R-script fot the preprint Big Five personality traits and COVID-19 precautionary behaviors among older adults in Europe, https://psyarxiv.com/rvbjf/

To account for the clustering of the respondents in countries, associations between personality and COVID-19 precautionary behaviors were examined with multilevel, randomintercept logistic regression models to avoid artificially low standard errors of estimates and potentially inflated Type 1 error rate. The random intercept for country accounted for the potential non-independence of observations from the same country. The five personality traits (extraversion, agreeableness, conscientiousness, neuroticism, and openness) and the five outcomes (wearing a mask, limiting social contacts, keeping distance, washing hands, and using disinfectant) were analyzed in separate models (a total of 25 models).

We first examined the unconditional model without predictors to determine the proportion of variance in the outcomes attributable to countries and individual-level factors. We then included the fixed effects of personality and covariates in the model. Personality variables were standardized before the analysis. All analyses and data visualizations were conducted in R Statistical Software (version 3.6.1; R Team, 2019) using the packages lme4 (Bates, Mächler, Bolker, & Walker, 2015) and ggplot2 (Wickham, 2016).

As a supplementary analysis, we examined the association between personality and taking all three types of COVID-19 precautions (wearing a mask, limiting social contacts, keeping distance, washing hands, and using disinfectant).