Indirect Questioning Techniques Research Articles

Prevalence estimates for COVID-19-related health behaviors based on the cheating detection triangular model

BackgroundSurvey studies in medical and health sciences predominantly apply a conventional direct questioning (DQ) format to gather private and highly personal information. If the topic under investigation is sensitive or even stigmatizing, such as COVID-19-related health behaviors and adherence to non-pharmaceutical interventions in general, DQ surveys can lead to nonresponse and untruthful answers due to the influence of social desirability bias (SDB). These effects seriously threaten the validity of the results obtained, potentially leading to distorted prevalence estimates for behaviors for which the prevalence in the population is unknown. While this issue cannot be completely avoided, indirect questioning techniques (IQTs) offer a means to mitigate the harmful influence of SDB by guaranteeing the confidentiality of individual responses. The present study aims at assessing the validity of a recently proposed IQT, the Cheating Detection Triangular Model (CDTRM), in estimating the prevalence of COVID-19-related health behaviors while accounting for cheaters who disregard the instructions.MethodsIn an online survey of 1,714 participants in Taiwan, we obtained CDTRM prevalence estimates via an Expectation-Maximization algorithm for three COVID-19-related health behaviors with different levels of sensitivity. The CDTRM estimates were compared to DQ estimates and to available official statistics provided by the Taiwan Centers for Disease Control. Additionally, the CDTRM allowed us to estimate the share of cheaters who disregarded the instructions and adjust the prevalence estimates for the COVID-19-related health behaviors accordingly.ResultsFor a behavior with low sensitivity, CDTRM and DQ estimates were expectedly comparable and in line with official statistics. However, for behaviors with medium and high sensitivity, CDTRM estimates were higher and thus presumably more valid than DQ estimates. Analogously, the estimated cheating rate increased with higher sensitivity of the behavior under study.ConclusionsOur findings strongly support the assumption that the CDTRM successfully controlled for the validity-threatening influence of SDB in a survey on three COVID-19-related health behaviors. Consequently, the CDTRM appears to be a promising technique to increase estimation validity compared to conventional DQ for health-related behaviors, and sensitive attributes in general, for which a strong influence of SDB is to be expected.

Substance or Noise?

Abstract: Indirect questioning techniques aim to provide more valid prevalence estimates for sensitive attributes than conventional direct questions. Despite being an important prerequisite for high estimation validity, indirect questioning techniques’ retest stability has rarely been addressed. For temporally stable attributes, high stability of both prevalence estimates and individual responses is expected; however, insufficient understanding of the instructions and random response behavior may compromise retest stability. The present study is the first to assess the retest stability of the Extended Crosswise Model (ECWM), a recent indirect questioning technique, and to compare it to the retest stability of a conventional direct question (DQ). With a retest interval of approximately 10 days, we asked N = 2,317 mothers twice whether they had smoked during a previous pregnancy. In both ECWM and DQ conditions, prevalence estimates were virtually identical over time, and most respondents answered consistently (ECWM: 89%, DQ: 95%). In the ECWM condition, inconsistent response behavior was slightly more prevalent and negatively associated with respondents’ education. However, as these effects were small, the retest stability of both ECWM and DQ in surveys on sensitive attributes was evaluated as high.

Aiding the well celebrated Kuk's randomized response technique through auxiliary and prior information

Asking direct questions in face to face surveys about sensitive traits is an intricate issue. One of the solutions to this issue is the randomized response technique (RRT). Being the most widely used indirect questioning technique to obtain truthful data on sensitive traits in survey sampling RRT has been applied in a variety of fields including behavioral science, socio-economic, psychological, epidemiology, biomedical, criminology, data masking, public health engineering, conservation studies, ecological studies and many others. This paper aims at exploring the methods to subsidize the randomized response technique through additional information relevant to the parameter of interest. Specifically, we plan to contribute by proposing more efficient hybrid estimators compared to existing estimator based on (Kuk, 1990) [31] family of randomized response models. The proposed estimators are based on the methodology of incorporating the pertinent information, available on the basis of either historical records or expert opinion. Specifically, in case of availability of auxiliary information, the regression-cum-ratio estimator is found to be the best to further enhance the estimation through (Kuk, 1990) [31] model while the (Thompson, 1968) [49] shrinkage estimation is observed to be yielding more precise and accurate estimator of sensitive proportion. The findings in this study signify the importance of the proposed methodology. Additionally, to support the mathematical findings, a detailed numerical investigation to evaluate the comparative performances is also conducted. Based on performance analysis, overwhelming evidences are witnessed in the favor of proposed strategies.

