False discovery control with p-value weighting

By Christopher R. Genovese, Kathryn Roeder, Larry A. Wasserman. 2006

354 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b877cf63a1174fbafc1a91aa009f6e9b9c661849

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Discovering the false discovery rate (2010, background): “The weights may incorporate differing importance of the hypotheses (Benjamini and Hochberg, 1997), or different prospects for showing effects (Genovese et al., 2006).”
GATES: a rapid and powerful gene-based association test using extended Simes procedure. (2011, methodology): “A procedure for assigning prior p value weights based on a mixture model for p values has been suggested.(19) Indeed, given the observed p values, it is possible to optimize the choice of p value weights to be applied to tests grouped by prior information.”
Covariate powered cross‐weighted multiple testing (2017, methodology): “These results are valuable, since weighted multiple testing procedures are tolerant to weight mispecification (Genovese et al., 2006): choosing good weights can lead to huge increases in power, yet “bad” weights will only slightly decrease power”
Large‐scale multiple testing under dependence (2009, methodology): “Comparing with testing procedures that were proposed by Genovese et al. (2006), Benjamini and Heller (2007) and Wei and Li (2008), our testing procedure does not rely on prior information such as prespecified weights or welldefined clusters for different time periods.”
Two simple sufficient conditions for FDR control (2008, methodology): “Both types of weighting are of interest and of diﬀerent nature; using weighted p -values can have a large impact on power (Genovese et al., 2006; Roquain and van de Wiel, 2008; see also above Remark 2.8), while using a volume Λ diﬀerent from the cardinality measure can be of relevance for some…”
α‐investing: a procedure for sequential control of expected false discoveries (2008, methodology): “Genovese et al. (2006) described other testing situations that offer domain knowledge.”
Data-driven hypothesis weighting increases detection power in genome-scale multiple testing (2016, methodology): “In addition, the IHW method readily extends to other weighted multiple testing procedures [6].”
Leveraging polygenic functional enrichment to improve GWAS power (2017, methodology): “Applying these weights while imposing a global p value threshold of 5 3 10 8 yields the well-known ‘‘weighted-Bonferroni’’ procedure first described in Genovese et al.(36) With independently derivedweights that average to 1, this procedure guarantees”
CHiCAGO: robust detection of DNA looping interactions in Capture Hi-C data (2015, methodology): “[15], which is a generalisation of a segment-wise weighting procedure by Sun et al.”
Asymptotic optimality of the Westfall--Young permutation procedure for multiple testing under dependence (2011, background): “[12] and Roeder and Wasserman [28] looked at the intriguing possibility of incorporating prior information by p-value weighting.”
Multiple testing with the structure‐adaptive Benjamini–Hochberg algorithm (2016, methodology): “…to be an estimate of the proportion of nulls (which is constant across all i ), then this can give us Storey’s modiﬁcation of the BH procedure. b b not dependent on P ), then this is equivalent to Genovese et al. [15] p-value weighting method, their weights w i are given by 1 / q i in our notation.”
Optimal weighting for false discovery rate control (2008, methodology): “Note that this result covers the earlier result of Genovese et al. (2006); Blanchard and Roquain (2008), by taking W i ( u ) = w i constant in u .”
Large-scale inference (2010, methodology): “Notes The leukemia data was the motivating example in Golub et al. (1999), an early exploration of advanced statistical approaches to microarray experiments. Ridgeway and MacDonald (2009) discuss the police data, providing a much more extensive analysis than the one here. Van’t Wout et al. (2003) or”
A unified treatment of multiple testing with prior knowledge using the p-filter (2017, methodology): “Their work in turn generalizes earlier work using prior weights [16] and penalty weights Benjamini and Hochberg [4] separately.”
SIMULTANEOUS INFERENCE : WHEN SHOULD HYPOTHESIS TESTING PROBLEMS BE COMBINED? (2008, methodology): “Suppose that all the z-values come, independently, from a one-parameter exponential family having density functions g�(z) = e�z (�)g0(z), (8.20) 24 B. EFRON as in Lehmann and Romano (2005) , with”