Simultaneous Statistical Inference
With Applications in the Life Sciences
Simultaneous Statistical Inference
With Applications in the Life Sciences
This monograph will provide an in-depth mathematical treatment of modern multiple test procedures controlling the false discovery rate (FDR) and related error measures, particularly addressing applications to fields such as genetics, proteomics, neuroscience and general biology. The book will also include a detailed description how to implement these methods in practice. Moreover new developments focusing on non-standard assumptions are also included, especially multiple tests for discrete data. The book primarily addresses researchers and practitioners but will also be beneficial for graduate students.
1;Preface;6 2;Contents;8 3;Acronyms;12 4;1 The Problem of Simultaneous Inference;14 4.1;1.1 Sources of Multiplicity;16 4.2;1.2 Multiple Hypotheses Testing;17 4.2.1;1.2.1 Measuring and Controlling Errors;17 4.2.2;1.2.2 Structured Systems of Hypotheses;21 4.3;1.3 Relationships to Other Simultaneous Statistical Inference Problems;22 4.4;1.4 Contributions of this Work;24 4.5;References;25 5;Part IGeneral Theory;27 6;2 Some Theory of p-values;28 6.1;2.1 Randomized p-values;31 6.1.1;2.1.1 Randomized p-values in Discrete Models;31 6.1.2;2.1.2 Randomized p-values for Testing Composite Null Hypotheses;32 6.2;2.2 p-value Models;33 6.2.1;2.2.1 The iid.-Uniform Model;33 6.2.2;2.2.2 Dirac-Uniform Configurations;35 6.2.3;2.2.3 Two-Class Mixture Models;36 6.2.4;2.2.4 Copula Models Under Fixed Margins;37 6.2.5;2.2.5 Further Joint Models;37 6.3;References;38 7;3 Classes of Multiple Test Procedures;40 7.1;3.1 Margin-Based Multiple Test Procedures;41 7.1.1;3.1.1 Single-Step Procedures;41 7.1.2;3.1.2 Stepwise Rejective Multiple Tests;43 7.1.3;3.1.3 Data-Adaptive Procedures;46 7.2;3.2 Multivariate Multiple Test Procedures;48 7.2.1;3.2.1 Resampling-Based Methods;48 7.2.2;3.2.2 Methods Based on Central Limit Theorems;49 7.2.3;3.2.3 Copula-Based Methods;49 7.3;3.3 Closed Test Procedures;51 7.4;References;54 8;4 Simultaneous Test Procedures;57 8.1;4.1 Three Important Families of Multivariate Probability Distributions;60 8.1.1;4.1.1 Multivariate Normal Distributions;60 8.1.2;4.1.2 Multivariate t-distributions;61 8.1.3;4.1.3 Multivariate Chi-Square Distributions;61 8.2;4.2 Projection Methods Under Asymptotic Normality;62 8.3;4.3 Probability Bounds and Effective Numbers of Tests;66 8.3.1;4.3.1 Sum-Type Probability Bounds;67 8.3.2;4.3.2 Product-Type Probability Bounds;68 8.3.3;4.3.3 Effective Numbers of Tests;71 8.4;4.4 Simultaneous Test Procedures in Terms of p-value Copulae;72 8.5;4.5 Exploiting the Topological Structure of the Sample Space via Random Field Theory;75 8.6;References;78 9;5 Stepwise Rejective Multiple Tests;80 9.1;5.1 Some Concepts of Dependency;81 9.2;5.2 FWER-Controlling Step-Down Tests;83 9.3;5.3 FWER-Controlling Step-Up Tests;85 9.4;5.4 FDR-Controlling Step-Up Tests;89 9.5;5.5 FDR-Controlling Step-Up-Down Tests;91 9.6;References;98 10;6 Multiple Testing and Binary Classification;100 10.1;6.1 Binary Classification Under Sparsity;102 10.2;6.2 Binary Classification in Non-Sparse Models;105 10.3;6.3 Feature Selection for Binary Classification via Higher Criticism;108 10.4;References;110 11;7 Multiple Testing and Model Selection;111 11.1;7.1 Multiple Testing for Model Selection;112 11.2;7.2 Multiple Testing and Information Criteria;114 11.3;7.3 Multiple Testing After Model Selection;116 11.3.1;7.3.1 Distributions of Regularized Estimators;116 11.3.2;7.3.2 Two-Stage Procedures;119 11.4;7.4 Selective Inference;120 11.5;References;122 12;8 Software Solutions for Multiple Hypotheses Testing;124 12.1;8.1 The R Package multcomp;125 12.2;8.2 The R Package multtest;125 12.3;8.3 The R-based ?TOSS Software;126 12.3.1;8.3.1 The ?TOSS Simulation Tool;127 12.3.2;8.3.2 The ?TOSS Graphical User Interface;129 12.4;References;131 13;Part IIFrom Genotype to Phenotype;133 14;9 Genetic Association Studies;134 14.1;9.1 Statistical Modeling and Test Statistics;135 14.2;9.2 Estimation of the Proportion of Informative Loci;138 14.3;9.3 Effective Numbers of Tests via Linkage Disequilibrium;139 14.4;9.4 Combining Effective Numbers of Tests and Pre-estimation of ?0;142 14.5;9.5 Applicability of Margin-Based Methods;143 14.6;References;144 15;10 Gene Expression Analyses;146 15.1;10.1 Marginal Models and p-values;146 15.2;10.2 Dependency Considerations;148 15.3;10.3 Real Data Examples;151 15.3.1;10.3.1 Application of Generic Multiple Tests to Large-Scale Data;151 15.3.2;10.3.2 Copula Calibration for a Block of Correlated Genes;152 15.4;10.4 LASSO and Statistical Learning Methods;154 15.5;10.5 Gene Set Analyses and Group Structures;155 15.6;References;156 16;11 F
Dickhaus, Thorsten
ISBN | 9783642451829 |
---|---|
Artikelnummer | 9783642451829 |
Medientyp | E-Book - PDF |
Auflage | 2. Aufl. |
Copyrightjahr | 2014 |
Verlag | Springer-Verlag |
Umfang | 182 Seiten |
Sprache | Englisch |
Kopierschutz | Digitales Wasserzeichen |