Falsification of home rapid antigen lateral flow tests during the COVID-19 pandemic

During the COVID-19 pandemic, lateral flow tests (LFTs) were used to regulate access to work, education, social activities, and travel. However, falsification of home LFT results was a concern. Falsification of test results during an ongoing pandemic is a sensitive issue. Consequently, respondents may not answer truthfully to questions about LFT falsification behaviours (FBs) when asked directly. Indirect questioning techniques such as the Extended Crosswise model (ECWM) can provide more reliable prevalence estimates of sensitive behaviors than direct questioning. Here we report the prevalence of LFT FBs in a representative sample in England (n = 1577) using direct questioning (DQ) and the ECWM. We examine the role of demographic and psychological variables as predictors of LFT FBs. We show that the prevalence estimates of the FBs in the DQ condition were significantly lower than the ECWM estimates, e.g., reporting a negative result without conducting a test: 5.7% DQ vs 18.4% ECWM. Moral norms, subjective norms, anticipated regret, perception of risk to self, and trust in government predicted some of the FBs. Indirect questioning techniques can help provide more realistic and higher quality data about compliance with behavioural regulations to government and public health agencies.

Unmasking academic cheating behavior in the artificial intelligence era: Evidence from Vietnamese undergraduates

The proliferation of artificial intelligence (AI) technology has brought both innovative opportunities and unprecedented challenges to the education sector. Although AI makes education more accessible and efficient, the intentional misuse of AI chatbots in facilitating academic cheating has become a growing concern. By using the indirect questioning technique via a list experiment to minimize social desirability bias, this research contributes to the ongoing dialog on academic integrity in the era of AI. Our findings reveal that students conceal AI-powered academic cheating behaviors when directly questioned, as the prevalence of cheaters observed via list experiments is almost threefold the prevalence of cheaters observed via the basic direct questioning approach. Interestingly, our subsample analysis shows that AI-powered academic cheating behaviors differ significantly across genders and grades, as higher-grade female students are more likely to cheat than newly enrolled female students. Conversely, male students consistently engage in academic cheating throughout all grades. Furthermore, we discuss potential reasons for the heterogeneous effects in academic cheating behavior among students such as gender disparity, academic-related pressure, and peer effects. Implications are also suggested for educational institutions to promote innovative approaches that harness the benefits of AI technologies while safeguarding academic integrity.

Identifying bias in self-reported pro-environmental behavior

Research on pro-environmental behavior (PEB) informs social policies and interventions, so the quality of PEB measurement is critical. Self-reported PEB measures in surveys often contain non-negligible measurement error that can bias estimates and lead to incorrect findings. Given the potential presence of error, we hypothesize that changes to the way self-reported PEB is measured might lead to systematic measurement errors that affect the validity of results. Study 1 (N = 951) showed that priming participants with related scales like environmentalist identity did not substantively change reported behavior (all ds ≤ 0.12). To investigate the possibility of overreporting without priming, Study 2 (N = 385) measured littering prevention behavior using the Unmatched Count Technique. A standard questionnaire format led to much higher reported behavior compared to the more anonymous covert condition, d = 0.53, and this effect appeared driven by participants who reported a stronger environmentalist identity. These results may help to explain some of the observed error in PEB measures. We suggest that researchers could reduce measurement bias with indirect questioning techniques.

