Estimating Income Inequality from Binned Incomes with Paul von Hippel
Description
Researchers studying the gender wage gap often analyze data that puts income into bins, such as $0-10,000, $10,000-20,000, and $200,000+. Many methods have been used to analyze binned incomes, but few have been evaluated for accuracy. In this seminar, Paul von Hippel compares and evaluates three methods: the multi-model generalized beta estimator (MGBE), the robust Pareto midpoint estimator (RPME), and the spline CDF estimator. He finds that the MGBE and RPME produces comparable results, while the spline CDF estimator is much more accurate. Paul has implemented all three methods in software for Stata and R.
Paul von Hippel, Associate Professor of Public Affairs, Lyndon B. Johnson School of Public Affairs, The University of Texas at Austin
United States
