Department of Economics and Business Economics

A Statistical Programme Assignment Model

Research output: Working paperResearch

  • Michael Rosholm, Aarhus School of Business, Denmark
  • Jonas Staghøj, Denmark
  • Michael Svarer
  • School of Economics and Management
When treatment effects of active labour market programmes are heterogeneous in an observable way  across the population, the allocation of the unemployed into different programmes becomes a particularly  important issue. In this paper, we present a statistical model designed to improve the present assignment  mechanism, which is based on the discretionary choice of case workers. This is done in a duration model
context, using the timing-of-events framework to identify causal effects. We compare different assignment  mechanisms, and the results suggest that a significant reduction in the average duration of unemployment spells may result if a statistical programme assignment model is introduced. We discuss several issues regarding the  plementation of such a system, especially the interplay between the statistical model and  case workers.
Original languageEnglish
Place of publicationAarhus
PublisherInstitut for Økonomi, Aarhus Universitet
Number of pages40
Publication statusPublished - 2007

    Research areas

  • Profiling, Targeting, Statistical Treatment Rules, Heterogeneous Effects

See relations at Aarhus University Citationformats

ID: 8923786