An improved Bonferroni procedure for multiple tests of significance

By R. Simes, BY R. J. Simes. 1986

How researchers see this paper

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

Citations in the corpus

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift (2018, methodology): “While several less conservative aggregations methods have been proposed [18, 32, 46, 53, 55], they typically require assumptions on the dependencies among the tests.”
Nest predation in forest birds: influence of predator type and predator's habitat quality (2003, unknown): “Modified Bonferroni procedures for multiple tests were applied where appropriate (Simes 1986).”
A unified treatment of multiple testing with prior knowledge using the p-filter (2017, methodology): “When we instantiate p-filterwith the coarsest partitions with a single group containing all n hypotheses, we recover exactly (g) the Simes’ test [38] without weights, and (h) a variant by Hochberg and Liberman [19] if prior weights are used.”
Hochberg's Step-Up Method: Cutting Corners Off Holm's Step-Down Method (2007, methodology): “Consider testing each partition hypothesis H∗0I using Simes’ (1986) test: reject H∗0I if p[i]I iα/|I| for some i. (3) Simes’ test is a level α test for H0I and therefore for H ∗ 0I as well when the test statistics are independent (Simes, 1986) or, more generally, when the test statistics have a…”
Permutation-based simultaneous confidence bounds for the false discovery proportion (2018, background): “In many practical situations, the distribution of Q is such that a well-known probability inequality by Simes (1986) holds (Rødland, 2006): This probability equality provides a critical vector, which can be used to obtain a conﬁdence envelope B : [0 , 1] → { 1 , ..., n } with Proposition 3:…”
Dependency and false discovery rate: Asymptotics (2007, background): “, n, introduced in [15] in a different context.”
Multiple Testing for Exploratory Research (2011, methodology): “In this section, we loosely extend the concept of shortcuts to non-consonant procedures, and discuss ways of finding tα(R) in a computationally easy way for specific choices of the local test, namely those based on Fisher combinations, on Simes’ inequality, and on sums of normally distributed test s”
False Discovery Control for Multiple Tests of Association Under General Dependence (2006, methodology): “To control the probability of erroneously rejecting true null hypotheses, traditional techniques rely mostly on control of the family-wise error rate (Sidak, 1967; Holm, 1979; Simes, 1986; Westfall & Young, 1993).”
A Linear Non-Gaussian Acyclic Model for Causal Discovery (2006, methodology): “Some authors have improved the Bonferroni procedure or devised new techniques so that they have more power of test (e.g., Benjamini and Hochberg, 1995; Hochberg, 1988; Holm, 1979; Simes, 1986).”
Asymptotic Minimaxity Of False Discovery Rate Thresholding For Sparse Exponential Data (2006, unknown): “Observe that∣∣B2(T̂q,n,G) − B̃2(Tq,G)∣∣≤ E[log2(µ1)|1{X1 T̂q,n} − 1{X1 Tq(G)}|],(6.3) ∣∣V (T̂q,n,G) − Ṽ (Tq,G)∣∣≤ E[log2(X1/µ1)|1{X1 T̂q,n} − 1{X1 Tq(G)}|].”
Controlling the false discovery rate: a practical and powerful approach to multiple testing (1995, methodology): “This procedure was mentioned by Simes (1986) as an exploratory extension to his procedure for rejection of the intersection hypothesis that all null hypotheses are true if, for some i, P(;) < ia/m.”
Principal component analysis for second-order stationary vector time series (2014, background): “As these P -values are approximately independent for large n, a multiple test at the significant level α ∈ (0,1) rejects H0, defined in (2.10), if p(j) ≤ jα/(2m + 1) for at least one 1 ≤ j ≤ 2m + 1; see Simes (1986) for details.”