We propose a first-order bias correction term for the Gini index to reduce the bias due to grouping. It only depends upon the number of individuals in each group and is derived from a measurement error framework. We also provide a formula for the remaining second order bias. Both Monte Carlo and EU and US empirical evidence show that the first-order correction reduces a considerable share of the bias, but that there is some remaining second-order bias that is increasing in the variance. We propose a procedure that addresses the remaining second-order bias by using additional information.