Pouring water into wine: revisiting the advantages of the crosswise model for asking sensitive questions

The Crosswise Model (CM) has been proposed as a method to reduce effects of social in sensitive questions. In contrast with former variants of Randomized Response (RRTs), the crosswise model neither offers a self-protective response strategy, nor it require a random device. For these reasons, the crosswise model has received a lot of attention in the scientific community. However, previous validation studies have mostly negatively connoted behaviour and thus draw on the principle of “more is better”. prevalence rates of socially undesirable behaviour in the crosswise model cannot be unambiguously to a reduction in social desirability bias, since random ticking from respondent confusion about the question format cannot be ruled out as an explanation. Unlike most research on crosswise models and randomized response, we conduct an experiment in a general population survey that does not assess connoted but socially desirable behaviour (namely, whether respondents had blood within the last twelve months). This design allows us to empirically disentangle reduction of social desirability bias from random responses. We find signifcantly higher rates in the crosswise condition than in the direct question. What is more, we not identify any subgroup of respondents, in which the CM successfully reduced social bias. These results cast doubts on the validity of cosswise models. They suggest a considerable number of respondents do not comply with the intended procedure.