Bayesian Model Selection and Prediction with Empirical Applications
This paper builds on some recent work by the author and Werner Ploberger (1991, 1994) on the development of "Bayes models" for time series and on the authors' model selection criterion "PIC." The PIC criterion is used in this paper to determine the lag order, the trend degree, and the presence or absence of a unit root in an autoregression with deterministic trend. A new forecast encompassing test for Bayes models is developed which allows one Bayes model to be compared with another on the basis of their respective forecasting performance. The paper reports an extended empirical application of the methodology to the Nelson-Plosser (1982)/Schotman-van Dijk (1991) data. It is shown that parsimonious, evolving-format Bayes models forecast-encompass fixed Bayes models of the "AR(3) + linear trend" variety for most of these series. In some cases, the forecast performance of the parsimonious Bayes models is substantially superior. The results cast some doubts on the value of working with fixed format time series models in empirical research and demonstrate the practical advantages of evolving-format models. The paper makes a new suggestion for modelling interest rates in terms of reciprocals of levels rather than levels (which display more volatility) and shows that the best data-determined model for this transformed series is a martingale. Keywords: Bayes model, Bayes measure, BIC, forecast, forecast-encompass, model selection, PIC, unit root
|Date of creation:||Jul 1992|
|Date of revision:|
|Publication status:||Published in Journal of Econometrics (1995), 69: 289-331|
|Contact details of provider:|| Postal: Yale University, Box 208281, New Haven, CT 06520-8281 USA|
Phone: (203) 432-3702
Fax: (203) 432-6167
Web page: http://cowles.yale.edu/
More information through EDIRC
|Order Information:|| Postal: Cowles Foundation, Yale University, Box 208281, New Haven, CT 06520-8281 USA|
References listed on IDEAS
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.:
- DeJong, David N. & Whiteman, Charles H., 1991. "Reconsidering 'trends and random walks in macroeconomic time series'," Journal of Monetary Economics, Elsevier, vol. 28(2), pages 221-254, October.
- Nelson, Charles R. & Plosser, Charles I., 1982. "Trends and random walks in macroeconmic time series : Some evidence and implications," Journal of Monetary Economics, Elsevier, vol. 10(2), pages 139-162.
- Florens, Jean-Pierre & Larribeau, Sophie & Mouchart, Michel, 1994.
"Bayesian Encompassing Tests of a Unit Root Hypothesis,"
Cambridge University Press, vol. 10(3-4), pages 747-763, August.
- Florens, J.P. & Mouchart, M. & Larribeau-Nori, S., 1992. "Bayesian Encompassing Tests of Unit Root Hypothesis," Papers 92.274, Toulouse - GREMAQ.
- Phillips, Peter C.B., 1994.
"Spurious Regression in Forecast-Encompassing Tests,"
Cambridge University Press, vol. 10(3-4), pages 818-819, August.
- Phillips, Peter C.B., 1995. "Spurious Regression in Forecast-Encompassing Tests," Econometric Theory, Cambridge University Press, vol. 11(05), pages 1188-1190, October.
- Durlauf, Steven N & Phillips, Peter C B, 1988.
"Trends versus Random Walks in Time Series Analysis,"
Econometric Society, vol. 56(6), pages 1333-54, November.
- Steven N. Durlauf & Peter C.B. Phillips, 1986. "Trends Versus Random Walks in Time Series Analysis," Cowles Foundation Discussion Papers 788, Cowles Foundation for Research in Economics, Yale University.
- Phillips, Peter C.B. & Ploberger, Werner, 1994.
"Posterior Odds Testing for a Unit Root with Data-Based Model Selection,"
Cambridge University Press, vol. 10(3-4), pages 774-808, August.
- Peter C.B. Phillips & Werner Ploberger, 1992. "Posterior Odds Testing for a Unit Root with Data-Based Model Selection," Cowles Foundation Discussion Papers 1017, Cowles Foundation for Research in Economics, Yale University.
- Min, Chung-ki & Zellner, Arnold, 1993.
"Bayesian and non-Bayesian methods for combining models and forecasts with applications to forecasting international growth rates,"
Journal of Econometrics,
Elsevier, vol. 56(1-2), pages 89-118, March.
- Min, C.K. & Zellner, A., 1992. ""Bayesian and Non-Bayesian Methods for Combining Models and Forecasts with Applications to Forecasting International Growth Rates"," Papers 90-92-23, California Irvine - School of Social Sciences.
- Peter C.B. Phillips, 1985.
"Understanding Spurious Regressions in Econometrics,"
Cowles Foundation Discussion Papers
757, Cowles Foundation for Research in Economics, Yale University.
- Phillips, P.C.B., 1986. "Understanding spurious regressions in econometrics," Journal of Econometrics, Elsevier, vol. 33(3), pages 311-340, December.
- Peter C. Schotman & Herman K. van Dijk, 1991.
"On Bayesian routes to unit roots,"
Discussion Paper / Institute for Empirical Macroeconomics
43, Federal Reserve Bank of Minneapolis.
- Peter C.B. Phillips & Werner Ploberger, 1991. "Time Series Modelling with a Bayesian Frame of Reference: 1. Concepts and Illustrations," Cowles Foundation Discussion Papers 980, Cowles Foundation for Research in Economics, Yale University.
When requesting a correction, please mention this item's handle: RePEc:cwl:cwldpp:1023. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Matthew C. Regan)
If references are entirely missing, you can add them using this form.