Advances in high throughput technology have enabled the generation of unprecedented amounts of genomic data (e.g., next-generation sequence data, transcriptomics, metabolomics, and proteomics), which promises to unravel the genetic architecture of complex traits. These discoveries may lead to novel therapeutic targets, guide disease prevention, and enable personalized medicine. However, the pace of data generation surpasses the ability to process and analyze the vast amounts of data. For example, in a typical study of transcription regulation, the relationship between more than 1 million genetic variants and 10,000 transcript levels are explored, requiring tens of billions of tests. In order to address this problem, we propose a fast, accurate, and robust method that can assess the significance of associations between quantitative phenotypes and genotypes. The method is an extension of the allelic test commonly used in case–control studies for the analysis of quantitative traits. We show the asymptotic equivalence of the proposed test to linear regression results. We also reduce a generalized linear regression problem to the comparison of two groups, which can handle nonnormal and survival time phenotypes.