Atnaujinkite slapukų nuostatas

Machine Learning for Knowledge Discovery with R: Methodologies for Modeling, Inference and Prediction [Kietas viršelis]

  • Formatas: Hardback, 244 pages, aukštis x plotis: 234x156 mm, weight: 485 g, 98 Line drawings, black and white; 98 Illustrations, black and white
  • Išleidimo metai: 15-Sep-2021
  • Leidėjas: Chapman & Hall/CRC
  • ISBN-10: 1032065362
  • ISBN-13: 9781032065366
Kitos knygos pagal šią temą:
Machine Learning for Knowledge Discovery with R: Methodologies for Modeling, Inference and PredictionDidesnis paveikslėlis
  • Formatas: Hardback, 244 pages, aukštis x plotis: 234x156 mm, weight: 485 g, 98 Line drawings, black and white; 98 Illustrations, black and white
  • Išleidimo metai: 15-Sep-2021
  • Leidėjas: Chapman & Hall/CRC
  • ISBN-10: 1032065362
  • ISBN-13: 9781032065366
Kitos knygos pagal šią temą:
Pastovi nuoroda: https://www.kriso.lt/db/9781032065366.html
Raktažodžiai:
"Machine Learning for Knowledge Discovery with R contains methodologies and examples for statistical modelling, inference, and prediction of data analysis. It includes many recent supervised and unsupervised machine learning methodologies such as recursive partitioning modelling, regularized regression, support vector machine, neural network, clustering, and causal-effect inference. Additionally, it emphasizes statistical thinking of data analysis, use of statistical graphs for data structure exploration, and result presentations. The book includes many real-world data examples from life-science, finance, etc. to illustrate the applications of the methods described therein"--

‘Machine Learning for Knowledge Discovery with R’ contains methodologies and examples for statistical modelling, inference, and prediction of data analysis. It includes most recent supervised and unsupervised machine learning methodologies



Machine Learning for Knowledge Discovery with R contains methodologies and examples for statistical modelling, inference, and prediction of data analysis. It includes many recent supervised and unsupervised machine learning methodologies such as recursive partitioning modelling, regularized regression, support vector machine, neural network, clustering, and causal-effect inference. Additionally, it emphasizes statistical thinking of data analysis, use of statistical graphs for data structure exploration, and result presentations. The book includes many real-world data examples from life-science, finance, etc. to illustrate the applications of the methods described therein.

Key Features:

  • Contains statistical theory for the most recent supervised and unsupervised machine learning methodologies.
  • Emphasizes broad statistical thinking, judgment, graphical methods, and collaboration with subject-matter-experts in analysis, interpretation, and presentations.
  • Written by statistical data analysis practitioner for practitioners.

The book is suitable for upper-level-undergraduate or graduate-level data analysis course. It also serves as a useful desk-reference for data analysts in scientific research or industrial applications.

Recenzijos

"A knowledgeable applied statistician with good math skills will likely appreciate the brevity of this presentation, as well as its clear descriptions about how to easily apply the methods in R. This book is likely best used as a quick reference for those already familiar with these methods, for when one wants to aplly a particular machine learning method."

Amit K. Chowdhry, University of Rochester, USA, Royal Statistical Society, Series A: Statistics in Society.

"I will definitely recommend this book without any reservation to individuals in data science or associated disciplines that utilize machine learning and predictive modelling strategies for quantitatively making inference of data sets."

- Reuben Adatorwovor, ISCB News, September 2022.

"This book is a must-read for those involved in data science, machine learning, and statistical analysis. It provides the necessary tools and knowledge to understand and apply various techniques in data analysis. I highly recommend this book for academics, professionals, and enthusiasts interested in advancing their understanding of machine learning and statistical analysis. This book promises to enlighten readers on the theory and equip them with the practical skills to apply these concepts in real-world situations."

- Aszani Aszani, Universitas Gadjah Mada, Indonesia, Technometrics, November 2023.

