Course Description
Introduces the applications of machine learning methods for explanatory analysis and causal inference. Students are exposed to different views of causality in business research, machine learning concepts and methods, and the applications of machine learning in combination with econometrics methods in information systems and related disciplines.
Athena Title
Machine Learning & Econometric
Prerequisite
MARK 9650 or MGMT 9620
Semester Course Offered
Offered fall
Grading System
A - F (Traditional)
Course Objectives
The purpose of this course is to examine the recent modifications and extensions to standard methods for hypothesis testing and causal inference. Upon successful completion of this course, students should be able to: • Recognize different views of causality in business research and the formulation of research questions. • Understand empirical methods for causal inference in observational studies. • Describe machine learning concepts and methods. • Interpret model estimation results. • Acknowledge challenges of drawing causal inferences in empirical research and machine learning. • Understand and apply recent modifications and extensions to standard methods for hypothesis testing. • Understand and apply machine learning methods to develop independent, dependent, control, and instrument variables. • Understand and apply machine learning methods to match samples in quasi-experimental settings. • Understand DAG theory and apply DAG graphs to visualize research model. • Apply DAG criteria to dragonize models.
Topical Outline
- Different views of causality in business research and the formulation of research questions - Empirical methods for causal inference in observational studies - Machine learning concepts and methods - Model interpretation - Challenges of drawing causal inferences in machine learning - Recent modifications and extensions to standard methods for hypothesis testing - Machine learning for independent, dependent, control, and instrument variables - Machine learning for matching samples in quasi-experimental settings - Machine learning for probing into the underlying causal mechanisms - Machine learning for policy evaluation - DAG theory and graphs for research assumptions - Criteria to identify potential biases
Syllabus