Journal
JOURNAL OF MACHINE LEARNING RESEARCH
Volume 22, Issue -, Pages -Publisher
MICROTOME PUBL
Keywords
FDR control; false discovery rate; sequential hypothesis testing; sequential experimentation; p-values
Ask authors/readers for more resources
This study focuses on controlling the false discovery rate in asynchronous online testing, proposing a general framework that addresses dependency issues and improves existing algorithms. The use of conflict sets is highlighted as a way to better manage dependencies among test statistics.
We consider the problem of asynchronous online testing, aimed at providing control of the false discovery rate (FDR) during a continual stream of data collection and testing, where each test may be a sequential test that can start and stop at arbitrary times. This setting increasingly characterizes real-world applications in science and industry, where teams of researchers across large organizations may conduct tests of hypotheses in a decentralized manner. The overlap in time and space also tends to induce dependencies among test statistics, a challenge for classical methodology, which either assumes (overly optimistically) independence or (overly pessimistically) arbitrary dependence between test statistics. We present a general framework that addresses both of these issues via a unified computational abstraction that we refer to as conflict sets. We show how this framework yields algorithms with formal FDR guarantees under a more intermediate, local notion of dependence. We illustrate our algorithms in simulations by comparing to existing algorithms for online FDR control.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available