Forecasting Analogous Time Series

  • George T. Duncan
  • Wilpen L. Gorr
  • Janusz Szczypula

Abstract

Organizations that use time-series forecasting regularly, generally use it for many products or services. Among the variables they forecast are groups of analogous time series (series that follow similar, time-based patterns). Their covariation is a largely untapped source of information that can improve forecast accuracy. We take the Bayesian pooling approach to drawing information from analogous time series to model and forecast a given time series. In using Bayesian pooling, we use data from analogous time series as multiple observations per time period in a group-level model. We then combine estimated parameters of the group model with conventional time-series-model parameters, using so-called weights shrinkage. Major benefits of this approach are that it (1) requires few parameters for estimation; (2) builds directly on conventional time-series models; (3) adapts to pattern changes in time series, providing rapid adjustments and accurate model estimates; and (4) screens out adverse effects of outlier data points on time-series model estimates. For practitioners, we provide the terms, concepts, and methods necessary for a basic understanding of Bayesian pooling and the conditions under which it improves upon conventional time-series methods. For researchers, we describe the experimental data, treatments, and factors needed to compare the forecast accuracy of pooling methods. Last, we present basic principles for applying pooling methods and supporting empirical results. Conditions favoring pooling include time series with high volatility and outliers. Simple pooling methods are more accurate than complex methods, and we recommend manual intervention for cases with few time series.