Assessing the effectiveness of indirect questioning techniques by detecting liars

In many fields of applied research, mostly in sociological, economic, demographic and medical studies, misreporting due to untruthful responding represents a nonsampling error that frequently occurs especially when survey participants are presented with direct questions about sensitive, highly personal or embarrassing issues. Untruthful responses are likely to affect the overall quality of the collected data and flaw subsequent analyses, including the estimation of salient characteristics of the population under study such as the prevalence of people possessing a sensitive attribute. The problem may be mitigated by adopting indirect questioning techniques which guarantee privacy protection and enhance respondent cooperation. In this paper, making use of direct and indirect questions, we propose a procedure to detect the presence of liars in sensitive surveys which allows researchers to evaluate the impact of untruthful responses on the estimation of the prevalence of a sensitive attribute. We first introduce the theoretical framework, then apply the proposal to the Warner randomized response method, the unrelated question model, the item count technique, the crosswise model and the triangular model. To assess the effectiveness of the procedure, a simulation study is carried out. Finally, the presence and the amount of liars is discussed in two real studies concerning racism and workplace mobbing.

Efficient Bayes estimators of sensitive proportion with simple and mixture priors using direct and indirect responses

In this study, efficient Bayes estimators of sensitive proportion are proposed. It is documented that indirect reports increase variances of the estimates. To counteract this increase in variances we divided the total sample size, n = n 1+n 2, such that n 1 individuals record direct responses and n 2 individuals record indirect responses. The decision that a group of individuals should report indirect or direct responses would be based on distinct known factors. Bayes estimates and subsequent posterior risks are calculated taking into account different prior distributions, loss functions and a generalized randomized response technique. The impact of design parameters and the number of responses obtained using direct and indirect questioning techniques on the relative efficiencies are investigated. Graphical and numerical results indicate that the proposed estimators are better than the existing.

Sensitive attitudes and adherence to recommendations during the COVID-19 pandemic: Comparing direct and indirect questioning techniques

During the COVID-19 pandemic, various behavioral measures were imposed to curb the spread of the virus. In a preregistered study based on a quota-representative sample of adult Danish citizens (N = 1031), we compared the prevalence estimates of self-reported handwashing, physical distancing, and attitudes toward the behavioral measures between people surveyed with a direct and an indirect questioning approach (i.e., the crosswise model). Moreover, we investigated two possible predictors of sensitive behaviors and attitudes, namely empathy for people vulnerable to the virus and Honesty-Humility from the HEXACO Model of Personality. We also examined the interaction of both predictors with the questioning format. Survey participants reported more violation of guidelines regarding handwashing and physical distancing when asked indirectly rather than directly, whereas attitudes regarding the behavioral measures did not differ between the two questioning formats. Respondents with less empathy for people vulnerable to COVID-19 reported more violations of handwashing and physical-distancing, and those low on Honesty-Humility reported more violations of physical distancing.

A New Approach to Detecting Cheating in Sensitive Surveys: The Cheating Detection Triangular Model

Indirect questioning techniques such as the randomized response technique aim to control social desirability bias in surveys of sensitive topics. To improve upon previous indirect questioning techniques, we propose the new Cheating Detection Triangular Model. Similar to the Cheating Detection Model, it includes a mechanism for detecting instruction non-adherence, and similar to the Triangular Model, it uses simplified instructions to improve respondents’ understanding of the procedure. Based on a comparison with the known prevalence of a sensitive attribute serving as external criterion, we report the first individual-level validation of the Cheating Detection Model, the Triangular Model and the Cheating Detection Triangular Model. Moreover, the sensitivity and specificity of all models was assessed, as well as the respondents’ subjective evaluation of all questioning technique formats. Based on our results, the Cheating Detection Triangular Model appears to be the best choice among the investigated indirect questioning techniques.

