Fig. 3From: Increase in power by obtaining 10 or more controls per case when type-1 error is small in large-scale association studiesExpected p-value under replication of an association versus the number of controls per case as α decreases, as the power of a study with 1 control per case increases from 0.1 to 0.2 to 0.3 to 0.5. Dotted lines represent the α level for that color. Both axes are on a log scaleBack to article page