INFORMS.org
Certified Analytics Professional
PubsOnline
Career Center
2018 International Meeting
Sign in | Register | Mobile | Help | Cart
INFORMS
JOURNAL HOME
Journals
INFORMS Publications
ABOUT
ISSUES
INFORMS Editor's Cut
ARTICLES IN ADVANCE
FOR AUTHORS
Subscriber Services
CONTACT
Contact INFORMS
YOU ARE HERE: Home > Management Science > All Issues > Volume 39, Issue 3 > Bayesian Forecasting for Se… Prev
Article Tools Add to Favorites
Current Issue Articles in Advance
Next
Archive Subscribe
Bayesian Forecasting for Seemingly Unrelated Time Series: Application to Local Government Revenue Forecasting
About Submit a Manuscript
Email to a Colleague Download Citation Track Citations Permissions
Search
Enter Search Term
George Duncan Heinz School of Public Policy and Management, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
Quicklinks & Resources From the Editor blog
Wilpen Gorr Heinz School of Public Policy and Management, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
Management Science Review blog Management Science Service Awards
Janusz Szczypula Heinz School of Public Policy and Management, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
INFORMS Author Portal Download Journal Flyer
Permalink: https://doi.org/10.1287/mnsc.39.3.275 Published Online: March 1, 1993
Most Read
Cited
Page Range: 275 - 293
Abstract
Cited by
From the Editor Citation References Full-text PDF
PDF
Management Science 2012 Best Paper Awards Abstract Full-text PDF
Abstract One important implementation of Bayesian forecasting is the Multi-State Kalman Filter (MSKF) method. It is particularly suited for short and irregular time series data. In certain applications, time series data are available on numerous parallel observational units which, while not having cause-and-effect relationships between them, are subject to the same external forces (e.g., business cycles). Treating them separately may lose useful information for forecasting. For such situations, involving seemingly unrelated time series, this article develops a Bayesian forecasting method called C-MSKF that combines the MSKF method with the Conditionally Independent Hierarchical method. A case study on forecasting income tax revenue for each of forty school districts in Allegheny County, Pennsylvania, based on fifteen years of data, is used to illustrate the application of C-MSKF in comparison with univariate MSKF. Results show that C-MSKF is more accurate than MSKF. The relative accuracy of C-MSKF increases with decreasing length of historical time series data, increasing forecasting horizon, and sensitivity of school districts to the economic cycle. Keywords: Bayesian forecasting ; Kalman filtering ; multivariate time series methods ; seemingly unrelated time series
INFORMS • 5521 Research Park Drive, Suite 200, Catonsville, MD 21228 USA • +1-443-757-3500 •
[email protected] Loading [Contrib]/a11y/accessibility-menu.js Sitemap Terms of Use Contact INFORMS INFORMS © 2017
A Theoretical Extension of the Technology Acceptance Model: Four Longitudinal Field Studies Abstract References PDF Innovation, Openness, and Platform Control Abstract References PDF Looking Across and Looking Beyond the Knowledge Frontier: Intellectual Distance, Novelty, and Resource Allocation in Science Abstract References PDF
See More