Muutke küpsiste eelistusi

Introduction to Statistical Learning: with Applications in R Second Edition 2021 [Pehme köide]

4.59/5 (2299 hinnangut Goodreads-ist)
, , ,
  • Formaat: Paperback / softback, 607 pages, kõrgus x laius: 235x155 mm, kaal: 943 g, 182 Illustrations, color; 9 Illustrations, black and white; XV, 607 p. 191 illus., 182 illus. in color., 1 Paperback / softback
  • Sari: Springer Texts in Statistics
  • Ilmumisaeg: 30-Jul-2022
  • Kirjastus: Springer-Verlag New York Inc.
  • ISBN-10: 1071614207
  • ISBN-13: 9781071614204
Teised raamatud teemal:
  • Pehme köide
  • Hind: 57,96 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 68,19 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Introduction to Statistical Learning: with Applications in R Second Edition 2021Suurem pilt
  • Formaat: Paperback / softback, 607 pages, kõrgus x laius: 235x155 mm, kaal: 943 g, 182 Illustrations, color; 9 Illustrations, black and white; XV, 607 p. 191 illus., 182 illus. in color., 1 Paperback / softback
  • Sari: Springer Texts in Statistics
  • Ilmumisaeg: 30-Jul-2022
  • Kirjastus: Springer-Verlag New York Inc.
  • ISBN-10: 1071614207
  • ISBN-13: 9781071614204
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781071614204.html
Märksõnad:
An Introduction to Statistical Learning provides an accessible overview of the field of statistical learning, an essential toolset for making sense of the vast and complex data sets that have emerged in fields ranging from biology to finance to marketing to astrophysics in the past twenty years. This book presents some of the most important modeling and prediction techniques, along with relevant applications. Topics include linear regression, classification, resampling methods, shrinkage approaches, tree-based methods, support vector machines, clustering, deep learning, survival analysis, multiple testing, and more. Color graphics and real-world examples are used to illustrate the methods presented. Since the goal of this textbook is to facilitate the use of these statistical learning techniques by practitioners in science, industry, and other fields, each chapter contains a tutorial on implementing the analyses and methods presented in R, an extremely popular open source statistical software platform.

Two of the authors co-wrote The Elements of Statistical Learning (Hastie, Tibshirani and Friedman, 2nd edition 2009), a popular reference book for statistics and machine learning researchers. An Introduction to Statistical Learning covers many of the same topics, but at a level accessible to a much broader audience. This book is targeted at statisticians and non-statisticians alike who wish to use cutting-edge statistical learning techniques to analyze their data. The text assumes only a previous course in linear regression and no knowledge of matrix algebra.





This Second Edition features new chapters on deep learning, survival analysis, and multiple testing, as well as expanded treatments of naïve Bayes, generalized linear models, Bayesian additive regression trees, and matrix completion. R code has been updated throughout to ensure compatibility.
Preface vii
1 Introduction
1(14)
2 Statistical Learning
15(44)
2.1 What Is Statistical Learning?
15(14)
2.1.1 Why Estimate f?
17(4)
2.1.2 How Do We Estimate f?
21(3)
2.1.3 The Trade-Off Between Prediction Accuracy and Model Interpretability
24(2)
2.1.4 Supervised Versus Unsupervised Learning
26(2)
2.1.5 Regression Versus Classification Problems
28(1)
2.2 Assessing Model Accuracy
29(13)
2.2.1 Measuring the Quality of Fit
29(4)
2.2.2 The Bias-Variance Trade-Off
33(4)
2.2.3 The Classification Setting
37(5)
2.3 Lab: Introduction to R
42(10)
2.3.1 Basic Commands
43(2)
2.3.2 Graphics
45(2)
2.3.3 Indexing Data
47(1)
2.3.4 Loading Data
48(2)
2.3.5 Additional Graphical and Numerical Summaries
50(2)
2.4 Exercises
52(7)
3 Linear Regression
59(70)
3.1 Simple Linear Regression
60(11)
3.1.1 Estimating the Coefficients
61(2)
3.1.2 Assessing the Accuracy of the Coefficient Estimates
63(5)
3.1.3 Assessing the Accuracy of the Model
68(3)
3.2 Multiple Linear Regression
71(12)
3.2.1 Estimating the Regression Coefficients
72(3)
3.2.2 Some Important Questions
75(8)
3.3 Other Considerations in the Regression Model
83(20)
3.3.1 Qualitative Predictors
83(4)
3.3.2 Extensions of the Linear Model
87(5)
3.3.3 Potential Problems
92(11)
3.4 The Marketing Plan
103(2)
3.5 Comparison of Linear Regression with K-Nearest Neighbors
105(5)
3.6 Lab: Linear Regression
110(11)
3.6.1 Libraries
110(1)
3.6.2 Simple Linear Regression
111(3)
3.6.3 Multiple Linear Regression
114(2)
3.6.4 Interaction Terms
116(1)
3.6.5 Non-linear Transformations of the Predictors
116(3)
3.6.6 Qualitative Predictors
119(1)
3.6.7 Writing Functions
120(1)
3.7 Exercises
121(8)
4 Classification
129(68)
4.1 An Overview of Classification
130(1)
