Transformation models for two samples of censored data are considered. Main examples are the proportional hazards and proportional odds model. The key assumption of these models is that the ratio of transformation rates (e. g., hazard rates or odds rates) is constant in time. A method of verification of this proportionality assumption is developed. The proposed procedure is based on the idea of Neyman's smooth test and its data-driven version. The method is suitable for detecting monotonic as well as nonmonotonic ratios of rates.
Keywords:
The article focuses on adult education in the Czech Republic. It begins by defining the institutional context of adult education in the country. Three institutional characteristics are of particular interest in this respect: returns to education, the current level of education of the adult population (and the related demand for adult education), and institutions offering adult education. Using the LFS and AES surveys, the authors find that it is primarily young and educated persons who pursue adult education. With respect to the returns to adult education, the results show that adult education does not protect against downward mobility but does increase the odds of upward mobility. The positive effect of adult education on upward mobility is more pronounced among women than men.
The Accelerated Failure Time model presents a way to easily describe survival regression data. It is assumed that each observed unit ages internally faster or slower, depending on the covariate values. To use the model properly, we want to check if observed data fit the model assumptions. In present work we introduce a goodness-of-fit testing procedure based on modern martingale theory. On simulated data we study empirical properties of the test for various situations.
There is a sharp discrepancy between the emphasis being placed on active ageing and labour market participation in older age and the high unemployment rates observed among older workers. Cross-sectional data in the Czech Republic consistently present evidence of job insecurity and employment vulnerability in older age groups. Aggregated data and statistical indices do not, however, offer a sufficiently detailed picture of the social processes (e.g. exit from the labour market, duration of unemployment, and exit from unemployment) behind the numbers. This article takes a dynamic look at the position of older workers in the labour market by investigating transitions between employment and unemployment using a sub-sample of older workers (50 year and over) from the Czech EU-SILC, who were interviewed repeatedly in a panel survey between 2004 and 2009. The authors use survival analysis methods to study the time-dependence of transitions into and out of unemployment and both with and without covariates. The results suggest that older workers are not at a higher risk of exiting the labour market (compared to other age groups), but once they are unemployed, their odds of getting back into employment are significantly lower. Even when controls (such as education level) are included in the model this disadvantage persists. Interestingly, while education generally protects people from labour market exit, this protective effect is weaker among older workers.