BIA 652 Multivariate Data Analysis



Course Catalog Description

Introduction

This course introduces basic theory and methods underlying multivariate analysis. Students will study techniques used for regression, classification, dimension reduction, and clustering. They will build expertise in applying these techniques to real data through class exercises and a project, and learn how to present results. This proficiency will enable students to become sophisticated data analysts, and to help make more informed design, marketing, and business decisions. Python will be the default programming language used for the course.

Prerequisite: Calculus (e.g., derivative and integration) and Linear Algebra (e.g., vector and matrix operation)


Campus Fall Spring Summer
On Campus X X
Web Campus X X

Instructors

Professor Email Office
Dr. Feng Mai
fmai@stevens.edu

More Information

Course Outcomes

By the end of this course, the students will be able to:

  1. understand the probability behind basic statistical models
  2. use Python to analyze multivariate data
  3. think critically about data and research findings
  4. Create realistic departmental/corporate budgets.
  5. present findings
  6. read and execute multivariate analysis techniques not covered in class

Course Resources

Textbook

  • Mathematical Statistics and Data Analysis. Author: John A. Rice, ISBN: 9780534399429
  • All of Statistics. Author: Larry A. Wasserman. ISBN: 1441923225


Lecture Outline

Topic Readings Assignments
Week 1 Introduction, Probability, Counting Rules
Week 2 Lab Session 1: Pandas
Week 3 Random Variables
Week 4 Random Variables
Week 5 Estimation
Week 6 Simple Linear Regression
Week 7 Multiple Regression
Week 8 Variable Selection and Model Comparison
Week 9 Lab Session 2: Regression using Python
Week 10 Logistic Regression and Classification
Week 11 Dimension Reduction
Week 12 Lab Session 3: Dimension Reduction and Classification using Python
Week 13 Clustering
Week 14 Bayesian Inference