|
% Usage: |
|
% * download http://www-bcf.usc.edu/~gareth/ISL/ISLR%20Seventh%20Printing.pdf |
|
% as 'in.pdf' |
|
% * create 'cover.pdf' from any image of the cover you can find on the web |
|
% (print to pdf) |
|
% * store this file as 'out.tex', and compile as 'pdflatex out.tex' |
|
% * rename output file to e.g. |
|
% 'James, Witten, Hastie, Tibshirani - An Introduction to Statistical Learning.pdf' |
|
|
|
|
|
\documentclass{article} |
|
\usepackage[utf8]{inputenc} |
|
|
|
\usepackage{geometry} |
|
%\geometry{papersize={155mm,235mm}} |
|
% You may uncomment the above line to create the book in the original size. |
|
% Otherwise, the output page size will be the defaul letter or A4, which |
|
% I prefer (extra margins for notes) |
|
|
|
\usepackage{pdfpages} |
|
\usepackage[ |
|
pdfpagelabels=true, |
|
pdftitle={An introduction to statistical learning: with applications in R}, |
|
pdfauthor={Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani}, |
|
pdfsubject={Mathematical statistics, R}, |
|
pdfkeywords={}, |
|
unicode=true, |
|
]{hyperref} |
|
\usepackage{bookmark} |
|
|
|
\begin{document} |
|
|
|
\pagenumbering{Roman} |
|
\setcounter{page}{1} |
|
\includepdf[pages={1, {}}]{cover.pdf} % with extra blank page |
|
|
|
\pagenumbering{roman} |
|
\setcounter{page}{1} |
|
\includepdf[pages=1-14]{in.pdf} |
|
|
|
\pagenumbering{arabic} |
|
\setcounter{page}{1} |
|
\includepdf[pages=15-]{in.pdf} |
|
|
|
\bookmark[page=1,level=0]{Cover} |
|
\bookmark[page=5,level=0]{Title Page} |
|
\bookmark[page=9,level=0]{Preface} |
|
\bookmark[page=11,level=0]{Contents} |
|
|
|
\bookmark[page=17,level=0]{1.: Introduction} |
|
\bookmark[page=31,level=0]{2.: Statistical Learning} |
|
\bookmark[page=31,level=1]{2.1.: What Is Statistical Learning?} |
|
\bookmark[page=33,level=2]{2.1.1.: Why Estimate $f$?} |
|
\bookmark[page=37,level=2]{2.1.2.: How Do We Estimate $f$?} |
|
\bookmark[page=40,level=2]{2.1.3.: The Trade-Off Between Prediction Accuracy and Model Interpretability} |
|
\bookmark[page=42,level=2]{2.1.4.: Supervised Versus Unsupervised Learning} |
|
\bookmark[page=44,level=2]{2.1.5.: Regression Versus Classification Problems} |
|
\bookmark[page=45,level=1]{2.2.: Assessing Model Accuracy} |
|
\bookmark[page=45,level=2]{2.2.1.: Measuring the Quality of Fit} |
|
\bookmark[page=49,level=2]{2.2.2.: The Bias-Variance Trade-Off} |
|
\bookmark[page=53,level=2]{2.2.3.: The Classification Setting} |
|
\bookmark[page=58,level=1]{2.3.: Lab: Introduction to R} |
|
\bookmark[page=58,level=2]{2.3.1.: Basic Commands} |
|
\bookmark[page=61,level=2]{2.3.2.: Graphics} |
|
\bookmark[page=63,level=2]{2.3.3.: Indexing Data} |
|
\bookmark[page=64,level=2]{2.3.4.: Loading Data} |
|
\bookmark[page=65,level=2]{2.3.5.: Additional Graphical and Numerical Summaries} |
|
\bookmark[page=68,level=1]{2.4.: Exercises} |
|
\bookmark[page=75,level=0]{3.: Linear Regression} |
|
