The Estimation of Flows on Regional Labour Markets By Using the ADETON Procedure

Uwe Blien () and Friedrich Graef ()

ERSA conference papers from European Regional Science Association

Abstract: An in-depth analysis of regional labour markets requires information not only on stocks but also on flows. As a tool for detailed flow analysis the Multi Account System (MAS) has been developed at the Institute for Employment Research (IAB) which uses fine grained transition matrices as basic information. To estimate these transition matrices from possibly incomplete and inconsistent statistical data the ADETON procedure has been worked out to compute matrices which are struc-turally similar to given reference matrix and at the same time satisfy certain linear con-straints. As main advantage of ADETON in comparison to conventional methods soft constraints may be specified which allow information of inherently fuzzy character about transition flows to be taken into account. By using soft constraints of this kind it is possible to in-clude data affected by sampling errors or are distorted by some kind of “noise†. To obtain structural similarity to a reference matrix two different distance measures can be used: relative entropy and the chi-square distance function. They have been proven to give approximately identical results. Up to now ADETON has shown to be an efficient computation method even for complex problems with thousands of matrix elements and constraints. ADETON has been applied to estimate matrices of the Multi Account System. The results are used for the guidance of regional labour market policy.

Date: 2006-08
New Economics Papers: this item is included in nep-geo
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www-sre.wu.ac.at/ersa/ersaconfs/ersa06/papers/157.pdf (application/pdf)

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:wiw:wiwrsa:ersa06p157

Access Statistics for this paper

More papers in ERSA conference papers from European Regional Science Association Welthandelsplatz 1, 1020 Vienna, Austria.
Bibliographic data for series maintained by Gunther Maier ().