4.2 Why Not Linear Regression?
131(2)
4.3 Logistic Regression
133(8)
4.3.1 The Logistic Model
133(2)
4.3.2 Estimating the Regression Coefficients
135(1)
4.3.3 Making Predictions
136(1)
4.3.4 Multiple Logistic Regression
137(3)
4.3.5 Multinomial Logistic Regression
140(1)
4.4 Generative Models for Classification
141(17)
4.4.1 Linear Discriminant Analysis for p = 1
142(3)
4.4.2 Linear Discriminant Analysis for p > 1
145(7)
4.4.3 Quadratic Discriminant Analysis
152(1)
4.4.4 Naive Bayes
153(5)
4.5 A Comparison of Classification Methods
158(6)
4.5.1 An Analytical Comparison
158(3)
4.5.2 An Empirical Comparison
161(3)
4.6 Generalized Linear Models
164(7)
4.6.1 Linear Regression on the Bikeshare Data
164(3)
4.6.2 Poisson Regression on the Bikeshare Data
167(3)
4.6.3 Generalized Linear Models in Greater Generality
170(1)
4.7 Lab: Classification Methods
171(18)
4.7.1 The Stock Market Data
171(1)
4.7.2 Logistic Regression
172(5)
4.7.3 Linear Discriminant Analysis
177(2)
4.7.4 Quadratic Discriminant Analysis
179(1)
4.7.5 Naive Bayes
180(1)
4.7.6 K-Nearest Neighbors
181(4)
4.7.7 Poisson Regression
185(4)
4.8 Exercises
189(8)
5 Resampling Methods
197(28)
5.1 Cross-Validation
198(11)
5.1.1 The Validation Set Approach
198(2)
5.1.2 Leave-One-Out Cross-Validation
200(3)
5.1.3 K-Fold Cross-Validation
203(2)
5.1.4 Bias-Variance Trade-Off for k-Fold Cross-Validation
205(1)
5.1.5 Cross-Validation on Classification Problems
206(3)
5.2 The Bootstrap
209(3)
5.3 Lab: Cross-Validation and the Bootstrap
212(7)
5.3.1 The Validation Set Approach
213(1)
5.3.2 Leave-One-Out Cross-Validation
214(1)
5.3.3 FC-Fold Cross-Validation
215(1)
5.3.4 The Bootstrap
216(3)
5.4 Exercises
219(6)
6 Linear Model Selection and Regularization
225(64)
6.1 Subset Selection
227(10)
6.1.1 Best Subset Selection
227(2)
6.1.2 Stepwise Selection
229(3)
6.1.3 Choosing the Optimal Model
232(5)
6.2 Shrinkage Methods
237(14)
6.2.1 Ridge Regression
237(4)
6.2.2 The Lasso
241(9)
6.2.3 Selecting the Tuning Parameter
250(1)
6.3 Dimension Reduction Methods
251(10)
6.3.1 Principal Components Regression
252(7)
6.3.2 Partial Least Squares
259(2)
6.4 Considerations in High Dimensions
261(6)
6.4.1 High-Dimensional Data
261(1)
