The false discovery rate has recently become an important
application in fields where large amounts of data are analyzed, such
as in genomics, astronomy, and brain imaging. Statisticians have
also been interested in the false discovery rate because it shows
some interesting and useful connections between different
statistical paradigms.
Does
it describe a new discovery or a new methodology that's useful to
others?
It describes a new methodology.
Could
you summarize the significance of your paper in layman's terms?
A typical task statisticians face today is to test thousands of
hypotheses simultaneously. This paper presents a straightforward
method for estimating the proportion of false positives among all
tests called significant. This proportion is called the false
discovery rate.
How
did you become involved in this research?
I became involved in this research because of my interest in
applying the methodology to various problems in genomics. Several
collaborators at Stanford University were instrumental in getting me
involved.
John Storey
Assistant Professor
Department of Biostatistics
Department of Genome Sciences
University of Washington
Seattle, WA, USA
