Applied GEWR(n,p,q) Normal Discount Bayesian Model: An Austrian Economic Case Study

M. Akram
Additional contact information
M. Akram: Bahrain University, Business and Management Department

A chapter in Probability and Bayesian Statistics, 1987, pp 7-16 from Springer

Abstract: Abstract The theory of Generalised Exponentially Weighted Regression (GEWR) and dynamic Bayesian models has been given previously by Harrison-Akram(1982), Akram-Harrison(1983) and Akram(1984). This paper breifly reviews some of the main results and applies them to seasonal data concerned with the disposable personal income in Austria. For the selection of an appropriate model a new Stepwise Identification Procedure(SIP) based on a nonparametric measure, called Average String Length(ASL), is used. Both short and long term full forecasts and trends are obtained from a single model using on-line Bayesian learning procedure. The model applied yields optimum forecasts in the senses of minimum mean square error and whiteness of one step ahead forecast errors.

Keywords: Generalised Exponentially Weighted Regression; coloured noise process; Normal Discount Bayesian Model; Average String Length; Stepwise Identification Procedure; on-line Bayesian learning procedure (search for similar items in EconPapers)
Date: 1987
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-1-4613-1885-9_2

Ordering information: This item can be ordered from
http://www.springer.com/9781461318859

DOI: 10.1007/978-1-4613-1885-9_2

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().