Analysis of Variance for High-Dimensional Data : Applications in Life, Food, and Chemical Sciences

• Autore: Smilde Age K
• Pubblicazione: Newark : , : John Wiley & Sons, Incorporated, , 2025; ©2025
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (339 pages)
• Disciplina: 570.285
• Soggetto topico: Life sciences - Data processing; Food science - Data processing; Chemistry - Data processing; Experimental design
• Altri autori: MariniFederico WesterhuisJohan A LilandKristian Hovde
• Nota di contenuto: Cover -- Title Page -- Copyright -- Contents -- About the Authors -- Foreword -- Preface -- Chapter 1 Introduction -- 1.1 Types of Data -- 1.2 Statistical Design of Experiments -- 1.3 High‐Dimensional Data -- 1.4 Examples -- 1.4.1 Metabolomics -- 1.4.2 Genomics -- 1.4.3 Microbiome -- 1.4.4 Proteomics -- 1.4.5 Food Science -- 1.4.6 Sensory Science -- 1.4.7 Chemistry -- 1.5 Complexities -- 1.5.1 Normalization -- 1.5.2 Different Measurement Scales -- 1.5.3 Different Distributions -- 1.5.4 Heteroscedastic Error -- 1.5.5 Comparability -- 1.5.6 Sparseness, Non‐detects, and Missing Values -- 1.5.7 Unbalancedness -- 1.6 Direct Versus Indirect Methods -- 1.7 Some History -- 1.A.1 Types of Measurements -- 1.A.2 Notation and Terminology -- 1.A.3 Some Definitions -- 1.A.4 Abbreviations -- Chapter 2 Basic Theory and Concepts -- 2.1 Mathematical Background -- 2.1.1 Vector Spaces and Subspaces -- 2.1.2 Matrix Decompositions -- 2.1.3 Inverses and Generalized Inverses -- 2.1.4 Distances and Projections -- 2.1.4.1 Formal Description of Distances -- 2.1.4.2 Projections -- 2.1.5 Principal Component Analysis -- 2.2 Statistical Background -- 2.2.1 Estimation Methods -- 2.2.1.1 Least Squares -- 2.2.1.2 Maximum Likelihood -- 2.2.2 Regression Methods -- 2.2.2.1 Multiple Linear Regression: Full Rank Case -- 2.2.2.2 Multiple Linear Regression Using Dummy Variables -- 2.2.2.3 Multiple Linear Regression: Rank Deficient Case -- 2.2.2.4 Penalized Regression -- 2.2.2.5 Principal Component Regression -- 2.2.2.6 Partial Least Squares -- 2.2.2.7 Redundancy Analysis -- 2.2.3 Significance Tests -- 2.2.3.1 Classical Tests -- 2.2.3.2 Permutation Tests -- 2.2.3.3 Likelihood Ratio Tests -- 2.3 Association Measures -- 2.3.1 Pearson and Spearman Correlation Coefficients -- 2.3.2 Problems with Correlations -- Chapter 3 Linear Models -- 3.1 Introduction -- 3.2 Simple ANOVA Models. ; 3.2.1 One‐Way ANOVA -- 3.2.2 Two‐Way ANOVA -- 3.2.2.1 Crossed Designs -- 3.2.2.2 Nested Designs -- 3.2.3 Unbalanced Designs -- 3.2.3.1 One‐Way ANOVA -- 3.2.3.2 Two‐Way ANOVA for Crossed Designs -- 3.2.3.3 Nested ANOVA -- 3.3 Regression Formulation, Estimability, and Contrasts -- 3.4 Coding Schemes -- 3.4.1 Codings for Balanced Designs -- 3.4.1.1 One‐Way Layout -- 3.4.1.2 Two‐Way Crossed Designs -- 3.4.1.3 Two‐Way Nested Designs -- 3.4.2 Codings for Unbalanced Designs -- 3.5 Advanced Models -- 3.5.1 Variance Component Models -- 3.5.2 Linear Mixed Models -- 3.5.2.1 General Idea -- 