\bookmark[page=77,level=1]{3.1.: Simple Linear Regression} |
|
\bookmark[page=77,level=2]{3.1.1.: Estimating the Coefficients} |
|
\bookmark[page=79,level=2]{3.1.2.: Assessing the Accuracy of the Coefficient Estimates} |
|
\bookmark[page=84,level=2]{3.1.3.: Assessing the Accuracy of the Model} |
|
\bookmark[page=87,level=1]{3.2.: Multiple Linear Regression} |
|
\bookmark[page=88,level=2]{3.2.1.: Estimating the Regression Coefficients} |
|
\bookmark[page=91,level=2]{3.2.2.: Some Important Questions} |
|
\bookmark[page=98,level=1]{3.3.: Other Considerations in the Regression Model} |
|
\bookmark[page=98,level=2]{3.3.1.: Qualitative Predictors} |
|
\bookmark[page=102,level=2]{3.3.2.: Extensions of the Linear Model} |
|
\bookmark[page=108,level=2]{3.3.3.: Potential Problems} |
|
\bookmark[page=118,level=1]{3.4.: The Marketing Plan} |
|
\bookmark[page=120,level=1]{3.5.: Comparison of Linear Regression with K-Nearest Neighbors} |
|
\bookmark[page=125,level=1]{3.6.: Lab: Linear Regression} |
|
\bookmark[page=125,level=2]{3.6.1.: Libraries} |
|
\bookmark[page=126,level=2]{3.6.2.: Simple Linear Regression} |
|
\bookmark[page=129,level=2]{3.6.3.: Multiple Linear Regression} |
|
\bookmark[page=131,level=2]{3.6.4.: Interaction Terms} |
|
\bookmark[page=131,level=2]{3.6.5.: Non-linear Transformations of the Predictors} |
|
\bookmark[page=133,level=2]{3.6.6.: Qualitative Predictors} |
|
\bookmark[page=135,level=2]{3.6.7.: Writing Functions} |
|
\bookmark[page=136,level=1]{3.7.: Exercises} |
|
\bookmark[page=143,level=0]{4.: Classification} |
|
\bookmark[page=144,level=1]{4.1.: An Overview of Classification} |
|
\bookmark[page=145,level=1]{4.2.: Why Not Linear Regression?} |
|
\bookmark[page=146,level=1]{4.3.: Logistic Regression} |
|
\bookmark[page=147,level=2]{4.3.1.: The Logistic Model} |
|
\bookmark[page=149,level=2]{4.3.2.: Estimating the Regression Coefficients} |
|
\bookmark[page=150,level=2]{4.3.3.: Making Predictions} |
|
\bookmark[page=151,level=2]{4.3.4.: Multiple Logistic Regression} |
|
\bookmark[page=153,level=2]{4.3.5.: Logistic Regression for $>2$ Response Classes} |
|
\bookmark[page=154,level=1]{4.4.: Linear Discriminant Analysis} |
|
\bookmark[page=154,level=2]{4.4.1.: Using Bayes' Theorem for Classification} |
|
\bookmark[page=155,level=2]{4.4.2.: Linear Discriminant Analysis for $p=1$} |
|
\bookmark[page=158,level=2]{4.4.3.: Linear Discriminant Analysis for $p>1$} |
|
\bookmark[page=165,level=2]{4.4.4.: Quadratic Discriminant Analysis} |
|
\bookmark[page=167,level=1]{4.5.: A Comparison of Classification Methods} |
|
\bookmark[page=170,level=1]{4.6.: Lab: Logistic Regression, LDA, QDA, and KNN} |
|
\bookmark[page=170,level=2]{4.6.1.: The Stock Market Data} |
|
\bookmark[page=172,level=2]{4.6.2.: Logistic Regression} |
|
\bookmark[page=177,level=2]{4.6.3.: Linear Discriminant Analysis} |
|
\bookmark[page=178,level=2]{4.6.4.: Quadratic Discriminant Analysis} |
|
