Abstract
A Bayesian sampling algorithm for parameter estimation in a discrete-response model is presented, where the dependent variables contain two layers of binary choices and one ordered response. The investigation is motivated by an empirical study using such a double-selection rule for three labour-market outcomes, namely labour-force participation, employment and occupational skill level. It is of particular interest to measure the marginal effects of some mental health factors on these labour-market outcomes. The contribution is to present a sampling algorithm, which is a hybrid of Gibbs and Metropolis–Hastings algorithms. In Monte Carlo simulations, numerical maximization of likelihood fails to converge for more than half of the simulated samples. The proposed Bayesian method represents a substantial improvement: it converges in every sample, and performs with similar or better precision than maximum likelihood. The proposed sampling algorithm is applied to the double-selection model of labour-force participation, employment and occupational skill level, where marginal effects of explanatory variables, in particular the mental health factors, on the three labour-force outcomes are assessed through 95% Bayesian credible intervals. The proposed sampling algorithm can easily be modified for other multivariate nonlinear models that involve selectivity and are difficult to estimate by other means.
Highlights
Modeling non-random samples has been an important issue in microeconometrics since the seminal work of Heckman (1979) on sample selection
For the simulated samples where full information maximum likelihood (FIML) fails, the Bayesian method continues to perform as well as it does for the simulated samples where FIML works
We look at the impact of mental illness on an individual’s chances of participating in the labour force and being employed; and for the employed, we look at the impact of mental illness on an individual’s occupational skill level
Summary
Modeling non-random samples has been an important issue in microeconometrics since the seminal work of Heckman (1979) on sample selection. If in reality there are two layers of selection, which for example, are the participation and employment selection decisions in the labour market, the standard Heckman’s model lumps together the two selection rules into a single selection mechanism. This single selection equation is likely to be misspecified, as the parameters are held fixed across the two groups of non-working individuals — non-participants and unemployed. The bias which results from misspecification would affect estimates of parameters and marginal effects in the outcome equation This issue has often been dealt with by restricting the sample to labour market participants, and focusing only on selection into employment. We aim to extend the double-selection model to allow for a discrete response variable in the final outcome equation under two layers of sample selection
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