3.5.2.2 Estimation of Model Parameters -- 3.5.2.3 Repeated Measures ANOVA -- 3.5.2.4 Cross‐over Designs and Models -- 3.5.2.5 Longitudinal LMMs -- 3.6 Hasse Diagrams -- 3.6.1 Building a Hasse Diagram -- 3.7 Validation -- 3.7.1 Classical Tests Revisited -- 3.7.2 Expected Mean Squares from Hasse Diagrams -- 3.7.3 Permutation Tests -- 3.7.3.1 Exact Tests -- 3.7.3.2 Approximate Tests -- 3.8 Miscellaneous Models -- 3.8.1 Multivariate Analysis of Variance -- 3.8.1.1 Traditional Multivariate Analysis of Variance -- 3.8.1.2 Significance Testing in MANOVA -- 3.8.1.3 Regression Formulation of MANOVA -- 3.8.2 Multivariate LMMs -- 3.A.1 Proof -- 3.A.2 Relationships Between Codings -- 3.A.3 Practical Aspects of Codings -- Chapter 4 ASCA and Related Methods -- 4.1 ASCA -- 4.1.1 Basic Idea of ASCA -- 4.1.2 Properties of ASCA -- 4.1.3 Permutation Tests for ASCA -- 4.1.4 Back‐Projection -- 4.1.5 Scaling in ASCA -- 4.1.6 Group‐wise ASCA -- 4.1.7 Variable‐Selection ASCA -- 4.1.8 REP‐ASCA -- 4.1.9 ASCA as a Multivariate Multiple Regression Model -- 4.1.10 Geometry of ASCA -- 4.1.10.1 Geometry of ASCA in Row‐Space -- 4.1.10.2 Geometry of ASCA in Column‐Space -- 4.2 APCA -- 4.2.1 Basic Idea of APCA -- 4.2.2 Comparing APCA with ASCA -- 4.3 ASCA+ -- 4.3.1 Confidence Ellipsoids for ASCA. ; 4.3.2 ASCA and ASCA+ as RDA Models -- 4.4 Principal Response Curves -- 4.5 SMART -- 4.6 ASCA, PRC, and SMART Compared -- 4.7 MSCA -- 4.A.1 Proof of Equation -- 4.A.2 Proof of Equation -- Chapter 5 Alternative Methods -- 5.1 General Introduction -- 5.2 PLSR‐Based Methods -- 5.2.1 ANOVA‐TP -- 5.2.2 ANOVA Multiblock Orthogonal Partial Least Squares (AMOPLS) -- 5.3 LMM‐Based Methods -- 5.3.1 RM‐ASCA+ with Qualitative Time Models -- 5.3.2 Validation of the RM‐ASCA+ Model -- 5.3.2.1 Validation of RM‐ASCA+ Models with Nonparametric Bootstrap -- 5.3.2.2 Validation of RM‐ASCA+ Models with Permutation Testing -- 5.3.2.3 Visualization -- 5.3.2.4 RM‐ASCA+ with Quantitative Time Models -- 5.3.3 LiMM‐PCA -- 5.3.3.1 Validation -- 5.3.3.2 Visualization of Effects in LiMM‐PCA -- 5.4 Miscellaneous Methods -- 5.4.1 PC‐ANOVA -- 5.4.1.1 Basic Idea of PC‐ANOVA -- 5.4.1.2 Comparing PC‐ANOVA with ASCA -- 5.4.2 PARAFASCA -- 5.4.3 PE‐ASCA -- 5.4.4 rMANOVA -- 5.4.5 Fifty-Fifty MANOVA -- 5.4.6 AComDim -- 5.4.7 General Effect Modeling (GEM) -- Chapter 6 Distance‐based Methods -- 6.1 Introduction -- 6.1.1 Double Zeros -- 6.1.2 Horseshoe Effect -- 6.1.3 Compositionality -- 6.2 Methods -- 6.2.1 Principal Coordinate Analysis -- 6.2.2 PERMANOVA -- 6.2.2.1 PERMANOVA Calculated from the Gower Matrix -- 6.2.2.2 PERMANOVA of Non‐Euclidean Dissimilarity Matrices -- 6.2.3 Effect Sizes in PERMANOVA -- 6.2.4 Permutations in PERMANOVA -- 6.2.5 Assumptions for PERMANOVA -- 6.3 ANOSIM -- Chapter 7 Reviews and Reflections -- 7.1 Reviews -- 7.1.1 Metabolomics -- 7.1.1.1 Plant Science -- 7.1.1.2 Microbiology and Biotechnology -- 7.1.1.3 Animal Science -- 7.1.1.4 Human Science -- 7.1.2 Microbiome -- 7.1.3 