Measuring and explaining tax evasion: Improving self-reports using the crosswise model

Due to its sensitive nature, tax compliance is difficult to study empirically, and valid information on tax evasion is rare. More specifically, when directly asked on surveys, respondents are likely to underreport their evasion behavior. Such invalid responses not only bias prevalence estimates but may also obscure associations with individual predictors. To generate more valid estimates of tax evasion, we used a new method of data collection for sensitive questions, the crosswise model (CM). The CM is conceptually based on the randomized response technique (RRT), but due to its advanced design, it is better suited for large surveys than classical RRTs. In an experimental online survey, we compared the CM (N = 862) to standard direct questioning (DQ; N = 305). First, our results showed that the CM was able to elicit a higher proportion of self-stigmatizing reports of tax evasion by increasing privacy in the data collection process. Second, on average, we found stronger effects of our predictor variables on tax evasion in the CM condition compared with the DQ condition such that an egoistic personality and the opportunity for tax evasion predicted actual tax evasion only in the CM condition.     

Partisan difference in social desirability bias on anti-immigrant sentiments: Covert and overt expression among French voters

Various types of anti-immigrant sentiments have been taken as the characteristic independent variable to explain specific support for radical right parties. However, some survey respondents tend to conceal their attitudes towards socially sensitive issues. To overcome this challenge, the present study used a list experiment method (item count technique) to reveal respondents' covert attitudes towards immigrants (and compared these with overt expressions) based on party support in France. Results indicated similar levels of anti-immigrant sentiments among radical right National Front supporters and other centre-rightist parties. In addition, comparison with the direct question method revealed that while supporters of centre-right parties were reluctant to express their anti-immigrant sentiment in overt expressions, National Front supporters willingly expressed it overtly more than in covert expressions. Using regression analysis, this paper demonstrates the diversity of anti-immigrant norms and the social desirability bias gap in the French political space.     

Social stereotypes,personality traits and regional perception displaced: Attitudes towards the ‘new’ quotatives in the U.K.1

This article investigates the attitudes of British respondents towards the quotatives be like and go. The results of a matched guise test and a social attitudes survey are presented and compared with the findings of studies on be like and go‐perception in the U.S. It is found that the perceptual load of the two quotatives on both sides of the Atlantic is similar in some respects and different in others. This effectively means that, in cases of borrowing, the stereotypes attached to linguistic items are not simply taken over along with the surface item. Rather, the adoption of global resources is a more agentive process, whereby attitudes are re‐evaluated and re‐created by speakers of the borrowing variety. It is suggested that attitudinal information presents an important backdrop to distributional studies in cases of global language trends.     

The Effects of Branching on Item Nonresponse

The analysis of responses to a large sample survey instrumentindicates that branching instructions significantly increasethe rate of item nonresponse for items immediately followingthe branch. While older respondents did have a higher incidenceof item nonresponse, none of six other factors (education, gender,distance to next question, number of previous branches, futurebehavior, or nature of response) hypothesized to affect itemnonresponse were significantly related to the rate of nonresponse.     

Construct Validity and Error Components of Survey Measures: A Structural Modeling Approach

Measurement errors can have profound effects on statisticalrelationships, and better information on the quality of measuresseems needed. This study uses a new technology—structuralmodeling of data from special supplements to regular surveys—togenerate estimates of construct validity, method effects (amajor source of correlated error), and residual error (mainlyrandom error) for a broad set of measures obtained from fivenational surveys and an organizational survey (total respondents= 7,706). Analysis of these estimates suggested that a typicalsurvey item, when administered by a respected survey organizationto a general population sample, can be expected to yield 50–83percent valid variance, 0–7 percent method effects variance,and 14–48 percent residual variance. Multivariate analysisshowed that over two-thirds of the variation in measurementquality could be explained by 13 survey design characteristics;characteristics of respondents explained a small additionalportion. Results provide: (a) information on design conditionsassociated with better (or worse) measurement quality, (b) empiricallybased suggestions for improving measurement quality in futuresurveys, and (c) a set of coefficients for predicting the qualityof measures not studied here.     

Perceptions of the Extent of Problem Gambling Within New Casino Communities

Several recent studies using objective measures have found that the rate of pathological gambling in the U.S. is less than 5%. To determine the general population's perception of the prevalence of pathological gambling, a survey was conducted in seven communities where casinos have recently opened. Of the 1631 respondents who provided an estimate, the mean response was that 16% of the community residents were problem gamblers, more than three times the rate found by studies using specific diagnostic criteria. A regression equation found several demographic and attitudinal items are associated with higher prevalence estimates. In addition, the data support a close to home hypothesis that respondents who have relatives who have experienced problems with gambling will tend to perceive higher rates of problem gambling in the community.     

