Statistical modelling of vignette data in psychology

Abstract

Vignette methods are widely used in psychology and the social sciences to obtain responses to multi‐dimensional scenarios or situations. Where quantitative data are collected this presents challenges to the selection of an appropriate statistical model. This depends on subtle details of the design and allocation of vignettes to participants. A key distinction is between factorial survey experiments where each participant receives a different allocation of vignettes from the full universe of possible vignettes and experimental vignette studies where this restriction is relaxed. The former leads to nested designs with a single random factor and the latter to designs with two crossed random factors. In addition, the allocation of vignettes to participants may lead to fractional or unbalanced designs and a consequent loss of efficiency or aliasing of the effects of interest. Many vignette studies (including some factorial survey experiments) include unmodeled heterogeneity between vignettes leading to potentially serious problems if traditional regression approaches are adopted. These issues are reviewed and recommendations are made for the efficient design of vignette studies including the allocation of vignettes to participants. Multilevel models are proposed as a general approach to handling nested and crossed designs including unbalanced and fractional designs. This is illustrated with a small vignette data set looking at judgements of online and offline bullying and harassment.

Pandemic elevates sensitivity to moral disgust but not pathogen disgust

“…The stories were carefully designed during the first wave of the Covid-19 pandemic in spring 2020 and provisionally validated based on a data from the pilot study. The use of vignettes is a common tool used in psychological research 38 and vignettes are also widely employed in a research on sexual and moral disgust 17 – 19 . Nevertheless, one might argue that pathogen disgust was selected primarily to respond to perceptual cues of infection (e.g.…”

Maximization delays decision-making in acute care nursing

“…As all participants received all vignettes (fully crossed design), the multilevel models were fitted with random intercepts for the participants and the vignettes, which accounts for between-vignette heterogeneity and intra-respondent correlation. None of the two conditions for an alternative nested design—that each participant receives a unique set of vignettes or the dimensions defining the vignettes exhaust the variability in the vignette universe 44 —were met. Normality was analysed using the Shapiro-Wilks tests, given the moderate sample size.…”

Exploring the effects of personal and situational factors on cyber aggression

“…For instance, what may be considered as a "severe" incident by one person may be perceived as no so by another. Therefore, future, research should consider adopting a scenario based or vignette-based approach with multi-level modelling as they enable researchers to collect rich data on topics that present challenges when trying to study them directly (Baguley et al, 2022).…”