Genomics -- 7.1.4 Proteomics -- 7.1.5 Food Science -- 7.1.6 Sensory Science -- 7.1.7 Chemistry -- 7.2 Reflections -- 7.2.1 Summary of Reviews -- 7.2.2 Overview of Methods. ; 7.2.3 Remaining Challenges -- 7.2.3.1 ASCA+ and Partial RDA -- 7.2.3.2 Permutations: Correlations and Unbalancedness -- 7.2.3.3 PERMANOVA and Effect Sizes -- 7.2.3.4 Back‐Projection Approach -- 7.2.3.5 Inferential Statistics -- 7.2.3.6 Advanced HD‐ANOVA Methods -- Chapter 8 Software -- 8.1 HD‐ANOVA Software -- 8.2 R Package HDANOVA -- 8.3 Installing and Starting the Package -- 8.4 Data Handling -- 8.4.1 Read from File -- 8.4.2 Data Pre‐processing -- 8.4.2.1 Re‐coding Categorical data -- 8.4.3 Data Structures for Analysis Including Blocks -- 8.4.3.1 Create List of Blocks -- 8.4.3.2 Create data.frame of Blocks -- 8.5 Analysis of Variance (ANOVA) -- 8.5.1 Simulated Data -- 8.5.2 Fixed Effect Models -- 8.5.2.1 One‐Way ANOVA -- 8.5.2.2 Two‐Way Crossed Effects ANOVA -- 8.5.2.3 Types of Sums of Squares -- 8.5.2.4 Coding Schemes -- 8.5.2.5 Fixed Effect Nested ANOVA -- 8.5.3 Linear Mixed Models -- 8.5.3.1 Least Squares − mixlm -- 8.5.3.2 Restrictions -- 8.5.3.3 Repeated Measures -- 8.5.3.4 REML -- 8.5.4 Multivariate ANOVA (MANOVA) -- 8.6 Basic ASCA Family -- 8.6.1 Fit ASCA Model -- 8.6.1.1 Permutation Testing -- 8.6.1.2 Random Effects -- 8.6.1.3 Scores and Loadings -- 8.6.1.4 Data Ellipsoids and Confidence Ellipsoids -- 8.6.1.5 Combined Effects -- 8.6.1.6 Quantitative Effects -- 8.6.2 ANOVA‐PCA (APCA) -- 8.6.3 PC‐ANOVA -- 8.6.4 MSCA -- 8.6.5 LiMM‐PCA -- 8.6.6 Repeated Measures ASCA -- 8.7 Alternative Methods -- 8.7.1 Principal Response Curves (PRC) -- 8.7.2 Permutation‐Based MANOVA (PERMANOVA) -- 8.8 Software Packages -- 8.8.1 R Packages -- 8.8.2 MATLAB Toolboxes -- 8.8.3 Python -- References -- Index -- EULA.
• Sommario/riassunto: "This book presents an overview of available methods to analyze high-dimensional data that are obtained through applying an experimental design. This type of of data is often collected in the natural and life sciences, and many methods for data analysis have been developed in recent years. Following an introduction and overview of the basic theory from a mathematical and statistical perspective, the book introduces the available methods and their mutual relationships, including coverage of ASCA, APCA and PC-ANOVA, ASCA , LiMM-PCA and RM-ASCA , PERMANOVA. Various alternative methods and extensions are covered, followed by a thorough review of application in areas including metabolomics, microbiomoe, gene expression, proteomics, food science, sensory science and chemistry. The book concludes with discussions on commercially available and and open-source software for application of these methods."-- Provided by publisher.
• Titolo autorizzato: Analysis of Variance for High-Dimensional Data
• ISBN: 1-394-21124-4; 1-394-21122-8
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911020059203321
• Lo trovi qui: Univ. Federico II