Self-reported income data: are people telling the truth?

Abstract

Purpose This paper aims to detect anomalous data in income reports of Argentina, including personal income – from a sample of households – and statements of public officials. Design/methodology/approach A widely known technique in forensic accounting – such as Benford’s Law – is used. The Chi-square test and the absolute mean deviation are used for verification. The databases consulted include the income declared by households in the Permanent Household Survey – for the 2003-2017 period – and the capital declarations of high-ranking public officials – for the period 1999-2017. Findings The results suggest that income reported in the Encuesta Permanente de Hogares do not follow a Benford´s distribution, and the degree of conformity with this decreases significantly between 2007 and 2015 – coincident with the intervention period of the Instituto Nacional de Estadísticas y Censos. Patrimonial statements of public officials present an acceptable level of compliance with Benford’s law, especially among those of the legislative branch (in more than 90% of cases) although to a lesser extent among officials of the executive branch. Practical implications The results suggest that income reports from the Permanent Household Survey, for the period 2007-2015, should be used with reservations because of their possible manipulation. Originality/value During the intervention of the official statistics institute in Argentina (2007-2015), the idea of lack of credibility of its reports has been disseminated. To date, however, there is no empirical evidence to support it related to income.

Forensic Accounting: The Use of Benford's Law to Evaluate Indications of Fraud

“…The hypothesis which states that there are indications of fraud at PII Corporation according to Benford's Law is rejected. This is in line with previous results (González, 2020;Kruger & Yadavalli, 2017;Kuruppu, 2019;Qin et al, 2019;Striga & Podobnik, 2018). Meanwhile, 3 tests have shown that some data are not in line with Benford's Law distribution, also corroborated by previous research (Alali & Romero, 2013;Davydov & Swidler, 2017;Geyer & Drechsler, 2014;Silva, 2016;Slijepcevic & Blaskovic, 2014).…”

Lies, damned lies, and statistics: The uncertainty over COVID‐19 numbers in India

“…Notable instances include evaluating if economic data has been manipulated (Gonzales‐Garcia & Pastor, 2009 ; Nye & Moul, 2007 ; Rauch et al, 2011 , etc.) and assessing the veracity of information from household surveys (González, 2020 ; Judge & Schechter, 2009 ; Villas‐Boas et al, 2017 ).…”

“…Both the Chi‐square test and KS test can present type I error in large samples, and therefore their compliance with Benford's law is circumspect in scenarios where we reduce the difference in the proportions (Barney & Schulzke, 2016 ; Druică et al, 2018 ; González, 2020 ). To alleviate this concern, we use the mean average deviation to check the concordance of the frequency distribution with Benford's law.…”

“…We have used Pearson's Chi‐square test (Pearson, 1900) as a significance test to ascertain if the “true” distribution follows the theoretical (Benford) distribution and if the sample comes from a distribution with a certain probability density function (González, 2020). The Chi‐square statistic is calculated as follows: In addition, we have supplemented this analysis with another goodness of fit test, that is, Kolmogorov–Smirnov (KS) test wherein the empirical distribution function for n independent and identically distributed ordered observations is defined as: where is the indicator function, equal to 1 if and equal to 0 otherwise.…”

Tax Avoidance, Fraud Detection and Related Accounting Issues. Insights from the Visegrad Group Countries

“…Based on the literature review, it can be concluded that Mean Absolute Deviation (hereinafter referred to as MAD) is a standard method of examining the fit of distributions. MAD is commonly used to assess distribution fit (González, 2020;Isaković-Kaplan, Demirović, & Proho, 2021;Nigrini, 2012). This method examines the mean value of the absolute differences between the empirical and Benford's distributions for the analysed digits.…”