Preface xiii
1 Data Analysis 1(8)
1.1 Perspectives of Data Analysis
1(2)
1.2 Strategies and Stages of Data Analysis
3(1)
1.3 Data Quality
4(3)
1.3.1 Heterogeneity in Data Sources
5(1)
1.3.1.1 Heterogeneity in Study Subject Populations
5(1)
1.3.1.2 Heterogeneity in Data due to Timing of Generations
5(1)
1.3.2 Noise Accumulation
6(1)
1.3.3 Spurious Correlation
6(1)
1.3.4 Missing Data
6(1)
1.4 Data Sets Analyzed in This Book
7(2)
1.4.1 NCI-60
7(1)
1.4.2 Riboflavin Production with Bacillus Subtilis
7(1)
1.4.3 TCGA
7(1)
1.4.4 The Boston Housing Data Set
8(1)
2 Examining Data Distribution 9(20)
2.1 One Dimension
9(3)
2.1.1 Histogram, Stem-and-Leaf, Density Plot
9(1)
2.1.2 Box Plot
10(1)
2.1.3 Quantile-Quantile (Q-Q) Plot, Normal Plot, Probability-Probability (P-P) Plot
11(1)
2.2 Two Dimension
12(7)
2.2.1 Scatter Plot
12(1)
2.2.2 Ellipse - Visualization of Covariance and Correlation
13(4)
2.2.3 Multivariate Normality Test
17(2)
2.3 More Than Two Dimension
19(6)
2.3.1 Scatter Plot Matrix
19(1)
2.3.2 Andrews's Plot
20(3)
2.3.3 Conditional Plot
23(2)
2.4 Visualization of Categorical Data
25(4)
2.4.1 Mosaic Plot
26(1)
2.4.2 Association Plot
27(2)
3 Regressions 29(30)
3.1 Ridge Regression
29(1)
3.2 Lasso
30(4)
3.2.1 Example: Lasso on Continuous Data
31(1)
3.2.2 Example: Lasso on Binary Data
32(1)
3.2.3 Example: Lasso on Survival Data
33(1)
3.3 Group Lasso
34(3)
3.3.1 Example: Group Lasso on Gene Signatures
35(2)
3.4 Sparse Group Lasso
37(8)
3.4.1 Example: Lasso, Group Lasso, Sparse Group Lasso on Simulated Continuous Data
38(3)
3.4.2 Example: Lasso, Group Lasso, Sparse Group Lasso on Gene Signatures Continuous Data
41(4)
3.5 Adaptive Lasso
45(4)
3.5.1 Example: Adaptive Lasso on Continuous Data
46(1)
3.5.2 Example: Adaptive Lasso on Binary Data
47(2)
3.6 Elastic Net
49(4)
3.6.1 Example: Elastic Net on Continuous Data
51(1)
3.6.2 Example: Elastic Net on Binary Data
52(1)
3.7 The Sure Screening Method
53(4)
3.7.1 The Sure Screening Method
54(1)
3.7.2 Sure Independence Screening on Model Selection
55(1)
3.7.3 Example: SIS on Continuous Data
56(1)
3.7.4 Example: SIS on Survival Data
56(1)
3.8 Identify Minimal Class of Models
57(2)
3.8.1 Analysis Using Minimal Models
58(1)
4 Recursive Partitioning Modeling 59(42)
4.1 Recursive Partitioning Modeling via Trees
59(11)
4.1.1 Elements of Growing a Tree
59(1)
4.1.1.1 Grow a Tree
60(1)
4.1.2 The Impurity Function
60(1)
4.1.2.1 Definition of Impurity Function
61(1)
4.1.2.2 Measure of Node Impurity - the Gini Index
61(1)
4.1.3 Misclassification Cost
61(1)
4.1.4 Size of Trees
62(1)
4.1.5 Example of Recursive Partitioning
63(7)
4.1.5.1 Recursive Partitioning with Binary Outcomes
63(2)
4.1.5.2 Recursive Partitioning with Continuous Outcomes
65(2)
4.1.5.3 Recursive Partitioning for Survival Outcomes
67(3)
4.2 Random Forest
70(7)
4.2.1 Mechanism of Action of Random Forests
72(1)
4.2.2 Variable Importance
72(1)
4.2.3 Random Forests for Regression
73(1)
4.2.4 Example of Random Forest Data Analysis
73(4)
4.2.4.1 randomForest for Binary Data
73(3)
4.2.4.2 randomForest for Continuous Data
76(1)
4.3 Random Survival Forest
77(4)
4.3.1 Algorithm to Construct RSF
78(1)
4.3.2 Individual and Ensemble Estimate at Terminal Nodes
79(1)
4.3.3 VIMP
79(1)
4.3.4 Example
79(2)
4.4 XGBoost: A Tree Boosting System
