Econometric analysis of private and public wage determination for older workers using a copula and switching regression

Abstract

© 2014 by the Mathematical Association of Thailand. All rights reserved. This paper aims on applying the copula approach to an endogenous switching regression model to determine the public and private sector wages for older workers in Thailand. The copula approach to endogenous switching models not only allows for flexibility in the specification for the margins but also considers employing different families of copulas to measure the dependence between the disturbance terms in the switching equation (εs) and those in the two wage equations (ε0 and ε1). This paper demonstrates that based on the log–likelihood value and the criterion of BIC, all of the copula–based models perform better than the standard model, for this context, especially with the Frank-Gaussian (L–t–t) model. Furthermore, these results show the presence of significant negative dependency of unobservable factors between the switching regression and the wage regression, which implies that those older workers who are engaged in the public sector have suffered more from the wage penalty than those in the private sector. Thus, the concerned policy makers should run campaigns that encourage the public sector to retain the older workers with high wages, especially on those individuals with higher education and skills.