6.4.2 What Goes Wrong in High Dimensions?
262(2)
6.4.3 Regression in High Dimensions
264(2)
6.4.4 Interpreting Results in High Dimensions
266(1)
6.5 Lab: Linear Models and Regularization Methods
267(15)
6.5.1 Subset Selection Methods
267(7)
6.5.2 Ridge Regression and the Lasso
274(5)
6.5.3 PCR and PLS Regression
279(3)
6.6 Exercises
282(7)
7 Moving Beyond Linearity
289(38)
7.1 Polynomial Regression
290(2)
7.2 Step Functions
292(2)
7.3 Basis Functions
294(1)
7.4 Regression Splines
295(6)
7.4.1 Piecewise Polynomials
295(1)
7.4.2 Constraints and Splines
295(2)
7.4.3 The Spline Basis Representation
297(1)
7.4.4 Choosing the Number and Locations of the Knots
298(2)
7.4.5 Comparison to Polynomial Regression
300(1)
7.5 Smoothing Splines
301(3)
7.5.1 An Overview of Smoothing Splines
301(1)
7.5.2 Choosing the Smoothing Parameter A
302(2)
7.6 Local Regression
304(2)
7.7 Generalized Additive Models
306(5)
7.7.1 GAMs for Regression Problems
307(3)
7.7.2 GAMs for Classification Problems
310(1)
7.8 Lab: Non-linear Modeling
311(10)
7.8.1 Polynomial Regression and Step Functions
312(5)
7.8.2 Splines
317(1)
7.8.3 GAMs
318(3)
7.9 Exercises
321(6)
8 Tree-Based Methods
327(40)
8.1 The Basics of Decision Trees
327(13)
8.1.1 Regression Trees
328(7)
8.1.2 Classification Trees
335(3)
8.1.3 Trees Versus Linear Models
338(1)
8.1.4 Advantages and Disadvantages of Trees
339(1)
8.2 Bagging, Random Forests, Boosting, and Bayesian Additive Regression Trees
340(13)
8.2.1 Bagging
340(3)
8.2.2 Random Forests
343(2)
8.2.3 Boosting
345(3)
8.2.4 Bayesian Additive Regression Trees
348(3)
8.2.5 Summary of Tree Ensemble Methods
351(2)
8.3 Lab: Decision Trees
353(8)
8.3.1 Fitting Classification Trees
353(3)
8.3.2 Fitting Regression Trees
356(1)
8.3.3 Bagging and Random Forests
357(2)
8.3.4 Boosting
359(1)
8.3.5 Bayesian Additive Regression Trees
360(1)
8.4 Exercises
361(6)
9 Support Vector Machines
367(36)
9.1 Maximal Margin Classifier
368(5)
9.1.1 What Is a Hyperplane?
368(1)
9.1.2 Classification Using a Separating Hyperplane
369(2)
9.1.3 The Maximal Margin Classifier
371(1)
9.1.4 Construction of the Maximal Margin Classifier
372(1)
9.1.5 The Non-separable Case
373(1)
9.2 Support Vector Classifiers
373(6)
9.2.1 Overview of the Support Vector Classifier
373(2)
9.2.2 Details of the Support Vector Classifier
375(4)
9.3 Support Vector Machines
379(6)
9.3.1 Classification with Non-Linear Decision Boundaries
379(1)
9.3.2 The Support Vector Machine
380(3)
9.3.3 An Application to the Heart Disease Data
383(2)
9.4 SVMs with More than Two Classes
385(1)
9.4.1 One-Versus-One Classification
385(1)
9.4.2 One-Versus-All Classification
385(1)
9.5 Relationship to Logistic Regression
386(2)
9.6 Lab: Support Vector Machines
388(10)
9.6.1 Support Vector Classifier
389(3)
9.6.2 Support Vector Machine
392(2)
9.6.3 ROC Curves
394(2)
9.6.4 SVM with Multiple Classes
396(1)
9.6.5 Application to Gene Expression Data
396(2)
9.7 Exercises
398(5)
10 Deep Learning
403(58)
10.1 Single Layer Neural Networks
404(3)
10.2 Multilayer Neural Networks
407(4)
10.3 Convolutional Neural Networks
411(8)
10.3.1 Convolution Layers
412(3)
10.3.2 Pooling Layers
415(1)
10.3.3 Architecture of a Convolutional Neural Network
415(2)
10.3.4 Data Augmentation
417(1)
10.3.5 Results Using a Pretrained Classifier
417(2)
10.4 Document Classification
419(2)
10.5 Recurrent Neural Networks
421(11)
10.5.1 Sequential Models for Document Classification
424(3)
10.5.2 Time Series Forecasting
427(4)
10.5.3 Summary of RNNs
431(1)
10.6 When to Use Deep Learning
432(2)
10.7 Fitting a Neural Network
434(5)
10.7.1 Backpropagation
435(1)
10.7.2 Regularization and Stochastic Gradient Descent
436(2)
10.7.3 Dropout Learning
438(1)
10.7.4 Network Tuning
438(1)
10.8 Interpolation and Double Descent
439(4)
10.9 Lab: Deep Learning
443(15)
10.9.1 A Single Layer Network on the Hitters Data
443(2)
10.9.2 A Multilayer Network on the MNIST Digit Data
445(3)
10.9.3 Convolutional Neural Networks
448(3)
