In this dissertation, I explore a variety of methods for the econometric analysis of firm-level production data. Three distinct approaches are considered, namely i) proxy variable methods of controlling for unobservable productivity, ii) data envelopment techniques for estimating the boundary of a production set, and iii) stochastic frontier methods for estimating the productive inefficiency of firms. Much of the focus is on semiparametric and nonparametric estimators that allow for a highly flexible specification of the function that relates input combinations to output quantities. / Thesis / Doctor of Philosophy (PhD)

This study examines the effects of market concentration on firm-level productivity using data on Chinese above-scale industrial firms from 2001 to 2007. Productivity is identified as total factor productivity (TFP) and estimated using the Olley-Pakes three-step estimation in order to avoid simultaneity and selection biases. Using data on around 590,000 industrial firms, empirical results indicate that the less concentrated the market, the higher the productivity generally. However, a few industries are identified to have opposite direction; that is, the more concentrated, the more productive are the firms. In some industries, there is no significant relationship between market concentration and firm productivity.