The Use of Finite Mixtures of Probability Distributions for Modelling the Distribution of the Duration of Unemployment in the Czech Republic

Unemployment belongs to the most serious economic and social problems of developed countries. Usually, the rate of unemployment is analysed. Another problem is the duration of unemployment and especially long-term unemployment. The unemployment duration in the Czech Republic in 2010 is analysed in the paper. The model uses data from the Labour Force Sample Survey, which is performed quarterly by the Czech Statistical Office. The probability distribution of unemployment duration is modelled with the use of finite mixtures of lognormal distributions with the observable components of membership, gender and education. The observations are right and interval-censored, exact values of the unemployment duration are not included in the data. Both parametric and non-parametric Kaplan-Meier methods are used to estimate the survival function. The estimated survival functions are compared graphically and medians are evaluated for each component. A positive effect of education on the duration of unemployment is found. Also, a greater median unemployment duration is found for women than for men. All the computations are made in the R software.