The Analysis of Transition Data by the Minimum Chi-Square Method. An Application to Welfare Spells in Belgium

In this paper we analyse transition data by means of the minimum chi-square (MCS) method in stead of the more commonly used maximum likelihood (ML) method. The method requires a very large dataset with relatively little information on determining factors. If such data are available, the MCS method is to be the estimation procedure of choice, because it is more robust than the ML method and it has a lower mean square error for small sample sizes. The latter property is shown to be particularly relevant if one is interested in the estimation of the tail of the duration distribution. The analysis includes exists to multiple destinations and unmeasured heterogeneity. In the empirical application turnover in the welfare system is found to be very high in Belgium. Median duration is 4.5 months for men and 7 months for women. These figures overstate turnover in that exits out of welfare include those occurring as a consequence of recipients moving to another municipality while remaining on welfare.