Keywords

Analogous time series Bayesian methods multiple time series pooling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Benjamin, R.I. (1981), “Information technology in the 1990’s: A long range planning scenario,” MIS Quarterly, 6, 11–31.CrossRefGoogle Scholar
  2. Bretschneider, S. I. and W. Gorr (2000), “Projecting revenues,” in R.T. Meyers and A. Schick (ed.), Handbook of Government Budgeting. Jossey-Bass Inc.Google Scholar
  3. Bunn, D. W. and A. I. Vassilopoulos (1993), “Using group seasonal indices in multi-item short-term forecasting,” International Journal of Forecasting, 9, 517–526.CrossRefGoogle Scholar
  4. Collopy, F. and J. S. Armstrong (1992a), “Expert opinions about extrapolation and the mystery of the overlooked discontinuities,” International Journal of Forecasting, 8, 575–582. Full text at hops.wharton.upenn.edu/forecast.CrossRefGoogle Scholar
  5. Collopy, F. and J. S. Armstrong (1992b), “Rule-based forecasting: development and validation of an expert systems approach to combining time series extrapolations,” Management Science, 38, 1394–1414.CrossRefGoogle Scholar
  6. Duncan, G., W. Gorr and J. Szczypula (1993), “Bayesian forecasting for seemingly unrelated time series: Application to local government revenue forecasting ” Management Science, 39, 275–293.CrossRefGoogle Scholar
  7. Duncan, G., W. Gorr and J. Szczypula (1994), “Comparative study of cross-sectional methods for time series with structural changes,” Working Paper 94–23, Heinz School, Carnegie Mellon University.Google Scholar
  8. Duncan, G., W. Gorr and J. Szczypula (1995a), “Bayesian hierarchical forecasts for dynamic systems: Case study on backcasting school district income tax revenues,” in L. AnselinGoogle Scholar
  9. and R. Florax (eds.), New Directions in Spatial Econometrics. Berlin: Springer, 322–358.Google Scholar
  10. Duncan, G., W. Gorr and J. Szczypula (1995b), “Adaptive Bayesian Pooling Methods: Comparative Study on Forecasting Small Area Infant Mortality Rates,” Working Paper 95–7, Heinz School, Carnegie Mellon University.Google Scholar
  11. Enns, P. G., J. A. Machak, W. A. Spivey and W. J. Wroblewski (1982), “Forecasting applications of an adaptive multiple exponential smoothing model,” Management Science 28, 1035–1044.CrossRefGoogle Scholar
  12. Fildes, R. (1983), “An evaluation of Bayesian forecasting,” Journal of Forecasting, 2, 137–150.CrossRefGoogle Scholar
  13. Fox., A. J. (1972), “Outliers in time series,” Journal of the Royal Statistical Society, Series B, 34, 350–363.Google Scholar
  14. Gardner, E. S. (1983), “Automatic monitoring of forecast errors,” Journal of Forecasting, 2, 1–21.CrossRefGoogle Scholar
  15. Golub, A., W. Gorr and P. Gould (1993), “Spatial diffusion of the HIV/AIDS epidemic: Modeling implications and case study of aids incidence in Ohio,” Geographical Analysis 25, 85–100.CrossRefGoogle Scholar
  16. Gorr, W. (1986), “Special event data in shared databases,” MIS Quarterly, 10, 239–250. Greis, N. P. and Z. Gilstein (1991), “Empirical Bayes methods for telecommunications forecasting, International Journal of Forecasting, 7, 183–197.Google Scholar
  17. Harrison, P. J. and C. F. Stevens (1971), “A Bayesian approach to short-term forecasting,” Operations Research Quarterly, 22, 341–362.CrossRefGoogle Scholar
  18. Harrison, P. J. and C. F. Stevens (1976), `Bayesian Forecasting,“ Journal of the Royal Statistical Society, Series B, 38, 205–247.Google Scholar
  19. Harvey, A. C. (1986), “Analysis and generalization of a multivariate exponential smoothing model,” Management Science 32, 374–380.CrossRefGoogle Scholar
  20. Jones, R. H. (1966), “Exponential smoothing for multivariate time series,” Journal of the Royal Statistical Society Series B, 28, 241–251.Google Scholar
  21. Kass, R. E. and D. Steffey (1989), “Approximate Bayesian inference in conditionally independent hierarchical models (parametric empirical Bayes models),” Journal of the American Statistical Association, 84, 717–726.CrossRefGoogle Scholar
  22. Lee, Y. (1990), Conceptual design of a decision support system for local government revenue forecasting, Unpublished Ph.D. Dissertation, Heinz School, Carnegie Mellon University.Google Scholar
  23. LeSage, J. P. (1989), “Incorporating regional wage relations in local forecasting models with a Bayesian prior, ” International Journal of Forecasting 5, 37–47.CrossRefGoogle Scholar
  24. LeSage, J. P. and A. Krivelyova (1998a), “A spatial prior for Bayesian Vector Autoregressive Models,” University of Toledo Economics Department Working Paper, http://www.econ.utoledo.edu/faculty/lesage/papers/anna/anna-jpl.html Google Scholar
  25. LeSage, J. P. and A. Krivelyova (1998b), “A random walk averaging prior for Bayesian vector autoregressive models,” University of Toledo Economics Department Working Paper, July 1997, see http://www.econ.utoledo.edu/faculty/lesage/papers/anna2/anna_io.html.Google Scholar
  26. LeSage, J. P. and Z. Pan (1995), “Using spatial contiguity as Bayesian prior information in regional forecasting models,” International Regional Science Review, 18 (1), 33–53.CrossRefGoogle Scholar
  27. Lewandowski, R. (1982), “Sales forecasting by FORSYS,” Journal of Forecasting, 1, 205–214.CrossRefGoogle Scholar
  28. Litterman, R. B. (1986), “A statistical approach to economic forecasting,” Journal of Business and Economic Statistics, 4, 1–4.Google Scholar
  29. Mahajan, V. and Y. Wind (1988), “New product forecasting models: Directions for research and implementation, International Journal of Forecasting 4, 341–358.CrossRefGoogle Scholar
  30. Makridakis, S., A. Andersen, R. Carbone, R. Fildes, M. Hibon, R. Lewandowski, J. Newton, E. Parzen and R. Winkler (1982), “The accuracy of extrapolation (time series) methods: Results of forecasting competition,” Journal of Forecasting, 1, 111–153.CrossRefGoogle Scholar
  31. McLaughlin, R. L. (1982), “A model of average recession and recovery, Journal of Forecasting 1, 55–65.CrossRefGoogle Scholar
  32. Sayrs, L. W. (1989), Pooled Time Series Analysis. London: Sage Publications.Google Scholar
  33. Szczypula, J. (1997), Adaptive hierarchical pooling methods for univariate time series forecasting. Unpublished Ph.D. Dissertation, Heinz School, Carnegie Mellon University.Google Scholar
  34. Willemain, T. R, C. N. Smart, J. H. Shockor and P. A. DeSautels (1994), “Forecasting intermittent demand in manufacturing: A comparative evaluation of Croston’s method,” International Journal of Forecasting 10, 529–538.CrossRefGoogle Scholar
  35. Zellner, A. (1986), “A tale of forecasting 1001 series: The Bayesian knight strikes again,” International Journal of Forecasting 2, 491–494.CrossRefGoogle Scholar
  36. Zellner, A. and C. Hong (1989), “Forecasting international growth rates using Bayesian shrinkage and other procedures,” Journal of Econometrics, 40, 183–202.CrossRefGoogle Scholar
  37. Zellner, A. (1994), “Time-series analysis and econometric modelling: The structural econometric modelling, time-series analysis (SEMTSA) approach,” Journal of Forecasting, 13, 215–234.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • George T. Duncan
    • 1
  • Wilpen L. Gorr
    • 1
  • Janusz Szczypula
    • 1
  1. 1.H. John Heinz III School of Public Policy and ManagementCarnegie Mellon UniversityUSA

Personalised recommendations