Two essays on selection models and one essay on income inequality in rural China

This dissertation contains three essays in labor economics and applied micro econometrics. The first two essays cover selection problems in panel data and the third essay analyzes income inequality in rural China.; The first essay examines the extent to which non-random selection in labor market affects assessing black-white wage differences by applying a longitudinal method of imputing wages for nonworkers. Since fixed effects are crucial in determining the wages of nonworkers, the cross-sectional methods of controlling only on observables understate the impact of selection. Using the Panel Study of Income Dynamic (PSID) 1970--2000 data, I find that the selective bias can explain 40 percent of the observed change of black-white wage gaps over 1970--2000.; The second essay investigates whether non-random sample attrition causes the black and white wage differences in the PSID data to deviate from the Current Population Survey (CPS). The empirical analysis shows that part of the disparity between the two data sets can be explained by different attrition patterns between blacks and whites. However, the magnitude of attrition bias is quite small and attrition-adjusted weights, as a result, play a small role in reconciling the disparity of the black-white wage gaps between the two datasets.; The third essay assesses the contribution of the agricultural and industrial income for the rise of rural household income inequality in China by counterfactual decomposition techniques. Using the Chinese Household Income Project data in 1988 and 1995, I find that the rise in inequality reflected both the stagnant development of agriculture and the rural industrialization. Most of the rise inequality was accounted for spatial inequality, the increase of which reflected growing unevenly regional development of industrialization.