The Phantom of the ‘Responsible Consumer’: Unmasking the Intention–Action Gap with an Indirect Questioning Technique

The intention-action gap stands out in research on sustainable consumption for decades. The current research explores the role of socially desirable responding (SDR) in the appearance of this gap by utilising an indirect questioning technique. Two online experiments (n=306 and n=334) demonstrate, in line with most market surveys, that consumers present themselves as highly responsible when being assessed with the standard survey measurement approach (i.e., direct questioning). However, the responses of participants toward the exact same measures of consumers’ social responsibility perceptions and behavioural intentions heavily drop when applying an indirect questioning technique, indicating a substantial overstatement of consumers’ social responsibility perceptions in traditional market surveys. Furthermore, this study provides novel evidence regarding the validity and underlying mechanism of the indirect questioning technique, thereby alleviating long-lasting concerns about this method. Implications for the intention–action gap discussion and consumer ethics research are proposed.

Nothing but the truth? Effects of faking on the validity of the crosswise model.

In self-reports, socially desirable responding threatens the validity of prevalence estimates for sensitive personal attitudes and behaviors. Indirect questioning techniques such as the crosswise model attempt to control for the influence of social desirability bias. The crosswise model has repeatedly been found to provide more valid prevalence estimates than direct questions. We investigated whether crosswise model estimates are also less susceptible to deliberate faking than direct questions. To this end, we investigated the effect of “fake good” instructions on responses to direct and crosswise model questions. In a sample of 1,946 university students, 12-month prevalence estimates for a sensitive road traffic behavior were higher and thus presumably more valid in the crosswise model than in a direct question. Moreover, “fake good” instructions severely impaired the validity of the direct questioning estimates, whereas the crosswise model estimates were unaffected by deliberate faking. Participants also reported higher levels of perceived confidentiality and a lower perceived ease of faking in the crosswise model compared to direct questions. Our results corroborate previous studies finding the crosswise model to be an effective tool for counteracting the detrimental effects of positive self-presentation in surveys on sensitive issues.

Evaluating the sensitive question methods; recommended Uludag Adjustment for the Crosswise Model

Sensitive questions are frequently asked in medical, psychological, and sociological research. In the social science literature, it is widely accepted that when respondents are asked such questions, social desirability bias affects survey research. Different methods in the literature aimed to reduce measurement errors such as social desirability bias and increase the reliability of participants' answers. These methods address the problem to increase the effectiveness of predictions by using indirect questioning techniques. The sensitive question methods evaluated in this study are randomized response technique, grouped answer method, unmatched-count technique, and crosswise model. These methods were evaluated with a comprehensive simulation study. The performances of the methods were evaluated according to the sample size and the sensitive issue prevalence in the hypothetical population. In the second part, in order to reduce the small sample size and low prevalence effect of the crosswise model, the Uludag correction of the crosswise model was proposed in the study. As a result, the crosswise model performs quite well compared to the other methods. In the use of the crosswise model, it is recommended to use the Uludag correction of the model proposed in this study in cases where low prevalence and small samples are studied.

Investigating illegal activities that affect biodiversity: the case of wildlife consumption in the Brazilian Amazon.

The illegal use of natural resources, manifested in activities like illegal logging, poaching, and illegal wildlife trade, poses a global threat to biodiversity. Addressing them will require an understanding of the magnitude of and factors influencing these activities. However, assessing such behaviors is challenging because of their illegal nature, making participants less willing to admit engaging in them. We compared how indirect (randomized response technique) and direct questioning techniques performed when assessing non-sensitive (fish consumption, used as negative control) and sensitive (illegal consumption of wild animals) behaviors across an urban gradient (small towns, large towns, and the large city of Manaus) in the Brazilian Amazon. We conducted 1,366 surveys of randomly selected households to assess the magnitude of consumption of meat from wild animals (i.e., wild meat) and its socioeconomic drivers, which included years the head of household lived in urban areas, age of the head of household, household size, presence of children, and poverty. The indirect method revealed higher rates of wildlife consumption in larger towns than did the direct method. Results for small towns were similar between the two methods. The indirect method also revealed socioeconomic factors influencing wild meat consumption that were not detected with direct methods. For instance, the indirect method showed that wild meat consumption increased with age of the head of household, and decreased with poverty and years the head of household lived in urban areas. Simultaneously, when responding to direct questioning, households with characteristics associated with higher wild meat consumption, as estimated from indirect questioning, tended to underreport consumption to a larger degree than households with lower wild meat consumption. Results for fish consumption, used as negative control, were similar for both methods. Our findings suggest that people edit their answers to varying degrees when responding to direct questioning, potentially biasing conclusions, and indirect methods can improve researchers' ability to identify patterns of illegal activities when the sensitivity of such activities varies across spatial (e.g., urban gradient) or social (e.g., as a function of age) contexts. This work is broadly applicable to other geographical regions and disciplines that deal with sensitive human behaviors.

