Deficit versus social statistics: empirical evidence for the effectiveness of Benford’s law

Abstract

When analysing the quality of data, nonconformity with Benford’s law can be a useful indicator of poor data quality, which may be a result of fraud or manipulation. In this article, we use Benford’s law to compare government social security statistics with deficit related data reported by the EU member states to Eurostat. Unlike deficit related data, social security statistics are not subject to the fiscal monitoring connected with excessive deficit procedures (EDP) and the incentive to manipulate such statistics is therefore lower. Our results show that, across all but one 27 EU member states, the deviations from the Benford distribution in the social security statistics are considerably smaller than those shown by the deficit data. This leads us to conclude that, as would be expected, European governments behave in accordance with the incentives, i.e. while the quality of the social security statistics appears to be higher, there is a widespread tendency to report incorrect deficit data. We therefore consider our results to be evidence of the effectiveness of Benford’s law in identifying manipulated data.

Keywords:

• Benford’s law
• macroeconomic data
• digital analysis
• data manipulation

JEL Classification:

• C16
• E01
• M42

Notes

¹ Accounts ‘lmb_expend’, ‘spr_exp_func’ and ‘spr_rec_eur’ (latest update from 14 December 2012). Available at http://epp.eurostat.ec.europa.eu/portal/page/portal/statistics/search_database