Without high-quality data, even the best-designed monitoring and evaluation systems will collapse. Chapter 7 introduces some the basics of collecting high-quality data and discusses how to address challenges that frequently arise. High-quality data must be clearly defined and have an indicator that validly and reliably measures the intended concept. The chapter then explains how to avoid common biases and measurement errors like anchoring, social desirability bias, the experimenter demand effect, unclear wording, long recall periods, and translation context. It then guides organizations on how to find indicators, test data collection instruments, manage surveys, and train staff appropriately for data collection and entry.
Abstract
Identifying taxpayers who engage in noncompliant behaviour is crucial for tax authorities to determine appropriate taxation schemes. However, because taxpayers have an incentive to conceal their true income, it is difficult for tax authorities to uncover such behaviour (social desirability bias). Our study mitigates the bias in responses to sensitive questions by employing the list experiment technique, which allows us to identify the characteristics of taxpayers who engage in tax evasion. Using a dataset obtained from a tax office in Jakarta, Indonesia, we conducted a computer-assisted telephone interviewing survey in 2019. Our results revealed that 13% of the taxpayers, old, male, corporate employees, and members of a certain ethnic group had reported lower income than their true income on their tax returns. These findings suggest that our research design can be a useful tool for understanding tax evasion and for developing effective taxation schemes that promote tax compliance.
It is difficult to gauge people’s acceptance about same-sex sexualities, as responses to questionnaires are prone to social desirability bias. We offer a new proxy for understanding popular concern surrounding same-sex sexualities: prevalence of Google searches demonstrating concern over gay/lesbian sexual identities. Using Google Trends data, we find that Google searches about whether a specific person is gay or lesbian show patterned bias toward masculine searches, in that such searches are much more frequently conducted about boys and men compared with girls and women. We put these findings into context by comparing search frequencies with other popular Google searches about sexuality and otherwise. We put forth that the patterned bias toward masculine searches illustrates support for the enduring relationship between masculinity and heterosexuality and that it does so on a larger scale than previous research has been able to establish.
PurposeThe current study aims to provide a systematic approach to detecting and identifying social desirability bias (SDB) in survey data using controversial sponsorship as a research context.Design/methodology/approachWe used an experimental approach to manipulate sponsorship situations (e.g. Beer sponsor vs Sports drink sponsor) that could potentially motivate respondents to under-report their perceptions toward the sponsor. By employing both procedural and statistical approaches, our evidence shows that responses toward the controversial sponsor were in fact contaminated by SDB.FindingsThe findings of the study provide methodological and practical implications for how sport marketing scholars and practitioners can identify, detect and control SDB in self-report data.Originality/valueWe argue that some survey research in sport marketing may be prone to SDB, but SDB has not received sufficient attention in sport marketing research. We emphasize the importance of detecting (and avoiding/controlling) SDB in sport management research.
Consumers usually consider themselves as more ethical than their peers, manifesting a need to appear more socially orientated than they actually are. The main objective of this study was to analyze the influence of social desirability bias on ethical consumer behavior considered at a component level. Data were collected from a sample of 332 Romanian individuals from the 18-26 age group. The data analysis process involved co-variance structural equation modeling performed with the help of AMOS. Results show that both the positive and negative sides of social desirability significantly influence the three dimension of ethical consumer behavior. Therefore, based on results from this study, researchers can better understand the complex structure of ethical consumer behavior form a different point of view.
Google, Tell Me. Is He Gay? Masculinity, Heterosexuality, and Gendered Anxieties in Google Search Queries about Sexuality