\bookmark[page=179,level=2]{4.6.5.: K-Nearest Neighbors} |
|
\bookmark[page=180,level=2]{4.6.6.: An Application to Caravan Insurance Data} |
|
\bookmark[page=184,level=1]{4.7.: Exercises} |
|
\bookmark[page=191,level=0]{5.: Resampling Methods} |
|
\bookmark[page=192,level=1]{5.1.: Cross-Validation} |
|
\bookmark[page=192,level=2]{5.1.1.: The Validation Set Approach} |
|
\bookmark[page=194,level=2]{5.1.2.: Leave-One-Out Cross-Validation} |
|
\bookmark[page=197,level=2]{5.1.3.: k-Fold Cross-Validation} |
|
\bookmark[page=199,level=2]{5.1.4.: Bias-Variance Trade-Off for k-Fold Cross-Validation} |
|
\bookmark[page=200,level=2]{5.1.5.: Cross-Validation on Classification Problems} |
|
\bookmark[page=203,level=1]{5.2.: The Bootstrap} |
|
\bookmark[page=206,level=1]{5.3.: Lab: Cross-Validation and the Bootstrap} |
|
\bookmark[page=207,level=2]{5.3.1.: The Validation Set Approach} |
|
\bookmark[page=208,level=2]{5.3.2.: Leave-One-Out Cross-Validation} |
|
\bookmark[page=209,level=2]{5.3.3.: k-Fold Cross-Validation} |
|
\bookmark[page=210,level=2]{5.3.4.: The Bootstrap} |
|
\bookmark[page=213,level=1]{5.4.: Exercises} |
|
\bookmark[page=219,level=0]{6.: Linear Model Selection and Regularization} |
|
\bookmark[page=221,level=1]{6.1.: Subset Selection} |
|
\bookmark[page=221,level=2]{6.1.1.: Best Subset Selection} |
|
\bookmark[page=223,level=2]{6.1.2.: Stepwise Selection} |
|
\bookmark[page=226,level=2]{6.1.3.: Choosing the Optimal Model} |
|
\bookmark[page=230,level=1]{6.2.: Shrinkage Methods} |
|
\bookmark[page=231,level=2]{6.2.1.: Ridge Regression} |
|
\bookmark[page=235,level=2]{6.2.2.: The Lasso} |
|
\bookmark[page=243,level=2]{6.2.3.: Selecting the Tuning Parameter} |
|
\bookmark[page=244,level=1]{6.3.: Dimension Reduction Methods} |
|
\bookmark[page=246,level=2]{6.3.1.: Principal Components Regression} |
|
\bookmark[page=253,level=2]{6.3.2.: Partial Least Squares} |
|
\bookmark[page=254,level=1]{6.4.: Considerations in High Dimensions} |
|
\bookmark[page=254,level=2]{6.4.1.: High-Dimensional Data} |
|
\bookmark[page=255,level=2]{6.4.2.: What Goes Wrong in High Dimensions?} |
|
\bookmark[page=257,level=2]{6.4.3.: Regression in High Dimensions} |
|
\bookmark[page=259,level=2]{6.4.4.: Interpreting Results in High Dimensions} |
|
\bookmark[page=260,level=1]{6.5.: Lab 1: Subset Selection Methods} |
|
\bookmark[page=260,level=2]{6.5.1.: Best Subset Selection} |
|
\bookmark[page=263,level=2]{6.5.2.: Forward and Backward Stepwise Selection} |
|
\bookmark[page=264,level=2]{6.5.3.: Choosing Among Models Using the Validation Set Approach and Cross-Validation} |
|
\bookmark[page=267,level=1]{6.6.: Lab 2: Ridge Regression and the Lasso} |
|
\bookmark[page=267,level=2]{6.6.1.: Ridge Regression} |
|
\bookmark[page=271,level=2]{6.6.2.: The Lasso} |
|
\bookmark[page=272,level=1]{6.7.: Lab 3: PCR and PLS Regression} |
|
\bookmark[page=272,level=2]{6.7.1.: Principal Components Regression} |
|
