Extended Data Table 1 Summary of the analyses in the main text

From: Virtual communication curbs creative idea generation

  1. We used a Negative Binomial regression model for all tests with number of ideas or number of creative ideas as the dependent measure (see Supplementary Information A for model justification and assumption tests). For total props remembered, we used a mixed-effect Negative Binomial Regression and for unexpected props remembered, we used a mixed-effect Poisson regression (Supplementary Information C for test assumptions). For all other dependent measures, when the measure was per participant (e.g., eye gaze), we used a linear mixed-effect regression with random effect of group number. When the measure was per group (e.g., selected idea score), we used an OLS regression model (see Supplementary Information B and C for model assumption tests of normality and heteroskedasticity and for robustness checks). All tests are two-tailed and there were no adjustments made for multiple comparisons (for a discussion of our rationale, see Supplementary Information S).
Back to article page