• Corpus ID: 235254773

Improving Efficiency of Tests for Composite Null Hypotheses

  title={Improving Efficiency of Tests for Composite Null Hypotheses},
  author={Yotam Leibovici and Yair Goldberg},
The goal of mediation analysis is to study the effect of exposure on an outcome interceded by a mediator. Two simple hypotheses are tested: the effect of the exposure on the mediator, and the effect of the mediator on the outcome. When either of these hypotheses is true, a predetermined significance level can be assured. When both nulls are true, the same test becomes conservative. Adaptively finding the correct scenario enables customizing the tests and consequently enlarges their efficiency… 

Figures and Tables from this paper


Genome-wide analyses of sparse mediation effects under composite null hypotheses
A novel test assessing the product of two normally distributed test statistics under a composite null hypothesis, where either one parameter is zero or both are zero is developed, which shows that the null composition can be adjusted by variances of test statistics without directly estimating proportions of different nulls.
On optimal two-stage testing of multiple mediators
Mediation analysis in high-dimensional settings often involves identifying potential mediators among a large number of measured variables. For this purpose, a two-step familywise error rate procedure
A comparison of methods to test mediation and other intervening variable effects.
A Monte Carlo study compared 14 methods to test the statistical significance of the intervening variable effect and found two methods based on the distribution of the product and 2 difference-in-coefficients methods have the most accurate Type I error rates and greatest statistical power.
Testing for the indirect effect under the null for genome‐wide mediation analyses
This work evaluated the performance of commonly used mediation testing methods for the indirect effect in genome‐wide mediation studies using simulation studies, and performed an epigenome-wide mediation association study in the Normative Aging Study, analyzing DNAm as a mediator of the effect of pack‐years on FEV1.
Identifiability and Exchangeability for Direct and Indirect Effects
It is shown that adjustment for the intermediate variable, which is the most common method of estimating direct effects, can be biased, and that, even in a randomized crossover trial of exposure, direct and indirect effects cannot be separated without special assumptions.
Causal inference in statistics: An overview
This review presents empiricalresearcherswith recent advances in causal inference, and stresses the paradigmatic shifts that must be un- dertaken in moving from traditionalstatistical analysis to
Conceptual issues concerning mediation, interventions and composition
Concepts concerning mediation in the causal inference literature are reviewed. Notions of direct and indirect effects from a counterfactual approach to mediation are compared with those arising from
Direct and Indirect Effects
  • J. Pearl
  • Computer Science, Mathematics
  • 2001
A new way of defining the effect transmitted through a restricted set of paths, without controlling variables on the remaining paths is presented, which permits the assessment of a more natural type of direct and indirect effects.
A three-way decomposition of a total effect into direct, indirect, and interactive effects.
It is shown that what is often taken as an indirect effect can in fact be further decomposed into a "pure" indirect effect and a mediated interactive effect, thus yielding a three-way decomposition of a total effect (direct, indirect, and interactive).
Independent filtering increases detection power for high-throughput experiments
In an application to microarray data, it was found that gene-by-gene filtering by overall variance followed by a t-test increased the number of discoveries by 50%, and it was shown that this particular statistic pair induces a lower bound on fold-change among the set of discoveries.