Applying 'Benford's Law' to the Crosswise Model: Findings from an Online Survey on Tax Evasion

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Applying "Benford's law" to the Crosswise Model: Findings from an online survey on tax evasion Terms of use: Documents in THORBEN KUNDT Zusammenfassung/ AbstractMany surveys on sensitive topics such as tax evasion suffer from the reluctance of respondents to provide truthful answers which can cause downward-biased estimates. This paper addresses this problem by making use of a recent survey method (Crosswise Model) designed to provide positive incentives for respondents to answer sensitive questions more truthful. We extend the Crosswise Model by applying the so-called "Benford Illusion" which allows us to increase the precision of the Crosswise Model that is less statistically efficient than other methods. To test the effectiveness of the model in providing privacy protection, we carried out an online survey in which the respondents were randomly allocated into two splits differing only by the questioning technique applied. Our results suggest that the Crosswise Model can help to increase privacy protection compared to a simple direct questioning approach. As a consequence, survey estimates of tax evasion using the Crosswise Model are likely to become more valid. At the same time, we show that were able to obtain an efficient estimator without substantially decreasing privacy protection, even for a relatively small sample size.

Corruption as a Self‐Fulfilling Prophecy: Evidence from a Survey Experiment in Costa Rica

“…Recent studies have reported very good performance with the crosswise model in applications ranging from cheating by undergraduates to tax evasion (Jann, Jerke, and Krumpal ; Körndorfer, Krumpal, and Schmukle ; Kundt ).…”

Functionality of the Crosswise Model for Assessing Sensitive or Transgressive Behavior: A Systematic Review and Meta-Analysis

“…In addition, seven studies (Shamsipour et al, 2014;Khosravi et al, 2015;Nasirian et al, 2018;Banayejeddi et al, 2019;Hopp and Speil, 2019;Safiri et al, 2019;Schnapp, 2019) used a combination of birthday and non-birthday innocuous item pairs. Phone numbers were used in seven studies (Shamsipour et al, 2014;Khosravi et al, 2015;Vakilian et al, 2016Vakilian et al, , 2019Kundt et al, 2017;Banayejeddi et al, 2019;Safiri et al, 2019), house numbers in seven studies (Kundt, 2014;Shamsipour et al, 2014;Khosravi et al, 2015;Lehrer et al, 2019;Safiri et al, 2019;Schnapp, 2019;Vakilian et al, 2019), ATM card pin code in three studies (Shamsipour et al, 2014;Khosravi et al, 2015;Safiri et al, 2019), and ID card number in two studies (Khosravi et al, 2015;Safiri et al, 2019). The remaining studies relied on random numbers or letters of the alphabet (Banayejeddi et al, 2019), performance of academic tasks (Jerke et al, 2021), date of a significant personal event (Hopp and Speil, 2019), family size of four (Nasirian et al, 2018), owning a vehicle (Nasirian et al, 2018), friend or family member with a common name (Vakilian et al, 2014(Vakilian et al, , 2019, picking a card (Mirzazadeh et al, 2018), and random probability assignment (Atsusaka and Stevenson, 2020).…”

“…Of these, 49 pairs used specific birthday months with P ranging between 0.08 (1/12 months) and 0.25 (3/12 months). In five cases (Eslami et al, 2013;Nakhaee et al, 2013;Khosravi et al, 2015;Nasirian et al, 2018;Safiri et al, 2019), season (e.g., spring) was used which is open for interpretation Substance use and misuse Nakhaee et al, 2013;Shamsipour et al, 2014;Höglinger et al, 2016;Mirzazadeh et al, 2018;Banayejeddi et al, 2019;Safiri et al, 2019;Özgül, 2020;Canan et al, 2021Shamsipour et al, 2014Mirzazadeh et al, 2018;Safiri et al, 2019 Academic misconduct Coutts et al, 2011;Jann et al, 2012;Höglinger et al, 2016;Hopp and Speil, 2019;Jerke et al, 2021Coutts et al, 2011Jann et al, 2012;Jerke et al, 2021 Corruption, tax evasion, and theft Korndörfer et al, 2014;Kundt, 2014;Gingerich et al, 2015;Höglinger and Jann, 2018;Hopp and Speil, 2019;Oliveros and Gingerich, 2020 Health and STDs Mirzazadeh et al, 2018;Nasirian et al, 2018 Sexual behavior and infidelity Mirzazadeh et al, 2018;Klimas et al, 2019;Lacker et al, 2020 Substance use and misuse Khosravi et al, 2015;Kazemzadeh et al, 2016;Heck et al, 2018;…”

“…Online questionnaires (k = 21) Korndörfer et al, 2014;Kundt, 2014;Hoffmann et al, 2015Hoffmann et al, , 2017Höglinger et al, 2016;Höglinger and Diekmann, 2017;Waubert de Puiseau et al, 2017;Höglinger and Jann, 2018;Hopp and Speil, 2019;Klimas et al, 2019;Lehrer et al, 2019;Schnapp, 2019;Walzenbach and Hinz, 2019;Atsusaka and Stevenson, 2020;Jensen, 2020;Lacker et al, 2020;Meisters et al, 2020a;Canan et al, 2021;Jerke et al, 2021;Mieth et al, 2021 Paper questionnaires (k = 18) Coutts et al, 2011;Jann et al, 2012;Nakhaee et al, 2013;Shamsipour et al, 2014;Vakilian et al, 2014Vakilian et al, , 2016Vakilian et al, , 2019Khosravi et al, 2015;Kazemzadeh et al, 2016;Heck et al, 2018;Mirzazadeh et al, 2018;Nasirian et al, 2018;Banayejeddi et al, 2019;Safiri et al, 2019;Hoffmann et al, 2020;Meisters et al, 2020b;Özgül, 2020 Interviews (k = 4) Gingerich et al, 2015;Kundt et al, 2017;Oliveros and Gingerich, 2020 Interviews and questionnaires (k = 2) Eslami et al, 2013;Jerke e...…”

“…In the same study, 33.70% indicated full trust in CM whereas 26.4% indicated little or no trust, with a positive association between CM comprehension and trust. Also, in a German study involving 256 CM participants (Kundt, 2014), 63.0% indicated that they fully understood the mechanism of CM and that it provides privacy protection, 21.0% indicated that CM provides privacy protection although they did not exactly understand CM mechanism, and 16.0% had no understanding of CM. Additionally, in a study of a German voter panel (Lehrer et al, 2019), it was found that CM has a significantly lower item non-response compared to DQ.…”