Pareto models
Charpentier and Flachaire show that modelling top incomes with:
- Pareto Type I distribution can lead to severe over-estimation of inequality, even with millions of observations;
- The Generalized Pareto Distribution, is less sensitive to the choice of the threshold but its estimation is inaccurate; and
- The Extended Pareto Distribution , which allows to capture deviations from a strict Pareto distribution, is much less sensitive to the choice
of the threshold, and its estimation is quite accurate.
Pareto Models for Top Incomes
Authors: Arthur Charpentier, Emmanuel Flachaire
From: Université du Québec à Montréal, Aix-Marseille Université
Macroeconomic aggregates on households’ wealth
Chakraborty, Sofie R. Waltl argue that computing aggregates from the Household Finance and Consumption Survey (HFCS), usually underestimates wealth inequality since the wealthiest households are not included in HFCS. In this paper they combine a semi-parametric Pareto model estimated from survey data with a stratification approach making use of HFCS portfolio structures to quantify the impact of the missing wealthy households on instrument-specific gaps between micro and macro data. They analyse data for Austria and Germany, and find that adjusting for the missing wealthy pushes up inequality even further.
Missing the Wealthy in the HFCS: Micro Problems with Macro Implications
Authors: Robin Chakraborty, Sofie R. Waltl
From: Deutsche Bundesbank, Luxembourg Institute of Socio-Economic Research