\bookmark[page=274,level=2]{6.7.2.: Partial Least Squares} |
|
\bookmark[page=275,level=1]{6.8.: Exercises} |
|
\bookmark[page=281,level=0]{7.: Moving Beyond Linearity} |
|
\bookmark[page=282,level=1]{7.1.: Polynomial Regression} |
|
\bookmark[page=284,level=1]{7.2.: Step Functions} |
|
\bookmark[page=286,level=1]{7.3.: Basis Functions} |
|
\bookmark[page=287,level=1]{7.4.: Regression Splines} |
|
\bookmark[page=287,level=2]{7.4.1.: Piecewise Polynomials} |
|
\bookmark[page=287,level=2]{7.4.2.: Constraints and Splines} |
|
\bookmark[page=289,level=2]{7.4.3.: The Spline Basis Representation} |
|
\bookmark[page=290,level=2]{7.4.4.: Choosing the Number and Locations of the Knots} |
|
\bookmark[page=292,level=2]{7.4.5.: Comparison to Polynomial Regression} |
|
\bookmark[page=293,level=1]{7.5.: Smoothing Splines} |
|
\bookmark[page=293,level=2]{7.5.1.: An Overview of Smoothing Splines} |
|
\bookmark[page=294,level=2]{7.5.2.: Choosing the Smoothing Parameter Lambda} |
|
\bookmark[page=296,level=1]{7.6.: Local Regression} |
|
\bookmark[page=298,level=1]{7.7.: Generalized Additive Models} |
|
\bookmark[page=299,level=2]{7.7.1.: GAMs for Regression Problems} |
|
\bookmark[page=302,level=2]{7.7.2.: GAMs for Classification Problems} |
|
\bookmark[page=303,level=1]{7.8.: Lab: Non-linear Modeling} |
|
\bookmark[page=304,level=2]{7.8.1.: Polynomial Regression and Step Functions} |
|
\bookmark[page=309,level=2]{7.8.2.: Splines} |
|
\bookmark[page=310,level=2]{7.8.3.: GAMs} |
|
\bookmark[page=313,level=1]{7.9.: Exercises} |
|
\bookmark[page=319,level=0]{8.: Tree-Based Methods} |
|
\bookmark[page=319,level=1]{8.1.: The Basics of Decision Trees} |
|
\bookmark[page=320,level=2]{8.1.1.: Regression Trees} |
|
\bookmark[page=327,level=2]{8.1.2.: Classification Trees} |
|
\bookmark[page=330,level=2]{8.1.3.: Trees Versus Linear Models} |
|
\bookmark[page=331,level=2]{8.1.4.: Advantages and Disadvantages of Trees} |
|
\bookmark[page=332,level=1]{8.2.: Bagging, Random Forests, Boosting} |
|
\bookmark[page=332,level=2]{8.2.1.: Bagging} |
|
\bookmark[page=336,level=2]{8.2.2.: Random Forests} |
|
\bookmark[page=337,level=2]{8.2.3.: Boosting} |
|
\bookmark[page=340,level=1]{8.3.: Lab: Decision Trees} |
|
\bookmark[page=340,level=2]{8.3.1.: Fitting Classification Trees} |
|
\bookmark[page=343,level=2]{8.3.2.: Fitting Regression Trees} |
|
\bookmark[page=344,level=2]{8.3.3.: Bagging and Random Forests} |
|
\bookmark[page=346,level=2]{8.3.4.: Boosting} |
|
\bookmark[page=348,level=1]{8.4.: Exercises} |
|
\bookmark[page=353,level=0]{9.: Support Vector Machines} |
|
\bookmark[page=354,level=1]{9.1.: Maximal Margin Classifier} |
|
\bookmark[page=354,level=2]{9.1.1.: What Is a Hyperplane?} |
|
\bookmark[page=355,level=2]{9.1.2.: Classification Using a Separating Hyperplane} |
|
\bookmark[page=357,level=2]{9.1.3.: The Maximal Margin Classifier} |
|
\bookmark[page=358,level=2]{9.1.4.: Construction of the Maximal Margin Classifier} |