Indirect questioning methods for sensitive survey questions: Modelling criminal behaviours among a prison population.

Information such as the prevalence and frequency of criminal behaviour is difficult to estimate using standard survey techniques because of the tendency of respondents to withhold or misrepresent information. Social desirability bias is a significant threat to the validity of self-reported data, especially when supplied by persons such as sexual offenders or those convicted of theft or substance abuse. The randomized response approach is an alternative to the standard interview method and offers great potential for researchers in the field of criminal justice. By means of a survey of 792 prison inmates, incorporating both indirect and direct response techniques, we investigate if the prison population also has problems recognizing their participation in criminal acts such as theft, illicit drug use, violence against property, reckless driving and arson. Our research findings suggest that self-reported criminal behaviour among a prison population is affected by social desirability bias and that the behaviour considered is significantly associated with the severity of obsessive-compulsive symptoms. The results also demonstrate the inadequacy of traditional, yet widely used, direct questioning methods, and the great potential for indirect questioning techniques to advance policy formation and evaluation in the field of criminal behaviour.

Do they really wash their hands? Prevalence estimates for personal hygiene behaviour during the COVID-19 pandemic based on indirect questions

BackgroundDuring the COVID-19 pandemic, billions of people have to change their behaviours to slow down the spreading of the virus. Protective measures include self-isolation, social (physical) distancing and compliance with personal hygiene rules, particularly regular and thorough hand washing. Prevalence estimates for the compliance with the COVID-19 measures are often based on direct self-reports. However, during a health crisis there is strong public pressure to comply with health and safety regulations so that people’s responding in direct self-reports may be seriously compromised by social desirability.MethodsIn an online survey, an indirect questioning technique was used to test whether the prevalence of hygiene practices may be lower than in conventional surveys when confidentiality of responding is guaranteed. The Extended Crosswise Model is an indirect questioning technique that guarantees the confidentiality of responding. To the degree that direct self-reports are biased by social desirability, prevalence estimates of hygiene practices such as thorough hand washing based on the Extended Crosswise Model should be lower than those based on direct self-reports.ResultsWe analysed data of 1434 participants. In the direct questioning group 94.5% of the participants claimed to practice proper hand hygiene; in the indirect questioning group a significantly lower estimate of only 78.1% was observed.ConclusionsThese results indicate that estimates of the degree of commitment to measures designed to counter the spread of the disease may be significantly inflated by social desirability in direct self-reports. Indirect questioning techniques with higher levels of confidentiality seem helpful in obtaining more realistic estimates of the degree to which people follow the recommended personal hygiene measures. More realistic estimates of compliance can help to inform and to adjust public information campaigns on COVID-19 hygiene recommendations.

Controlling social desirability bias: An experimental investigation of the extended crosswise model.

Indirect questioning techniques such as the crosswise model aim to control for socially desirable responding in surveys on sensitive personal attributes. Recently, the extended crosswise model has been proposed as an improvement over the original crosswise model. It offers all of the advantages of the original crosswise model while also enabling the detection of systematic response biases. We applied the extended crosswise model to a new sensitive attribute, campus islamophobia, and present the first experimental investigation including an extended crosswise model, and a direct questioning control condition, respectively. In a paper-pencil questionnaire, we surveyed 1,361 German university students using either a direct question or the extended crosswise model. We found that the extended crosswise model provided a good model fit, indicating no systematic response bias and allowing for a pooling of the data of both groups of the extended crosswise model. Moreover, the extended crosswise model yielded significantly higher estimates of campus Islamophobia than a direct question. This result could either indicate that the extended crosswise model was successful in controlling for social desirability, or that response biases such as false positives or careless responding have inflated the estimate, which cannot be decided on the basis of the available data. Our findings highlight the importance of detecting response biases in surveys implementing indirect questioning techniques.