Sexual risk behaviors and alcohol: Higher base rates revealed using the unmatched‐count technique

HIV/AIDS is a disease whose only known prevention is behavioral. Risky sex is one of the ways in which people become infected with HIV, as well as other STDS. Estimating the base rates of risky sex and risky sex after drinking proves difficult. This study uses the unmatched‐count technique (UCT) to estimate base rates for sexual risk behaviors and sexual risk behaviors after drinking and compares the findings with those estimates found using conventional methods. UCT does not require the participant to directly answer sensitive questions, and, thus, may provide more accurate reporting than other methods. In a population of college students, the UCT revealed higher estimates of base rates for having had sex, having had sex without a condom, and having had sex without a condom after drinking than an anonymous self‐report survey. These higher estimates provide a better feel for the level of these risk behaviors, may help understand the relationship between alcohol and risky sex, and point to the need to target more interventions for condom use and condom use in the presence of drinking among college students.     

A social network approach to estimating seroprevalence in the United States

Results from a representative survey of respondents in Florida are given, concerning their knowledge about members of their personal network, and specifically how many people respondents know in selected subpopulations. We employ a method known as a “network scale-up method”. By using a collection of subpopulations of known size, and also asking about one subpopulation (those who are seropositive) of unknown size, we make various estimates of personal network size and the size of the seropositive subpopulation. Our best (maximum likelihood, unbiased) estimates are 108 members of the network defined by “having been in contact with during the previous two years”, and (approximately unbiased) 1.6 million for the seropositive subpopulation. Because of the proportional over-representation of AIDS (and presumably, therefore, seropositive) in Florida, by a factor of about two, this latter estimate could be an overestimate.     

Book reviews

Academics and others have long made use of survey items framed in a Likert form. This type of question, where respondents are asked to agree or disagree with a series of statements, has long been a staple of those creating attitude scales. There has, however, been increasing use of these items in inappropriate settings. This article discusses the appropriate and inappropriate use of Likert items in social science research, using three settings where the agree-disagree response settings are wrongly applied. It concludes with speculation about the diffusion of this form throughout the research culture.     

EFFECTS OF INTERVIEWER GENDER, INTERVIEWER CHOICE, AND ITEM WORDING ON RESPONSES TO QUESTIONS CONCERNING SEXUAL BEHAVIOR

We examined factors influencing responses to questions on sexualbehavior among adult respondents 18–49 years old (unweightedN = 2,030) obtained through a random-digit dialing survey. Basedon self-disclosure and perceived control the ory, we hypothesizedthat giving people a choice in selecting the gender of theirinterviewer rather than being assigned an inter viewer, andusing questions that are "supportive" of what may be perceivedof as nonnormative behavior (enhanced items), would increasedata quality relative to, respectively, matched-or opposite-genderinterviewer conditions and standard worded items. The enhanceditems facilitated responding to a number of sensitive topics.However, the effects of item wording on item response are oftenmediated by interviewer conditions. The "choice" results suggestthat giving respondents greater control decreases question threat.However, the overall findings argue for matching respondentsand interviewers on gender over opposite-gender interviewersor allowing respondents to select their interviewer's gender.Wording and interviewer manipulations reduced the discrepanciesbetween men's and women's self-reports of sexual behavior, butthey did not eliminate them, and in some cases they had no effect.The present findings suggest that males tend to be influencedby variations in item wording, interviewer gender, and respondentcontrol across a somewhat wider range of sexual topics. In general,the findings recommend matching respondents and interviewerson gender and the use of more supportive wording in sexual behaviorquestions. However, for assessment of some topics (e.g., sexualviolence) in particular segments of the population (e.g., men),other procedures, such as increasing respondent control, maybe a better choice. Overall, the data support the view thatin terms of preferred procedures, not all sexual topics arecreated equal.     

Eye-Tracking Data: New Insights on Response Order Effects and Other Cognitive Shortcuts in Survey Responding

Survey researchers since Cannell have worried that respondents may take various shortcuts to reduce the effort needed to complete a survey. The evidence for such shortcuts is often indirect. For instance, preferences for earlier versus later response options have been interpreted as evidence that respondents do not read beyond the first few options. This is really only a hypothesis, however, that is not supported by direct evidence regarding the allocation of respondent attention. In the current study, we used a new method to more directly observe what respondents do and do not look at by recording their eye movements while they answered questions in a Web survey. The eye-tracking data indicate that respondents do in fact spend more time looking at the first few options in a list of response options than those at the end of the list; this helps explain their tendency to select the options presented first regardless of their content. In addition, the eye-tracking data reveal that respondents are reluctant to invest effort in reading definitions of survey concepts that are only a mouse click away or paying attention to initially hidden response options. It is clear from the eye-tracking data that some respondents are more prone to these and other cognitive shortcuts than others, providing relatively direct evidence for what had been suspected based on more conventional measures.     

