Page 110 - Demo

Chapter 5108the ICC(A, 1) to test for absolute agreement between rates. We report the ICC estimate and the 95% confidence interval.Furthermore, we used the R package correlation (Makowski et al., 2020) to test the relationship between pre-date attractiveness ratings, post-date attractiveness ratings, and date outcome. The correlation package allows for computation of a wide variety of correlations, such as Bayesian multilevel correlations. In our case, we used Bayesian multilevel Spearman correlations to investigate the association between pre-date and post-date attractiveness ratings. To test the relationships between date outcome and pre-date and post-date attractiveness ratings, respectively, we used Bayesian point-biserial correlations. These analyses were based on a dataset that consisted of only complete cases for all three variables of interest. In total, this concerned 482 datapoints of 58 participants.For our main analyses, we used Bayesian mixed models. Bayesian analyses have gained in popularity over the past few years because they offer a number of benefits compared to frequentist analyses (Kruschke et al., 2012; Makowski et al., 2019). While frequentist methods (e.g., p-value null-hypothesis testing; Wagenmakers, 2007) inform us about the credibility of the data given a hypothesis, Bayesian methods inform us about the credibility of our parameter values given the data that we observed. This is reflected in the different interpretation of frequentist and Bayesian confidence intervals: The first is a range of values that contains the estimate in the long run, while the latter tells which parameter values are most credible based on the data (Kruschke et al., 2012; McElreath, 2018). Furthermore, Bayesian methods allow for the inclusion of prior expectations in the model, are less prone to Type I errors, and are more robust in small and noisy samples (Makowski et al., 2019). Altogether, these reasons make Bayesian methods a useful tool for data analysis.All models were created in the Stan computational framework and accessed using the brms package (Bürkner, 2017, 2018) , version 2.17.0. All models were run with 4 chains and 5000 iterations, of which 1000 were warmup iterations. We checked model convergence by inspecting the trace plots, histograms of the posteriors, Gelman-Rubin diagnostics, and autocorrelation between iterations (Depaoli & van de Schoot, 2017). We found no divergences or excessive autocorrelation in any model.Tom Roth.indd 108 08-01-2024 10:41