Optimized multiple testing procedures for nested sub-populations based on a continuous biomarker

2020 ◽  
Vol 29 (10) ◽  
pp. 2945-2957 ◽  
Author(s):  
Alexandra Christine Graf ◽  
Dominic Magirr ◽  
Alex Dmitrienko ◽  
Martin Posch
Keyword(s):  
Treatment Effect ◽  
Multiple Testing ◽  
A Priori ◽  
Testing Procedures ◽  
Type 1 Error ◽  
Multiple Testing Procedures ◽  
Small Subgroup ◽  
Positive Treatment Effect ◽  
Positive Treatment ◽  
Large Benefit

An important step in the development of targeted therapies is the identification and confirmation of sub-populations where the treatment has a positive treatment effect compared to a control. These sub-populations are often based on continuous biomarkers, measured at baseline. For example, patients can be classified into biomarker low and biomarker high subgroups, which are defined via a threshold on the continuous biomarker. However, if insufficient information on the biomarker is available, the a priori choice of the threshold can be challenging and it has been proposed to consider several thresholds and to apply appropriate multiple testing procedures to test for a treatment effect in the corresponding subgroups controlling the family-wise type 1 error rate. In this manuscript we propose a framework to select optimal thresholds and corresponding optimized multiple testing procedures that maximize the expected power to identify at least one subgroup with a positive treatment effect. Optimization is performed over a prior on a family of models, modelling the relation of the biomarker with the expected outcome under treatment and under control. We find that for the considered scenarios 3 to 4 thresholds give the optimal power. If there is a prior belief on a small subgroup where the treatment has a positive effect, additional optimization of the spacing of thresholds may result in a large benefit. The procedure is illustrated with a clinical trial example in depression.

Joint testing of overall and simple effects for the two-by-two factorial trial design

2021 ◽  
Vol 18 (5) ◽  
pp. 521-528
Author(s):  
Eric S Leifer ◽  
James F Troendle ◽  
Alexis Kolecki ◽  
Dean A Follmann
Keyword(s):  
Blood Pressure ◽  
Blood Pressure Control ◽  
Multiple Testing ◽  
Pressure Control ◽  
Factorial Analysis ◽  
Testing Procedures ◽  
Type 1 Error ◽  
Multiple Testing Procedures ◽  
To Receive

Background/aims: The two-by-two factorial design randomizes participants to receive treatment A alone, treatment B alone, both treatments A and B( AB), or neither treatment ( C). When the combined effect of A and B is less than the sum of the A and B effects, called a subadditive interaction, there can be low power to detect the A effect using an overall test, that is, factorial analysis, which compares the A and AB groups to the C and B groups. Such an interaction may have occurred in the Action to Control Cardiovascular Risk in Diabetes blood pressure trial (ACCORD BP) which simultaneously randomized participants to receive intensive or standard blood pressure, control and intensive or standard glycemic control. For the primary outcome of major cardiovascular event, the overall test for efficacy of intensive blood pressure control was nonsignificant. In such an instance, simple effect tests of A versus C and B versus C may be useful since they are not affected by a subadditive interaction, but they can have lower power since they use half the participants of the overall trial. We investigate multiple testing procedures which exploit the overall tests’ sample size advantage and the simple tests’ robustness to a potential interaction. Methods: In the time-to-event setting, we use the stratified and ordinary logrank statistics’ asymptotic means to calculate the power of the overall and simple tests under various scenarios. We consider the A and B research questions to be unrelated and allocate 0.05 significance level to each. For each question, we investigate three multiple testing procedures which allocate the type 1 error in different proportions for the overall and simple effects as well as the AB effect. The Equal Allocation 3 procedure allocates equal type 1 error to each of the three effects, the Proportional Allocation 2 procedure allocates 2/3 of the type 1 error to the overall A (respectively, B) effect and the remaining type 1 error to the AB effect, and the Equal Allocation 2 procedure allocates equal amounts to the simple A (respectively, B) and AB effects. These procedures are applied to ACCORD BP. Results: Across various scenarios, Equal Allocation 3 had robust power for detecting a true effect. For ACCORD BP, all three procedures would have detected a benefit of intensive glycemia control. Conclusions: When there is no interaction, Equal Allocation 3 has less power than a factorial analysis. However, Equal Allocation 3 often has greater power when there is an interaction. The R package factorial2x2 can be used to explore the power gain or loss for different scenarios.

