Mixed models have been useful in correcting for confounding due to population stratification and hidden relatedness in genome wide association studies. This class of models includes linear mixed models (LMM) and generalised linear mixed models (GLMM). Existing mixed model approaches to correct for population substructure have been investigated with both continuous and case/control response variables. However, they have not been investigated in the context of extreme phenotype sampling (EPS), where genetic covariates are only collected on samples having extreme response variable values. In this work, we compare the performance of existing mixed model approaches (LTMLM, GMMAT) with EPS data analysed as a binary trait. We use simulation to estimate the type 1 error of all approaches when there is confounding. Since LMMs are commonly used even with binary traits, we also analysed the data using a LMM. This work was done under the supervision of Kelly Burkett.