Ethnicity can confound results in pharmacogenomic studies. Allele frequencies of loci that influence drug metabolism can vary substantially between different ethnicities and underlying ancestral genetic differences can lead to spurious findings in pharmacogenomic association studies. We evaluated the application of principal component analysis (PCA) in a pharmacogenomic study in Canada to detect and correct for genetic ancestry differences using genotype data from 2094 loci in 220 key drug biotransformation genes. Using 89 Coriell worldwide reference samples, we observed a strong correlation between principal component values and geographic origin. We further applied PCA to accurately infer the genetic ancestry in our ethnically diverse Canadian cohort of 524 patients from the GATC study of severe adverse drug reactions. We show that PCA can be successfully applied in pharmacogenomic studies using a limited set of markers to detect underlying differences in genetic ancestry thereby maximizing power and minimizing false-positive findings.