The probability of exitfrom registered unemployment, based on the example of Szczecin

Abstract

The aim of the paper is to determine the influence of sex, age and education on the probability of exit from the registered unemployment in Szczecin. For the purposes of the study, the authors employed the survival analysis method, where they used survival trees built on the basis of the Kaplan-Meier estimators and adopted the statistic of the log-rank test as the splitting criterion. The research analysed the two most frequent reasons for deregistration, namely starting a job and the unemployed person’s failure to meet the conditions for being registered as unemployed. In addition, the study extracted subgroups of persons whom it took shortest and longestto start a job or deregister froma labour office. The analysis was based on the microdata from the Powiat Labour Office in Szczecin concerning persons who registered as unemployed in 2013 and were moni-tored until the end of 2014. The calculations were made in the R computer programme, using the partykit package and the ctree function. The research demonstrated that the probability of deregistration from the unemployment register because of finding a job depends solely on the age and education of the unemployed person, while the probability of getting removed from the unemployment register –on the two former determinants plus sex.