STT 3852

Statistical Learning II
Fall 2026 · Appalachian State University

Instructor
Dr. Lasanthi Watagoda
Associate Professor of Statistics

Class Meetings
Tuesday & Thursday
11:00 AM – 12:15 PM

Office Hours
Tuesday & Thursday
9:15 – 10:45 AM
Edwin Duncan Hall 123C

Prerequisite
STT 3851

Course Description

This course serves as a continuation of STT 3851 (Statistical Learning I). Fundamentals of generalized linear models (GLMs) are explored, with emphasis on the linear exponential family, link functions, and applications to categorical and count response variables.

Supervised learning techniques for classification and tree-based methods are examined for both regression and classification problems. Unsupervised learning is introduced through principal component analysis and clustering methods.

Additional topics such as support vector machines, regression splines, and smoothing splines may be included. Students will complete projects using methods and algorithms covered in the course and communicate their results using professional tools and principles of reproducible statistical research.

Student Learning Outcomes

By the end of the course, students should be able to:

  • explain key concepts in statistical learning and use R for statistical analysis;
  • fit statistical models in R and interpret model output and diagnostics;
  • describe and construct generalized linear models;
  • analyze categorical and count response data using appropriate GLMs;
  • apply principal component analysis;
  • construct and interpret decision-tree models;
  • apply clustering methods;
  • evaluate statistical models using appropriate diagnostics and performance measures; and
  • communicate statistical findings clearly through reproducible reports that integrate analysis, code, and interpretation.

Course Materials

Texts and Software

Primary references

  • James, G., Witten, D., Hastie, T., & Tibshirani, R. An Introduction to Statistical Learning. A free electronic version is available from the authors.
  • Frees, E. W. (2010). Regression Modeling with Actuarial and Financial Applications. Cambridge University Press. ISBN 978-0521135962.

Computing

  • R
  • RStudio / Posit
  • Course RStudio server provided by Appalachian State University
  • Reliable internet access and a computer capable of accessing course resources

Required purchases

Students should obtain lawful access to the Frees textbook if it is not supplied through the University’s textbook rental or other course-material program. The ISLR text and the course computing software are available without a required individual software purchase.

Assessment & Grading

Student performance will be evaluated using homework, quizzes, a project, a midterm examination, and a comprehensive final examination.

Assessment Weight
Homework 15%
Quizzes 30%
Project 15%
Midterm Exam 15%
Final Exam 20%
Attendace 05%
Total 100%

Grading Scale

Range Grade Range Grade
92.50% and above A 72.50–77.49% C
90.00–92.49% A– 70.00–72.49% C–
87.50–89.99% B+ 67.50–69.99% D+
82.50–87.49% B 62.50–67.49% D
80.00–82.49% B– 60.00–62.49% D–
77.50–79.99% C+ 59.99% and below F

Attendance & Participation

Students are expected to attend class regularly and participate actively in course activities. Attendance will be taken during class.

Students should communicate with the instructor as soon as possible when circumstances interfere with attendance and should follow Appalachian State University’s procedures for qualifying absences.

Course Assessments

Homework

Students are expected to complete all assigned problems. Selected assignments, or selected parts of assignments, may be graded. Due dates are listed in the course pacing schedule.

Quizzes

Short quizzes will generally be given throughout the semester and will assess recent course material.

Midterm Examination

One midterm examination will assess material from the first major portion of the course.

Project

The course project will require students to apply statistical-learning methods, use R appropriately, interpret results, and communicate findings in a professional and reproducible format.

Final Examination

A comprehensive final examination will cover material from throughout the course. The examination date and procedures will follow the University’s official final-examination schedule.

Diverse Scholarly Perspectives

This course engages diverse scholarly perspectives in order to develop critical thinking, analysis, and debate. The inclusion of a reading, method, example, source, or other course material does not imply endorsement of the ideas or viewpoints it contains.

University Policies & Student Responsibilities

Academic Integrity

Students are expected to uphold Appalachian State University’s Academic Integrity Code and to contribute to an academic environment grounded in honesty, fairness, responsibility, and respect.

Access & Opportunity

Appalachian State University is committed to accessible learning environments and equal opportunity. Students who need disability-related accommodations or academic adjustments should contact the Office of Access & Opportunity: Disability Resources.

Attendance

Appalachian State University expects students to attend class and to remain responsible for work missed. University policies address religious observances, University-sponsored activities, emergency absences, and other qualifying circumstances.

Student Engagement

University guidance indicates that students should generally expect substantial out-of-class preparation for each hour of class time. Success in this course requires consistent practice, reading, coding, and review outside scheduled class meetings.

Current University policy information:
Academic Affairs — Policy and Statement Information

Course Schedule

A separate Course Pacing document provides the detailed weekly schedule of topics, readings, homework, quizzes, examinations, project milestones, University breaks, and other important dates.

View Course Pacing

Fall 2026 instructional period: August 17 – December 2, 2026.

The detailed schedule is a planning guide and may be adjusted when necessary to support student learning or respond to University schedule changes. Material changes to course expectations will be communicated to students.

Syllabus Status

This syllabus is a guide to the course and does not constitute an express or implied contract. Course procedures or pacing may be adjusted when academically appropriate. Material changes will be communicated clearly to students.