Letters Section Editor: Robert M. Golub, MD, Senior Editor.
In Reply: The FDR q value is an approach to the problem of multiple comparisons that, although novel in epidemiology, has already become standard for reporting high-throughput genomic studies.1 Dr Horne maintains that the best statistical practice in genetic association studies is correction of P values for multiple comparisons, citing Havill and Dyer.2 However, that article describes 3 approaches to multiple testing, one of which is FDR; none of the 3 is declared “best statistical practice,” and the authors state that “which method to use is unclear.”
Smith NL, Hindorff LA, Heckbert SR, et al. Genetic Association Studies and False Discoveries—Reply. JAMA. 2007;297(22):2477–2478. doi:10.1001/jama.297.22.2478-a
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: