Statistical Learning

---

Course Description

The main goal of this course is to

1. provide a framework for applying basic statistical learning methods to build predictive models or perform exploratory analysis,
2. properly tune, select, and validate statistical learning models, and
3. build an ensemble of learning algorithms. Topics include the concepts of Ordinary Least Squares, Subset Selection, Regularization, Dimension Reduction, Classification, Cross-validation, Bootstrapping, and Ensemble learning.

Learning Goal

UNIST School of Business Administration (SBA) is currently preparing for achieving International Accreditation by the AACSB International - the Association to Advance Collegiate Schools of Business, which represents the highest standard of achievement for business schools worldwide. Less than 5% of the world’s 13,000 business programs have earned this distinction. AACSB accreditation means students will receive relevant knowledge, challenging courses, useful skills, easier access to employers, and a wealth of resources to help them succeed. One of the main steps toward accreditation is Assurance of Learning, which “refers to processes for demonstrating that students achieve learning expectations for the programs in which they participate. Assurance of learning also assists the school and faculty members to improve programs and courses. By measuring learning, the school can evaluate its students’ success at achieving learning goals, use the measures to plan improvement efforts, and (depending on the type of measures) provide feedback and guidance for individual students” (Eligibility Procedures and Accreditation Standards for Business Accreditation, AACSB International - the Association to Advance Collegiate Schools of Business) Accordingly, the Business Communication course has been chosen for the assessment purposes in the 2016 spring semester. The students who take this course will be assessed according to the following learning goal developed by the School:

1. GLG.3 Able to develop creative approaches in research and solving theoretical and practical problems. They will be

• 3b Able to develop a critical and reflective approach to research and application of management theory and practice.

2. GLG 5. Our graduates will be able to demonstrate the extensive knowledge in the particular area of interest. They will be

• 5a Able to understand the main research stream in the particular area of interest.

---

Weekly Schedule

1. 2/27 Course Orientation
   

• Chapter 1: Basic definitions
• Chapter 2: Statistical Learning Statistical learning goal: estimate f, Prediction versus model interpretability tradeoff, Common problem classes: supervised learning (e.g. regression, classification) versus unsupervised learning ( e.g. clustering)

1. Download and install R.
2. Download the PDF textbook An Introduction to Statistical Learning with Applications in R ISLR Seventh Printing.
3. Import library “ISLR” within R.
   
4. Download all datasets the ISLR R package with all datasets for the text.
5. Read ISLR chapter 1 and chapter 2 through section 2.1.2 (pp. 1-24).
6. Optionally watch these supplementary videos:

• ISLR Slides: Statistical Learning
• ISLR Videos: Opening Remarks and Examples, Supervised and Unsupervised Learning

2. 3/06 Ordinary Least Square
   

• Chapter 3: Simple linear regression Coefficient estimation, Assessing the accuracy of coefficient estimates, Assessing the accuracy of the model, Multiple linear regression, Relationships between response and predictors, Predictor selection, Assessing model fit, Prediction and confidence in prediction

1. Read chapter 3 through the end of section 3.2 (p. 82).
   
2. Do the guided lab of section 3.6 through 3.6.3.
3. Optionally watch these supplementary videos.

• ISLR Slides: Linear Regression
• ISLR Videos: Simple Linear Regression, Hypothesis Testing, Interpreting Regression Coefficients, Interactions and Nonlinearity

3. 3/13 Subset Selection
   

• ISLR Slides: Model Selection
• ISLR Videos: Model Selection and Qualitative Predictors, Best Subset Selection, Forward Stepwise Selection, Backward Stepwise Selection, Estimating Test Error I, Estimating Test Error II

4. 3/20 Regularization
   

• ISLR Slides: Model Selection
• ISLR Videos: Shrinkage Methods and Ridge Regression, The Lasso, Tuning Parameter Selection

5. 3/27 Generalized Additive Model
   

• Chapter 7: Moving Beyond Linearity Polynomial regression, Step and basis functions, Regression and smoothing splines, Local regressions, Generalized Additive Models (GAMs)

1. Read chapter 7 and complete the guided lab.
2. Optionally watch these supplementary videos.

• ISLR Slides: Moving Beyond Linearity
• ISLR Videos: Polynomial Regression and Step Functions, Piecewise Polynomials and Splines, Smoothing Splines, Local Regression and Generalized Additive Models

6. 4/03 Discriminant Analysis
   

• Chapter 4: Classification Linear discriminant analysis (LDA) Quadratic discriminant analysis (QDA)

1. Read chapter 4 and complete the guided lab.
2. Optionally watch these supplementary videos.

• ISLR Slides: Classification
• ISLR Videos: Introduction to Classification,Linear Discriminant Analysis and Bayes Theorem, Univariate Linear Discriminant Analysis, Multivariate Linear Discriminant Analysis, Quadratic Discriminant Analysis and Naive Bayes

7. 4/10 Logistic Regression

• Chapter 4: Classification Logistic regression and multinomial logistic regression

1. Read chapter 4 and complete the guided lab.
2. Optionally watch these supplementary videos.

• ISLR Slides: Classification
• ISLR Videos: Logistic Regression, Multiple Logistic Regression

8. 4/17 Accuracy, Precision, and Recall

• Chapter 5: Validation Cross-Validation, Validation set method, Leave-one-out cross validation (LOOCV), k-Fold cross validation and the bias-variance trade-off, The Bootstrap

1. Read chapter 5 and complete the guided lab.
2. Optionally watch these supplementary videos.

• ISLR Slides: Cross-validation and the Bootstrap
• ISLR Videos: Validation Set Approach, k-fold Cross-Validation, Cross-Validation: The Right and Wrong Ways

9. 4/24 Support Vector Machine
   

• ISLR Slides: Support Vector Machines
• ISLR Videos: Support Vector Machines

10. 5/01 Principal Component Analysis
    

• ISLR Slides: Unsupervised Learning
• ISLR Videos: Unsupervised Learning and Principal Components Analysis, Exploring Principal Components Analysis and Proportion of Variance Explained

11. 5/08 K-means Clustering
    

• ISLR Slides: [https://drive.google.com/open?id=1YeRJja8beLFdkmE1w5e5kPTzH6UHiUE8]
• ISLR Videos: K-means Clustering

12. 5/15 Hierarchical Clustering

• ISLR Slides: [https://drive.google.com/open?id=1YeRJja8beLFdkmE1w5e5kPTzH6UHiUE8]
• ISLR Videos: Hierarchical Clustering

13. 5/22 No class. Buddha’s birthday.

14. 5/29 Classification and Regression Tree
    

• ISLR Slides: Tree-based Methods
• ISLR Videos: Decision Trees, Pruning a Decision Tree, Classification Trees and Comparison with Linear Models

15. 6/05 Bagging and Boosting
    

• ISLR Slides: Tree-based Methods
• ISLR Videos: Bootstrap Aggregation (Bagging) and Random Forests, Boosting and Variable Importance

16. 6/12 Review and Discussion

---

---

par(mar = c(4, 4, .1, .1))
with(mtcars, {
plot(mpg~hp, pch=20, col='darkgray')
lines(lowess(hp, mpg))
})

plot(cars)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.