An integrated approach for top-corrected Ginis

Household survey data provide a rich information set on income, household context and demographic variables, but tend to under-report incomes at the very top of the distribution. Tax record data offer more precise information on top incomes at the expense of household context details and incomes of non-fillers at the bottom of the distribution. We combine the benefits of the two data sources to improve survey-based Gini coefficients in two ways. First, we incorporate top income share estimates based on tax records with survey-based Ginis for the rest of the population following Atkinson (2007) and Alvaredo (2011). Second, we impute top fractile's income in EU-SILC survey data with the Pareto distribution coefficients obtained from tax records and then calculate the Gini coefficient. We find that both approaches produce rather similar results. The gap between unadjusted and top-corrected Ginis is highest in countries that rely exclusively on survey data as compared to purely register or partly register countries.