Table 4 Inference for the treatment effect, θ, and the within-period intracluster correlation, ρ₁, for a randomly-selected simulated dataset for a SW design with S=1,T=5,m=10, true treatment effect θ=0, and intracluster correlation parameters ρ₁=0.1 and r=1. Estimate and 95% CI correspond to point estimates and 95% confidence intervals for the REML methods and medians of posterior draws and 95% credible intervals for the Bayesian method. Note that standard errors for ρ₁ are not provided in lme4 to permit 95% confidence intervals for the REML methods

From: Evaluating the performance of Bayesian and restricted maximum likelihood estimation for stepped wedge cluster randomized trials with a small number of clusters