Fig. 6From: Consequences of ignoring clustering in linear regressionType I error rates (%) from the OLS model for ICC = 0.1 and 0.3, by target prevalence rates of \({x}_{ij}\) (A 0.05, B 0.10, C 0.20, and D 0.40), and thirds of the distribution of the dispersion (expressed as SD) of prevalence of \({x}_{ij}\) across the clusters within each sampleBack to article page