TY  - RPRT
        AU  - Staghøj, Jonas
AU  - Svarer, Michael
AU  - Rosholm, Michael
        TI  - A Statistical Programme Assignment Model
        PY  - 2007/Nov/
        PB  - Institute of Labor Economics (IZA)
        CY  - Bonn
        T2  - IZA Discussion Paper
        IS  - 3165
        UR  - https://www.iza.org/index.php/publications/dp3165
        AB  - 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 implementation of such a system, especially the interplay between the statistical model and case workers.
        KW  - heterogeneous effects
KW  - targeting
KW  - profiling
KW  - statistical treatment rules
        ER  -