ARMA Model Identification Using the Bayes Factor

  • Published : 1999.12.01

Abstract

The Bayes factor for the identification of stationary ARM(p,q) models is exactly computed using the Monte Carlo method. As priors are used the uniform prior for (\ulcorner,\ulcorner) in its stationarity-invertibility region, the Jefferys prior and the reference prior that are noninformative improper for ($\mu$,$\sigma$\ulcorner).

Keywords

References

  1. IEEE Transaction on Automatic Control v.AC-19 A New Look at the Statistical Model Identification Akaike, H.
  2. Technical Report, 93-43C, Department of Statistics, Purdue University The Intrinsic Bayes Factor for Model Selection and Prediction Berger, J. O.;Pericchi, L. R.
  3. Journal of the American Statistical Association v.91 no.433 The Intrinsic Bayes Factor for Model Selection and Prediction Berger, J. O.;Pericchi, L. R.
  4. Time Series Analysis: forecasting and control Box, G.E.P.;Jenkins, G.M.
  5. ARMA Model Identification Choi, B.S.
  6. Theory of Probability Jefferys, H.
  7. Applied Statistics v.36 no.2 Randomly Choosing Parameters from the Stationarity and Invertibility Region of Autoregressive-Moving Average Models Jones, M.C.
  8. Journal of Econometrics v.63 The Covariance Matrix of ARMA Errors in Closed Form Leeuw, J.V.D.
  9. Journal of Econometrics v.21 Fully Bayesian Analysis of ARMA Time Series Models Monahan, J.F.
  10. Biometrika v.71 no.2 A Note on Enforcing Stationarity in Autoregressive-Moving Average Models Monahan, J.F.
  11. The Annals of Statistics v.6 Estimating the Dimension of a Model Schwarz, G.
  12. Bayesian Statistics v.6 Intrinsic Bayes Factor for Model Selection with Autoregressive Data Varshavsky, J.A.
  13. Time Series analysis Wei, W.W.S.