|
\bookmark[page=359,level=2]{9.1.5.: The Non-separable Case} |
|
\bookmark[page=360,level=1]{9.2.: Support Vector Classifiers} |
|
\bookmark[page=360,level=2]{9.2.1.: Overview of the Support Vector Classifier} |
|
\bookmark[page=361,level=2]{9.2.2.: Details of the Support Vector Classifier} |
|
\bookmark[page=365,level=1]{9.3.: Support Vector Machines} |
|
\bookmark[page=365,level=2]{9.3.1.: Classification with Non-linear Decision Boundaries} |
|
\bookmark[page=366,level=2]{9.3.2.: The Support Vector Machine} |
|
\bookmark[page=370,level=2]{9.3.3.: An Application to the Heart Disease Data} |
|
\bookmark[page=371,level=1]{9.4.: SVMs with More than Two Classes} |
|
\bookmark[page=371,level=2]{9.4.1.: One-Versus-One Classification} |
|
\bookmark[page=372,level=2]{9.4.2.: One-Versus-All Classification} |
|
\bookmark[page=372,level=1]{9.5.: Relationship to Logistic Regression} |
|
\bookmark[page=375,level=1]{9.6.: Lab: Support Vector Machines} |
|
\bookmark[page=375,level=2]{9.6.1.: Support Vector Classifier} |
|
\bookmark[page=379,level=2]{9.6.2.: Support Vector Machine} |
|
\bookmark[page=381,level=2]{9.6.3.: ROC Curves} |
|
\bookmark[page=382,level=2]{9.6.4.: SVM with Multiple Classes} |
|
\bookmark[page=382,level=2]{9.6.5.: Application to Gene Expression Data} |
|
\bookmark[page=384,level=1]{9.7.: Exercises} |
|
\bookmark[page=389,level=0]{10.: Unsupervised Learning} |
|
\bookmark[page=389,level=1]{10.1.: The Challenge of Unsupervised Learning} |
|
\bookmark[page=390,level=1]{10.2.: Principal Components Analysis} |
|
\bookmark[page=391,level=2]{10.2.1.: What Are Principal Components?} |
|
\bookmark[page=395,level=2]{10.2.2.: Another Interpretation of Principal Components} |
|
\bookmark[page=396,level=2]{10.2.3.: More on PCA} |
|
\bookmark[page=401,level=2]{10.2.4.: Other Uses for Principal Components} |
|
\bookmark[page=401,level=1]{10.3.: Clustering Methods} |
|
\bookmark[page=402,level=2]{10.3.1.: K-Means Clustering} |
|
\bookmark[page=406,level=2]{10.3.2.: Hierarchical Clustering} |
|
\bookmark[page=415,level=2]{10.3.3.: Practical Issues in Clustering} |
|
\bookmark[page=417,level=1]{10.4.: Lab 1: Principal Components Analysis} |
|
\bookmark[page=420,level=1]{10.5.: Lab 2: Clustering} |
|
\bookmark[page=420,level=2]{10.5.1.: K-Means Clustering} |
|
\bookmark[page=422,level=2]{10.5.2.: Hierarchical Clustering} |
|
\bookmark[page=423,level=1]{10.6.: Lab 3: NCI60 Data Example} |
|
\bookmark[page=424,level=2]{10.6.1.: PCA on the NCI60 Data} |
|
\bookmark[page=426,level=2]{10.6.2.: Clustering the Observations of the NC160 Data} |
|
\bookmark[page=429,level=1]{10.7.: Exercises} |
|
|
|
\bookmark[page=435,level=0]{Index} |
|
|
|
\end{document} |
A table of contents for the book "The Elements of Statistical Learning" by some of the same authors is available at
https://gist.github.com/goerz/4c863a2fde1d3357113b95643d0ace16