Estimating the prevalence of and characteristics associated with prescription opioid diversion among a clinic population living with HIV: Indirect and direct questioning techniques

BackgroundEvidence suggests that over 50 % of individuals who used prescription opioids non-medically obtained their prescription from friends or family. Despite its high consequence, reliable opioid diversion prevalence estimates are lacking due to social desirability bias. We used indirect questioning, a technique designed to measure sensitive behaviors, to assess the prevalence of prescription opioid diversion among a cohort of individuals with HIV. MethodsWe randomized 581 participants from a large urban HIV clinical cohort to answer either a direct or indirect question about opioid diversion between October 2016-July 2018. We estimated the prevalence of diversion under each method. We also estimated diversion prevalence in subsets of the sample by age, sex, race, HIV risk group, substance use, and mental health co-morbidities. ResultsOf 1,285 patients screened, 581 (45.2 %) reported ever having received an opioid prescription. Of these, 252 (43.4 %) directly answered whether they had ever diverted opioids and 313 (53.9 %) answered the indirect question. The prevalence of opioid diversion under direct and indirect questioning was 6.3 % (95 % CI 3.7 %–10.1 %) and 15.3 % (95 % CI 10.4 %–20.3 %), respectively. In unadjusted analyses, males, non-African Americans, and patients with a history of illicit drug use had a higher diversion prevalence. In adjusted analyses, ever having used cocaine was most associated with diversion (OR 15.67, 95 % CI 0.93−263.17). ConclusionsOpioid diversion was common among this population, with the estimated prevalence more than doubling under the indirect questioning method designed to elicit less biased responses.

Can detailed instructions and comprehension checks increase the validity of crosswise model estimates?

The crosswise model is an indirect questioning technique designed to control for socially desirable responding. Although the technique has delivered promising results in terms of improved validity in survey studies of sensitive issues, recent studies have indicated that the crosswise model may sometimes produce false positives. Hence, we investigated whether an insufficient understanding of the crosswise model instructions might be responsible for these false positives and whether ensuring a deeper understanding of the model and surveying more highly educated respondents reduces the problem of false positives. To this end, we experimentally manipulated the amount of information respondents received in the crosswise model instructions. We compared a crosswise model condition with only brief instructions and a crosswise model condition with detailed instructions and additional comprehension checks. Additionally, we compared the validity of crosswise model estimates between a higher- and a lower-educated subgroup of respondents. Our results indicate that false positives among highly educated respondents can be reduced when detailed instructions and comprehension checks are employed. Since false positives can also occur in direct questioning, they do not appear to be a specific flaw of the crosswise model, but rather a more general problem of self-reports on sensitive topics. False negatives were found to occur for all questioning techniques, but were less prevalent in the crosswise model than in the direct questioning condition. We highlight the importance of comprehension checks when applying indirect questioning and emphasize the necessity of developing instructions suitable for lower-educated respondents.

A Survey on Illicit Drug Use among University Students by Binary Randomized Response Technique: Crosswise Design

This paper aims to introduce Randomized Response Techniques (RRT’s) and show that how RRT’s are implemented in surveys in which sensitive behaviors are investigated. For this purpose, the most popular designs of the Binary RRT are summarized and an experimental study is conducted on drug use among dormitory students at a public university in Ankara, Turkey. Despite the wide applicability of the drug use studies in Turkey, surprisingly any applications using indirect questioning techniques are not observed in the literature. In this study, for the first time, drug use behavior is investigated with Crosswise design which is the most frequently used indirect questioning technique and indirect questioning method (Crosswise design) is compared with direct questioning method to evaluate the effectiveness of the RRT. Results revealed that when Crosswise design is provided on asking sensitive questions, considerably minor response refusals are happened and significantly higher drug-use estimates are observed.