Cowell, Frank and Victoria-Feser, Maria-Pia (2001) Robust Lorenz curves : a semi-parametric approach. Distributional Analysis Research Programme; DARP 50, DARP 50. Suntory and Toyota International Centres for Economics and Related Disciplines, London School of Economics and Political Science, London, UK.
Download (746Kb) | Preview
Lorenz curves and second-order dominance criteria are known to be sensitive to data contamination in the right tail of the distribution. We propose two ways of dealing with the problem: (1) Estimate Lorenz curves using parametric models for income distributions, and (2) Combine empirical estimation with a parametric (robust) estimation of the upper tail of the distribution using the Pareto model. Approach (2) is preferred because of its flexibility. Using simulations we show the dramatic effect of a few contaminated data on the Lorenz ranking and the performance of the robust approach (2). Statistical inference tools are also provided.
Actions (login required)
|Record administration - authorised staff only|