Machine Learning: Theory and Applications

Chapter 1: General Introduction
1.1 Introduction to the Predictive Modeling Process
1.2 Matrix Algebra Review
1.3 Data Pre-processing
1.4 Principal Component Analysis

Chapter 2: Over-Fitting and Model Tuning
2.1 The Problem of Over-Fitting
2.2 Model Tuning and Data Splitting
2.3 Resampling Techniques
2.4 Choosing Between Models

Chapter 3: Linear Models
3.1 Variance-Bias Trade-Off
3.2 Linear Regression
3.3 Partial Least Squares
3.4 Penalized Models/Regularization

Chapter 4: Nonlinear Regression Models
4.1 Neural Networks
4.2 Multivariate Adaptive Regression Splines
4.3 Support Vector Machines
4.4 K-Nearest Neighbors

Chapter 5: Regression Trees
5.1 Regression Tree Models
5.2 Rule-Based Models
5.3 Model Aggregation: Bagging/Boosting
5.4 Random Forests

Chapter 6: Linear Classification Models
6.1 Evaluating Classification Models
6.2 Logistic Regression
6.3 Linear Discriminant Analysis and Variants
6.4 Nearest Shrunken Centroids

Chapter 7: Nonlinear Classification Models
7.1 Nonlinear Discriminant Analysis
7.2 Flexible Discriminant Analysis
7.3 Continuous Throwback: Neural networks, support vector machines, k-nearest neighbors
7.4 Naïve Bayes

Chapter 8: Classification Trees
8.1 Classification Tree Models
8.2 Model Aggregation: Bagging/Boosting
8.3 Random Forests
8.4 C5.0 Algorithm

Chapter 9: Severe Case Imbalance
9.1 Alternate Cutoffs
9.2 Adjusting Prior Probabilities
9.3 Unequal Case Weights
9.4 Cost Sensitive Training

Chapter 10: Additional Considerations
10.1 Feature Selection (e.g., Variable Selection)
10.2 Type III Errors (rejecting the null for the wrong reasons)
10.3 Measurement Error
10.4 Trusting Your Model

This workshop is designed for graduate students, post-doctoral fellows, faculty, and research scientists from the behavioral, social, and health sciences. Although it is recommended that participants have a working knowledge of the general regression model, these core concepts will be reviewed at the beginning of the workshop. Participants who seek a more in depth review prior to attending may wish to watch our Linear Regression Playlist on YouTube.

Software demonstrations for machine learning are conducted using R.  Note that R can downloaded for free. While it is helpful to have some familiarity with R, it is not necessary. The lectures which constitute the majority of the workshop are software-independent.  All demonstrations covered in the lectures slides will be illustrated in software breakout sessions in the afternoon, ensuring that participants have a working knowledge of how to implement the myriad set of machine learning approaches discussed in the workshop.

Our goal is to provide a clear and accessible “behind the scenes” understanding of many machine learning procedures for prediction and classification that are more frequently being used in the health and behavioral sciences. We strive to strike a balance between core concepts of the algorithmic procedures along with their application and interpretation when implemented with real empirical data. This workshop is designed to provide participants with the knowledge to discern which machine learning models are appropriate for their research question and the subsequent tools to analyze their data in ways not previously possible.

Doug Steinley teaches this workshop via Zoom. Participants will receive complete PDF copies of the course notes and the computer demonstrations as well as data and code for all examples. The PDFs are not time-limited and may be retained indefinitely, but should not be distributed to others without obtaining prior permission.