Does Telephone Audio Computer-Assisted Self-Interviewing Improve the Accuracy of Prevalence Estimates of Youth Smoking? Evidence from the UMass Tobacco Study

Despite their advantage for obtaining representative samplesof adolescents, telephone surveys have been regarded as an inferiormethod for collecting data on youth tobacco use because theyyield lower estimates than school-based, self-administered surveys.Although no gold standard for smoking estimates exists, thelower estimates in telephone surveys have been attributed tounderreporting due to youths’ concern that parents orothers may overhear their responses. Telephone audio computer-assistedself-interviewing (T-ACASI) is a cost-effective method for obtaininga representative sample of youths and provides increased privacyfor the respondent. We hypothesize that using T-ACASI wouldencourage youths to report more fully smoking behavior comparedto traditional interviewer-administered telephone methods. Ouranalysis further assesses whether respondent age, gender, race/ethnicity,and parental attitude toward smoking moderated the relationshipbetween survey mode and smoking reports. Using data from a statewidetobacco use survey that randomly assigned youth respondentsto either T-ACASI or interviewer-administered modes, we findthat youths were more likely to report smoking behaviors inT-ACASI mode and that this was especially true for girls, particularlythose who believed their parents would disapprove strongly oftheir smoking. The findings suggest that traditional telephonesurveys may underestimate smoking prevalence in most girls bya factor of two, and that a technique for ensuring privacy forthese respondents is an important component of effective telephonesurvey methodology.     

"How much do you spend gambling?" ambiguities in survey questionnaire items

The validity of a survey's findings is dependent upon the clarity and lack of ambiguity contained in each individual item yet minimal attention has been directed to this issue in most prevalence studies. Researchers have shown a tendency to accept the uncritical assumption that respondents interpret seemingly simple and straightforward items such as 'how much do you spend gambling?' in a consistent manner. No attempt is made to confirm the uniformity of responses by clarifying the mathematical formulae used by respondents to derive their answers. The purpose of this paper was to examine the consistency shown by a sample of 181 medical undergraduate subjects in estimating the level of gambling expenditure in a series of five case vignettes describing various scenarios of wins and losses during a session of gambling. Results revealed a wide variation in calculated figures depending upon whether or not subjects interpreted the item to mean net expenditure or turnover. Only two thirds or less of subjects calculated the figure to be the difference between the initial amount risked and the residual at the conclusion of the session. It is suggested that more attention be paid in prevalence and clinical studies to providing subjects with clear instructions on how to calculate expenditure estimates.     

Spacing, Position, and Order: Interpretive Heuristics for Visual Features of Survey Questions

We present the results of six experiments that demonstrate theimpact of visual features of survey questions on the responsesthey elicit, the response process they initiate, or both. Allsix experiments were embedded in Web surveys. Experiments 1and 2 investigate the effects of the placement of nonsubstantiveresponse options (for example, "No opinion" and "Don’tknow" answer options) in relation to the substantive options.The results suggest that when these options are not differentiatedvisually (by a line or a space) from the substantive options,respondents may be misled about the midpoint of the scale; respondentsseemed to use the visual rather than the conceptual midpointof the scale as a reference point for responding. Experiment3, which varied the spacing of the substantive options, showeda similar result. Responses were pushed in the direction ofthe visual midpoint when it fell to one side of the conceptualmidpoint of the response scale. Experiment 4 examined the effectsof varying whether the response options, which were arrayedvertically, followed a logical progression from top to bottom.Respondents answered more quickly when the options followeda logical order. Experiment 5 examined the effects of the placementof an unfamiliar item among a series of similar items. For example,one set of items asked respondents to say whether several makesand models of cars were expensive or not. The answers for theunfamiliar items depended on the items that were nearby on thelist. Our last experiment varied whether a battery of relateditems was administered on a single screen, across two screens,or with each item on its own screen. The intercorrelations amongthe items were highest when they were all on the same screen.Respondents seem to apply interpretive heuristics in assigningmeaning to visual cues in questionnaires. They see the visualmidpoint of a scale as representing the typical or middle response;they expect options to be arrayed in a progression beginningwith the leftmost or topmost item; and they expect items thatare physically close to be related to each other conceptually.     