10.9.4 Using Pretrained CNN Models
451(1)
10.9.5 IMDb Document Classification
452(2)
10.9.6 Recurrent Neural Networks
454(4)
10.10 Exercises
458(3)
11 Survival Analysis and Censored Data
461(36)
11.1 Survival and Censoring Times
462(1)
11.2 A Closer Look at Censoring
463(1)
11.3 The Kaplan-Meier Survival Curve
464(2)
11.4 The Log-Rank Test
466(3)
11.5 Regression Models With a Survival Response
469(9)
11.5.1 The Hazard Function
469(2)
11.5.2 Proportional Hazards
471(4)
11.5.3 Example: Brain Cancer Data
475(1)
11.5.4 Example: Publication Data
475(3)
11.6 Shrinkage for the Cox Model
478(2)
11.7 Additional Topics
480(3)
11.7.1 Area Under the Curve for Survival Analysis
480(1)
11.7.2 Choice of Time Scale
481(1)
11.7.3 Time-Dependent Covariates
481(1)
11.7.4 Checking the Proportional Hazards Assumption
482(1)
11.7.5 Survival Trees
482(1)
11.8 Lab: Survival Analysis
483(7)
11.8.1 Brain Cancer Data
483(3)
11.8.2 Publication Data
486(1)
11.8.3 Call Center Data
487(3)
11.9 Exercises
490(7)
12 Unsupervised Learning
497(56)
12.1 The Challenge of Unsupervised Learning
497(1)
12.2 Principal Components Analysis
498(12)
12.2.1 What Are Principal Components?
499(4)
12.2.2 Another Interpretation of Principal Components
503(2)
12.2.3 The Proportion of Variance Explained
505(2)
12.2.4 More on PCA
507(3)
12.2.5 Other Uses for Principal Components
510(1)
12.3 Missing Values and Matrix Completion
510(6)
12.4 Clustering Methods
516(16)
12.4.1 If-Means Clustering
517(4)
12.4.2 Hierarchical Clustering
521(9)
12.4.3 Practical Issues in Clustering
530(2)
12.5 Lab: Unsupervised Learning
532(16)
12.5.1 Principal Components Analysis
532(3)
12.5.2 Matrix Completion
535(3)
12.5.3 Clustering
538(4)
12.5.4 NCI60 Data Example
542(6)
12.6 Exercises
548(5)
13 Multiple Testing
553(44)
13.1 A Quick Review of Hypothesis Testing
554(6)
13.1.1 Testing a Hypothesis
555(4)
13.1.2 Type I and Type II Errors
559(1)
13.2 The Challenge of Multiple Testing
560(1)
13.3 The Family-Wise Error Rate
561(10)
13.3.1 What is the Family-Wise Error Rate?
562(2)
13.3.2 Approaches to Control the Family-Wise Error Rate
564(6)
13.3.3 Trade-Off Between the FWER and Power
570(1)
13.4 The False Discovery Rate
571(4)
13.4.1 Intuition for the False Discovery Rate
571(2)
13.4.2 The Benjamini-Hochberg Procedure
573(2)
13.5 A Re-Sampling Approach to p-Values and False Discovery Rates
575(7)
13.5.1 A Re-Sampling Approach to the p-Value
576(2)
13.5.2 A Re-Sampling Approach to the False Discovery Rate
578(3)
13.5.3 When Are Re-Sampling Approaches Useful?
581(1)
13.6 Lab: Multiple Testing
582(9)
13.6.1 Review of Hypothesis Tests
582(1)
13.6.2 The Family-Wise Error Rate
583(3)
13.6.3 The False Discovery Rate
586(2)
13.6.4 A Re-Sampling Approach
588(3)
13.7 Exercises
591(6)
Index 597
Gareth James is a professor of data sciences and operations, and the E. Morgan Stanley Chair in Business Administration, at the University of Southern California. He has published an extensive body of methodological work in the domain of statistical learning with particular emphasis on high-dimensional and functional data. The conceptual framework for this book grew out of his MBA elective courses in this area.

Daniela Witten is a professor of statistics and biostatistics, and the Dorothy Gilford Endowed Chair, at the University of Washington. Her research focuses largely on statistical machine learning techniques for the analysis of complex, messy, and large-scale data, with an emphasis on unsupervised learning.

Trevor Hastie and Robert Tibshirani are professors of statistics at Stanford University, and are co-authors of the successful textbook Elements of Statistical Learning. Hastie and Tibshirani developed generalized additive models and wrote a popular book of that title. Hastie co-developed much of the statistical modeling software and environment in R/S-PLUS and invented principal curves and surfaces. Tibshirani proposed the lasso and is co-author of the very successful An Introduction to the Bootstrap.