Key Words: Statistical Power · Disease Model · Rejection · Markov Chain Monte Carlo (MCMC) · Backward Sampling · Receiver Oper-

Objective: Assessing the statistical power to detect suscepti-bility variants plays a critical role in GWA studies both from the prospective and retrospective points of view. Power is em-pirically estimated by simulating phenotypes under a disease model H1. For this purpose, the “gold ” standard consists in si-mulating genotypes given the phenotypes (e.g. Hapgen). We introduce here an alternative approach for simulating pheno-types under H1 that does not require generating new geno-types for each simulation. Methods: In order to simulate phe-notypes with a fixed total number of cases and under a given disease model, we suggest three algorithms: i) a simple re-jection algorithm; ii) a numerical Markov Chain Monte-Carlo (MCMC) approach; iii) and an exact and efficient backward sampling algorithm. In our study, we validated the three al-gorithms both on a toy-dataset and by comparing them wit