Some Correlates of Emotional Well-Being Among New England College Students

Abstract

In a questionnaire survey of New England college students, a large number of undergraduate men and women reported problems related to their personal, social, or academic adjustment. Given a list of 22 items described as “common concerns or feelings experienced by college students,” respondents were asked to rate the extent to which each item had been a problem for them in the past year. Most students (86%) reported having very much or somewhat of a problem with one or more items on the list. Pressure to do well in school, problems with weight control, anxiety, poor concentration and depression were among the most commonly reported concerns. The prevalence of these self-reported concerns and problems was found to be significantly associated with the respondents' sex, their perceptions of their health status, and academic standing.     

CONTEXT EFFECTS FOR CENSUS MEASURES OF RACE AND HISPANIC ORIGIN

This paper reports on the results of a split-ballot experimentconducted in 1987 to test alternative versions of the decennialcensus long form. Two forms were randomly assigned and self-administeredin group sessions involving a total of 515 respondents. Theorder of race and Hispanic origin items was experimentally manipulated.The standard long form asks race, then Hispanic origin. Theexperimental form reversed the order of the items in order toreduce perceived redundancy, and to create a more restrictedframe of reference for the race item. The objectives of thecontext manipulation were (1) to reduce item nonresponse forthe Hispanic origin item, and (2) to reduce reporting of "Otherrace" by Hispanics in the race item. Objective (1) was met.Objective (2) was met for Hispanics born in a U.S. state, butnot for immigrants. The results are interpreted as reflectinga process of acculturation that affects how Hispanic respondentsapply U.S. racial categories "white" and "black" in the census.     

A PARTIAL INDEPENDENCE ITEM RESPONSE MODEL FOR SURVEYS WITH FILTER QUESTIONS

In many surveys, responses to earlier questions determine whether later questions are asked. The probability of an affirmative response to a given item is therefore nonzero only if the participant responded affirmatively to some set of logically prior items, known as "filter items." In such surveys, the usual conditional independence assumption of standard item response models fails. A weaker "partial independence" assumption may hold, however, if an individual's responses to different items are independent conditional on the item parameters, the individual's latent trait, and the participant's affirmative responses to each of a set of filter items. In this paper, we propose an item response model for such "partially independent" item response data. We model such item response patterns as a function of a person-specific latent trait and a set of item parameters. Our model can be seen as a generalized hybrid of a discrete-time hazard model and a Rasch model. The proposed procedure yields estimates of (1) person-specific, interval-scale measures of a latent trait (or traits), along with person-specific standard errors of measurement; (2) conditional and marginal item severities for each item in a protocol; (3) person-specific conditional and marginal probabilities of an affirmative response to each item in a protocol; and (4) item information and total survey information. In addition, we show here how to investigate and test alternative conceptions of the dimensionality of the latent trait(s) being measured. Finally, we compare our procedure with a simpler alternative approach to summarizing data of this type.     

MEASURING EXTREME RESPONSE STYLE

Research on extreme response style (ERS) in rating scale responseshas been characterized by conflicting findings and little agreementover how to assemble and validate ERS measures. This articleproposes that, when ERS is defined as a proportion of extremeresponses, an ERS measure will be more accurate if the itemsare uncorrelated and have equal extreme response proportions.Furthermore, appropriate stochastic models should be used toassess the internal reliability and convergent validity of thesemeasures. An ERS measure is created and validated with thismethod, using items from a survey administered in 1975 and 1987to large samples of U.S. adults serving on a consumer panel.We find that ERS is stable over a lengthy survey compared toa benchmark stability for a "perfect" measure. Furthermore,the distribution of ERS over this population is stable overtime. Respondents' ERS is related to their age, education level,and household income but not to their gender.     

Use of the scale-up methods in injury prevention research: An empirical assessment to the case of choking in children

The scale-up method estimates the size of hard to count subpopulations. This method is based on the idea that the proportion of subjects in a subpopulation E known to each member of the general population T is the same as the proportion of members of E belonging to general population T.     

Problem Gambling Within a Chinese Speaking Community

The purpose of this study was to obtain preliminary data on pathological gambling rates within a metropolitan Chinese community to determine if more costly extensive epidemiological surveys were justified. Two thousand survey questionnaires were distributed to parents through children attending a local Chinese speaking school. A response rate of 27.4% was obtained. Over a quarter of respondents were born overseas in either Mainland China or Hong Kong. Results indicated that gambling was not a popular activity with 60.0% of respondents stating that they never gambled. Of those who gambled, a third of respondents identified lotto as the preferred form. Using a Chinese translation version of the SOGS and a cut-off score of 10, a prevalence estimate of 2.9% for pathological gambling was found with males showing a higher rate (4.3%) as compared to females (1.6%). Respondents reporting a prior history of gambling in their country of origin were more likely to be classified as probable pathological gamblers. Despite the use of a sample of convenience, changes to the wording of two items in the Chinese translation of the SOGS and the possibility of false positive cases in the present study, it is concluded that further research into problem gambling in this community should be undertaken.