Imputation is an in silico method that can increase the power of association studies by inferring missing genotypes, harmonizing data sets for meta-analyses, and increasing the overall number of markers available for association testing. This unit provides an introductory overview of the imputation method and describes a two-step imputation approach that consists of the phasing of the study genotypes and the imputation of reference panel genotypes into the study haplotypes. Detailed steps for data preparation and quality control illustrate how to run the computationally intensive two-step imputation with the high-density reference panels of the 1000 Genomes Project, which currently integrates more than 39 million variants. Additionally, the influence of reference panel selection, input marker density, and imputation settings on imputation quality are demonstrated with a simulated data set to give insight into crucial points of successful genotype imputation.