Fitting Truncated Mode Regression Model by Simulated Annealing (original) (raw)
Related papers
Some notes on sample selection models (in Russian)
2009
Sample selection problems are pervasive when working with micro economic models and datasets of individuals, households or firms. During the last three decades, there have been very significant developments in this area of econometrics. Different type of models have been proposed and used in empirical applications. And new estimation and inference methods, both parametric and semiparametric, have been developed. These notes provide a brief introduction to this large literature.
Some Notes on Sample Selection Models
2009
Sample selection problems are pervasive when working with micro economic models and datasets of individuals, households or firms. During the last three decades, there have been very significant developments in this area of econometrics. Different type of models have been proposed and used in empirical applications. And new estimation and inference methods, both parametric and semiparametric, have been developed. These notes provide a brief introduction to this large literature.
The Gender Wage Gap in Bulgaria: A Semiparametric Estimation of Discrimination
Journal of Comparative Economics, 2002
Bulgaria's transition to a market economy has coincided with a large increase in wage inequality. Given the emphasis on wage leveling in pre-transition Bulgaria, the rise in wage inequality may be due to managers rewarding more productive workers; or it may be the result of rewarding non-economic characteristics such as gender. Using data from the 1995, nationally representative Bulgaria Integrated Household Survey, I examine whether gender discrimination is an important factor determining the gap in wages between men and women and the extent to which gender discrimination affects wage inequality. I model wage determination with a correction for sample selection as a Type III Tobit and estimate this model with the Honoré et al. (1997) semiparametric estimator. Unlike the classic Heckman correction for sample selection, this estimator is consistent in the presence of heteroscedasticity. I bootstrap to estimate standard errors. Using separate wage regression estimates for men and women, an Oaxaca decomposition indicates that women's wages are 25 percent lower than men's wages and 85 percent of this differential is due to discrimination, or more precisely, due to differences in how men and women are rewarded for the same characteristics.
Journal of Development Economics, 2004
Most of the human capital literature pertaining to developing countries focuses on the returns to education in either farm work or wage work; few studies examine how education affects the allocation of time between these activities. This paper estimates the returns to education in farm and off-farm work, and consequently the role of education in determining the allocation of labor. The results from this study show that off-farm work has a much higher return to education than does farm work and suggest that this divergence in returns affects the allocation of labor in farm households between farm and off-farm work.
Modeling Nonnegative Data with Clumping at Zero: A Survey
Journal of the Iranian Statistical Society, 2002
Applications in which data take nonnegative values but have a substantial proportion of values at zero occur in many dis- ciplines. The modeling of such "clumped-at-zero" or "zero-inflated" data is challenging. We survey models that have been proposed. We consider cases in which the response for the non-zero observations is continuous and in which it is discrete. For the continuous and then the discrete case, we review models for analyzing cross-sectional data. We then summarize extensions for repeated measurement analyses (e.g., in longitudinal studies), for which the literature is still sparse. We also mention applications in which more than one clump can oc- cur and we suggest problems for future research.