81(7)
4.4.1 Example Using xgboost for Data Analysis
83(4)
4.4.1.1 xgboost for Binary Data
83(1)
4.4.1.2 xgboost for Continuous Data
84(3)
4.4.2 Example - xgboost for Cox Regression
87(1)
4.5 Model-based Recursive Partitioning
88(3)
4.5.1 The Recursive Partitioning Algorithm
89(1)
4.5.2 Example
89(2)
4.6 Recursive Partition for Longitudinal Data
91(4)
4.6.1 Methodology
91(1)
4.6.2 Recursive Partition for Longitudinal Data Based on Baseline Covariates
92(1)
4.6.2.1 Methodology
92(1)
4.6.3 LongCART Algorithm
93(1)
4.6.4 Example of Recursive Partitioning of Longitudinal Data
93(2)
4.7 Analysis of Ordinal Data
95(1)
4.8 Examples - Analysis of Ordinal Data
96(3)
4.8.1 Analysis of Cleveland Clinic Heart Data (Ordinal)
96(1)
4.8.2 Analysis of Cleveland Clinic Heart Data (Twoing)
97(2)
4.9 Advantages and Disadvantages of Trees
99(2)
5 Support Vector Machine 101(28)
5.1 General Theory of Classification and Regression in Hyperplane
101(3)
5.1.1 Separable Case
102(1)
5.1.2 Non-separable Case
102(2)
5.1.2.1 Method of Stochastic Approximation
103(1)
5.1.2.2 Method of Sigmoid Approximations
103(1)
5.1.2.3 Method of Radial Basis Functions
104(1)
5.2 SVM for Indicator Functions
104(8)
5.2.1 Optimal Hyperplane for Separable Data Sets
104(2)
5.2.1.1 Constructing the Optimal Hyperplane
105(1)
5.2.2 Optimal Hyperplane for Non-Separable Sets
106(2)
5.2.2.1 Generalization of the Optimal Hyperplane
106(2)
5.2.3 Support Vector Machine
108(1)
5.2.4 Constructing SVM
109(1)
5.2.4.1 Polynomial Kernel Functions
110(1)
5.2.4.2 Radial Basis Kernel Functions
110(1)
5.2.5 Example: Analysis of Binary Classification Using SVM
110(2)
5.2.6 Example: Effect of Kernel Selection
112(1)
5.3 SVM for Continuous Data
112(5)
5.3.1 Minimizing the Risk with f-insensitive Loss Functions
113(2)
5.3.2 Example: Regression Analysis Using SVM
115(2)
5.4 SVM for Survival Data Analysis
117(2)
5.4.1 Example: Analysis of Survival Data Using SVM
118(1)
5.5 Feature Elimination for SVM
119(3)
5.5.1 Example: Gene Selection via SVM with Feature Elimination
120(2)
5.6 Spare Bayesian Learning with Relevance Vector Machine (RVM)
122(5)
5.6.1 Example: Regression Analysis Using RVM
125(1)
5.6.2 Example: Curve Fitting for SVM and RVM
125(2)
5.7 SV Machines for Function Estimation
127(2)
6 Cluster Analysis 129(26)
6.1 Measure of Distance/Dissimilarity
129(2)
6.1.1 Continuous Variables
130(1)
6.1.2 Binary and Categorical Variables
130(1)
6.1.3 Mixed Data Types
130(1)
6.1.4 Other Measure of Dissimilarity
131(1)
6.2 Hierarchical Clustering
131(4)
6.2.1 Options of Linkage
132(1)
6.2.2 Example of Hierarchical Clustering
133(2)
6.3 K-means Cluster
135(4)
6.3.1 General Description of K-means Clustering
135(2)
6.3.2 Estimating the Number of Clusters
137(2)
6.4 The PAM Clustering Algorithm
139(2)
6.4.1 Example of K-means with PAM Clustering Algorithm
141(1)
6.5 Bagged Clustering
141(3)
6.5.1 Example of Bagged Clustering
142(2)
6.6 RandomForest for Clustering
144(1)
6.6.1 Example: Random Forest for Clustering
144(1)
6.7 Mixture Models/Model-based Cluster Analysis
145(2)
6.8 Stability of Clusters
147(1)
6.9 Consensus Clustering
147(4)
6.9.1 Determination of Clusters
148(1)
6.9.2 Example of Consensus Clustering on RNA Sequence Data
149(2)
6.10 The Integrative Clustering Framework
151(4)
