models. Journal of Applied Statistics, 30(10), 1161–1184.

    Article  MathSciNet  MATH  Google Scholar 

  • Salvador, M., & Gargallo, P. (2004). Automatic monitoring and intervention in multivariate dynamic linear models. Computational Statistics and Data Analysis, 47(3), 401-431.

    Article  MathSciNet  MATH  Google Scholar 

  • Shephard, N. (1994b). Partial non-Gaussian state space models. Biometrika, 81, 115–131.

    Article  MathSciNet  MATH  Google Scholar 

  • Shumway, R. H., & Stoffer, D. S. (1982). An approach to time series smoothing and forecasting using the EM algorithm. Journal of Time Series Analysis, 3, 253–264.

    Article  MATH  Google Scholar 

  • Shumway, R. H., & Stoffer, D. S. (2017). Time series analysis and its applications: With R examples (4th ed.). New York: Springer.

    Book  MATH  Google Scholar 

  • Tesfatsion, L., & Kalaba, R. (1989). Time-varying linear regression via flexible least squares. Computers and Mathematics with Applications, 17, 1215–1245.

    Article  MathSciNet  MATH  Google Scholar 

  • Tong, H. (1996). Non-linear time series. Oxford: Clarendon Press.

    Google Scholar 

  • Triantafyllopoulos, K. (2007a). Convergence of discount time series dynamic linear models. Communications in Statistics - Theory and Methods, 36, 2117–2127.

    Article  MathSciNet  MATH  Google Scholar 

  • Triantafyllopoulos, K. (2007b). Covariance estimation for multivariate conditionally Gaussian dynamic linear models. Journal of Forecasting, 26, 551–569.

    Article  MathSciNet  Google Scholar 

  • Triantafyllopoulos, K. (2011b). Time-varying vector autoregressive models with stochastic volatility. Journal of Applied Statistics, 38, 369–382.

    Article  MathSciNet  MATH  Google Scholar 

  • Triantafyllopoulos, K., & Harrison, P. J. (2008). Posterior mean and variance approximation for regression and time series problems. Statistics: A Journal of Theoretical and Applied Statistics, 42, 329–350.

    Article  MathSciNet  MATH  Google Scholar 

  • Triantafyllopoulos, K., & Montana, G. (2011). Dynamic modeling of mean-reverting spreads for statistical arbitrage. Computational Management Science, 8, 23–49.

    Article  MathSciNet  MATH  Google Scholar 

  • Triantafyllopoulos, K., & Nason, G. P. (2007). A Bayesian analysis of moving average processes with time-varying parameters. Computational Statistics and Data Analysis, 52, 1025–1046.

    Article  MathSciNet  MATH  Google Scholar 

  • Triantafyllopoulos, K., & Nason, G. P. (2009). A note on state-space representations of locally stationary wavelet time series. Statistics and Probability Letters, 79, 50–54.

    Article  MathSciNet  MATH  Google Scholar 

  • West, M. (1986). Bayesian model monitoring. Journal of the Royal Statistical Society Series B, 48, 70–78.

    MathSciNet  MATH  Google Scholar 

  • West, M. (1997). Time series decomposition. Biometrika, 84, 489–494.

    Article  MATH  Google Scholar 

  • West, M., & Harrison, P. J. (1986). Monitoring and adaptation in Bayesian forecasting models. Journal of the American Statistical Association, 81, 741–750.

    Article  MATH  Google Scholar 

  • West, M., & Harrison, P. J. (1997). Bayesian forecasting and dynamic models (2nd ed.). New York: Springer.

    MATH  Google Scholar 

  • West, M., Prado, R., & Krystal, A. D. (1999). Evaluation and comparison of EEG traces: latent structure in nonstationary time series. Journal of the American Statistical Association, 94, 375–387.

    Article  Google Scholar 

  • Whittle, P. (1984). Prediction and Regulation by linear least-square methods (2nd ed.). Oxford: Blackwell.

    Google Scholar 

  • Yule, G. U. (1927). On a method of investigating periodicities in disturbed series with special reference to Wolfer’s sunspot numbers. Philosophical Transactions, Royal Society, 226, 267–298.

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Mathematics, University of Sheffield, Sheffield, UK

    Kostas Triantafyllopoulos

Authors
  1. Kostas Triantafyllopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Triantafyllopoulos, K. (2021). Model Specification and Model Performance. In: Bayesian Inference of State Space Models. Springer Texts in Statistics. Springer, Cham. https://doi.org/10.1007/978-3-030-76124-0_4

Download citation

Publish with us

Policies and ethics

Search

Navigation