scholarly journals The Romano–Wolf multiple-hypothesis correction in Stata

2020 ◽  
Vol 20 (4) ◽  
pp. 812-843
Author(s):  
Damian Clarke ◽  
Joseph P. Romano ◽  
Michael Wolf
Keyword(s):  
Error Rate ◽  
Multiple Testing ◽  
Original Data ◽  
Dependence Structure ◽  
Familywise Error Rate ◽  
Testing Procedures ◽  
Multiple Testing Procedures ◽  
Multiple Hypothesis ◽  
Wide Range ◽  
Performance Gains

When considering multiple-hypothesis tests simultaneously, standard statistical techniques will lead to overrejection of null hypotheses unless the multiplicity of the testing framework is explicitly considered. In this article, we discuss the Romano–Wolf multiple-hypothesis correction and document its implementation in Stata. The Romano–Wolf correction (asymptotically) controls the familywise error rate, that is, the probability of rejecting at least one true null hypothesis among a family of hypotheses under test. This correction is considerably more powerful than earlier multiple-testing procedures, such as the Bonferroni and Holm corrections, given that it takes into account the dependence structure of the test statistics by resampling from the original data. We describe a command, rwolf, that implements this correction and provide several examples based on a wide range of models. We document and discuss the performance gains from using rwolf over other multiple-testing procedures that control the familywise error rate.

scholarly journals Efficacy of Zoledronic Acid in Patients with Systemic Osteoporosis and Problem of «Non Respondents» to the Treatment

2015 ◽  
Vol 22 (4) ◽  
pp. 39-43
Author(s):  
S. S Rodionova ◽  
Yu. V Buklemishev
Keyword(s):  
Bone Formation ◽  
Treatment Effect ◽  
Biochemical Tests ◽  
Zolendronic Acid ◽  
Bone Formation Markers ◽  
Study Results ◽  
Positive Treatment Effect ◽  
Positive Treatment ◽  
The Relationship ◽  
Mineral Bone Density

Prospective study of zolendronic acid efficacy was performed in 112 patients with systemic osteoporosis. Study results confirmed the presence of patients who did not response to the treatment: in 15.7 % of observations reduction of mineral bone density (BMD) continued to progress. No significant differences in initial deviations of resorption and bone formation markers, peculiarities of calcium homeostasis were detected in “non respondents”. At the same time by the 12th month after treatment initiation the relationship between BMD increase with preservation of marked decrease of resorption marker (deoxypyridinoline) and bone formation marker (osteocalcin) was noted, that pointed out the expediency of prognostic model creation. Evaluation of the influence of certain risk factors (age, results of blood and urine biochemical tests, data of densitometry including the results of femoral neck BMD in some patients) using discriminant analysis showed that 81.5% of patients were correctly referred to the groups of patients who responded and not responded to treatment. Out of all initially studied parameters the most significant were 7 that in 78.6% of cases (method sensitivity) enabled to identify the patients with negative treatment effect and in 82.1% of cases (method specificity) - with positive treatment effect.

scholarly journals Chicdiff: a computational pipeline for detecting differential chromosomal interactions in Capture Hi-C data

2019 ◽  
Vol 35 (22) ◽  
pp. 4764-4766 ◽  
Author(s):  
Jonathan Cairns ◽  
William R Orchard ◽  
Valeriya Malysheva ◽  
Mikhail Spivakov
Keyword(s):  
Multiple Testing ◽  
Positive Association ◽  
R Package ◽  
Supplementary Information ◽  
Gene Promoters ◽  
Robust Detection ◽  
Testing Procedures ◽  
Multiple Testing Procedures ◽  
Powerful Approach ◽  
Cell Type Specific

Abstract Summary Capture Hi-C is a powerful approach for detecting chromosomal interactions involving, at least on one end, DNA regions of interest, such as gene promoters. We present Chicdiff, an R package for robust detection of differential interactions in Capture Hi-C data. Chicdiff enhances a state-of-the-art differential testing approach for count data with bespoke normalization and multiple testing procedures that account for specific statistical properties of Capture Hi-C. We validate Chicdiff on published Promoter Capture Hi-C data in human Monocytes and CD4+ T cells, identifying multitudes of cell type-specific interactions, and confirming the overall positive association between promoter interactions and gene expression. Availability and implementation Chicdiff is implemented as an R package that is publicly available at https://github.com/RegulatoryGenomicsGroup/chicdiff. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document