6.10.1 Example: Integrative Clustering
152(3)
7 Neural Network 155(18)
7.1 General Theory of Neural Network
155(1)
7.2 Elemental Aspects and Structure of Artificial Neural Networks
156(1)
7.3 Multilayer Perceptrons
157(1)
7.3.1 The Simple (Single Unit) Perceptron
157(1)
7.3.2 Training Perceptron Learning
157(1)
7.4 Multilayer Perceptrons (MLP)
158(1)
7.4.1 Architectures of MLP
158(1)
7.4.2 Training MLP
159(1)
7.5 Deep Learning
159(2)
7.5.1 Model Parameterization
160(1)
7.6 Few Pros and Cons of Neural Networks
161(1)
7.7 Examples
162(11)
8 Causal Inference and Matching 173(24)
8.1 Introduction
173(1)
8.2 Three Layer Causal Hierarchy
173(1)
8.3 Seven Tools of Causal Inference
174(2)
8.4 Statistical Framework of Causal Inferences
176(1)
8.5 Propensity Score
177(1)
8.6 Methodologies of Matching
178(6)
8.6.1 Nearest Neighbor (or greedy) Matching
178(2)
8.6.1.1 Example Using Nearest Neighbor Matching
178(2)
8.6.2 Exact Matching
180(1)
8.6.2.1 Example
180(1)
8.6.3 Mahalanobis Distance Matching
181(1)
8.6.3.1 Example
181(1)
8.6.4 Genetic Matching
182(4)
8.6.4.1 Example
183(1)
8.7 Optimal Matching
184(2)
8.7.0.1 Example
185(1)
8.8 Full Matching
186(5)
8.8.0.1 Example
187(1)
8.8.1 Analysis of Data After Matching
188(3)
8.8.1.1 Example
189(2)
8.9 Cluster Matching
191(6)
8.9.1 Example
192(5)
9 Business 197(24)
9.1 Case Study One: Marketing Campaigns of a Portuguese Banking Institution
197(6)
9.1.1 Description of Data
197(1)
9.1.2 Data Analysis
198(6)
9.1.2.1 Analysis via Lasso
198(1)
9.1.2.2 Analysis via Elastic Net
198(1)
9.1.2.3 Analysis via SIS
199(1)
9.1.2.4 Analysis via rpart
200(1)
9.1.2.5 Analysis via randomForest
200(2)
9.1.2.6 Analysis via xgboost
202(1)
9.2 Summary
203(1)
9.3 Case Study Two: Polish Companies Bankruptcy Data
204(14)
9.3.1 Description of Data
204(2)
9.3.2 Data Analysis
206(19)
9.3.2.1 Analysis of Year-1 Data (univariate analysis)
207(2)
9.3.2.2 Analysis of Year-3 Data (univariate analysis)
209(1)
9.3.2.3 Analysis of Year-5 Data (univariate analysis)
210(2)
9.3.2.4 Analysis of Year-1 Data (composite analysis)
212(2)
9.3.2.5 Analysis of Year-3 Data (composite analysis)
214(2)
9.3.2.6 Analysis of Year-5 Data (composite analysis)
216(2)
9.4 Summary
218(3)
10 Analysis of Response Profiles 221(14)
10.1 Introduction
221(1)
10.2 Data Example
221(3)
10.3 Transition of Response States
224(1)
10.4 Classification of Response Profiles
225(5)
10.4.1 Dissimilarities Between Response Profiles
225(1)
10.4.2 Visualizing Clusters via Multidimensional Scaling
226(1)
10.4.3 Response Profile Differences among Clusters
227(1)
10.4.4 Significant Clinical Variables for Each Cluster
228(2)
10.5 Modeling of Response Profiles via GEE
230(3)
10.5.1 Marginal Models
230(1)
10.5.2 Estimation of Marginal Regression Parameters
231(1)
10.5.3 Local Odds Ratio
231(1)
10.5.4 Results of Modeling
231(2)
10.6 Summary
233(2)
Bibliography 235
Index 24
Kao-Tai Tsai obtained his Ph.D. in Mathematical Statistics from University of California, San Diego and had worked at AT&T Bell Laboratories to conduct statistical research, modelling, and exploratory data analysis. After that, he joined the US FDA and later pharmaceutical companies focusing on biostatistics, clinical trial research and data analysis to address the unmet needs in human health.