Dear mixed modelers, If I have interactions between a categorical covariate and a random-effects grouping factor. How can I test formally the correlations? For example data(Machines, package = "MEMSS") fm2aM <- lmer(score ~ Machine + (0 + Machine|Worker), Machines) Random effects: Groups Name Variance Std.Dev. Corr Worker MachineA 13.81574 3.71695 MachineB 61.94506 7.87052 0.805 MachineC 16.00492 4.00061 0.625 0.772 How do I formally test the significance for every single Corr(A,B); Corr(A,C); Corr(B,C)? thanks for any help, Ren?