Reducing socially desirable responses in epidemiologic surveys: An extension of the Randomized-Response Technique. Epidemiology, 21, 379-382

Institute of Experimental Psychology, University of Duesseldorf, Duesseldorf, Germany.
Epidemiology (Cambridge, Mass.) (Impact Factor: 6.18). 05/2010; 21(3):379-82. DOI: 10.1097/EDE.0b013e3181d61dbc
Source: PubMed

ABSTRACT Even though the validity of self-reports of sensitive behaviors is threatened by social desirability bias, interviews and questionnaires are widely used in epidemiologic surveys on these topics.
In the randomized-response technique, a randomization device is used to determine whether participants are asked to respond truthfully or whether they are prompted to provide a prespecified response. In this study, the randomized-response technique was extended by using a cheating-detection modification to obtain more valid data. The survey was on the dental hygiene habits of Chinese college students.
Whereas only 35% of men and 10% of women admitted to insufficient dental hygiene when questioned directly, 51% of men and 20% of women attested to this socially undesirable behavior in a randomized-response survey.
Given the considerable discrepancy between the results obtained by direct questioning and by using the randomized-response technique, we propose that this technique be considered for use in epidemiologic studies of sensitive behaviors.

Download full-text


Available from: Morten Moshagen, Jan 15, 2014
  • Source
    • "Finally, the present study relied on self-reports so the validity of the responses cannot be guaranteed (Tourangeau and Yan, 2007; Moshagen et al., 2010). The effects of these concerns were held to a minimum in the present investigation through assurances of confidentiality and anonymity. "
    [Show abstract] [Hide abstract]
    ABSTRACT: AIMS: To investigate the relationship between alcohol expectancies and alcohol use in a community sample as a function of age and gender. METHODS: The study is based on a national probability sample of 6467 German adults. Respondents were grouped into five age groups ranging from 18 to 59 years. A brief version of the Comprehensive Alcohol Expectancy Questionnaire was used to assess alcohol expectancies. Alcohol use was assessed by the number of drinking days during the past month and the number of drinks on an average drinking day. RESULTS: Prior to conducting group comparisons, measurement invariance across age and gender was established. Latent mean level comparisons showed that the endorsement of both positive and negative expectancies almost linearly decreased with increasing age. However, this decrease was not reflected in alcohol consumption patterns. Structural analysis of the expectancy factors and drinking variables showed that the predictive power of expectancies varied by age and gender. Particularly, expectancies related to social assertiveness and sexual enhancement were strong predictors only in younger, but not in older respondents. Conversely, expectancies related to tension reduction and impairment were the most important predictors of drinking in respondents older than 30 years, but not in younger age groups. Additionally, the onset and course of age-related changes in expectancies was moderated by gender. CONCLUSIONS: The present study demonstrates substantial age-related changes in the relationship between alcohol expectancies and alcohol use. Moreover, the profile of alcohol expectancies appears to be more important than their absolute strength.
    Drug and alcohol dependence 06/2012; 126(3). DOI:10.1016/j.drugalcdep.2012.05.040 · 3.28 Impact Factor
  • Source
  • [Show abstract] [Hide abstract]
    ABSTRACT: To monitor trends in under-reporting of smoking in Italy over the last two decades. A total of 9 representative population-based surveys on smoking conducted in Italy in 1990 and annually between 2001 and 2008, covering 26,397 individuals, were studied. The number of cigarettes per day per person aged 15 years or over, obtained from these interview-based surveys, was compared with official data from legal sales. Over the last two decades, self-reported smoking prevalence progressively decreased from 32% in 1990 to 22% in 2008. Self-reported daily per capita consumption of cigarettes also showed a reduction between 1990 and 2008, notably so over the last few years (from 5.2 in 1990 to 4.0 in 2004 to 3.2 in 2008). According to data from legal sales, number of cigarettes per day per person decreased from 5.3 in 1990 to 5.0 in 1992, levelled off from 1992 to 1997, subsequently increased from 5.0 in 1997 to 5.8 in 2002 (likely due to control of smuggling), and decreased over the last 6 years (to 4.9 in 2008). These figures correspond to an under-reporting of approximately 1% in 1990, 25% in 2001 and up to 35% in 2008. The difference in cigarette consumption between legal sale and self-reported data has substantially increased over the last two decades in Italy, reflecting increasing under-reporting of cigarette consumption mainly due to a decreasing social acceptability of smoking. Comparisons between interview-based and legal sale data are complicated by factors such as smuggling control and changes in the population (eg, increased proportion of immigrants); however these are able to justify only a small proportion of the gap found in Italy.
    Tobacco control 01/2011; 20(1):34-9. DOI:10.1136/tc.2009.034132 · 5.15 Impact Factor
Show more