1  Introduction

In our final three-week block, we’ll cover four topics:

Data analysis and interpretation (Week 8)

This section revisits descriptive statistics, which are used to summarise large data sets. Understanding these basics is crucial before advancing to inferential statistics, which enable predictions and conclusions about populations based on samples, so we’ll make sure our understanding of these basic concepts is secure.

We’ll also revise some challenges in data analysis, such as dealing with missing data and outliers.

Regression analysis (Week 8)

This section explores regression analysis, a standard statistical method for examining relationships between variables. Mastering this technique allows us to model and predict outcomes based on independent variables.

We’ll build on our understanding of linear regression and address common challenges (such as multicollinearity and overfitting), ensuring we can apply regression analysis effectively.

Introduction to multivariate analysis (Week 9)

This section introduces multivariate analysis, which examines patterns and relationships among multiple variables simultaneously. By understanding this more advanced technique, we can uncover deeper insights and interactions in complex data sets.

We’ll introduce some foundational methods like principal component analysis (PCA) and move toward more sophisticated approaches, which will be covered in more detail in the B1705 module in Semester Two. Challenges such as variable scaling and multivariate normality will also be discussed.

Dealing with categorical data (Week 10)

This section focuses on handling categorical data, an essential skill for data analysis in sport. We’ll explore methods for encoding categorical variables, such as one-hot encoding and ordinal encoding, and understand how these choices impact model performance.

We’ll also address the unique challenges of analysing categorical data, like dealing with class imbalance or creating meaningful visualisations, to ensure we can handle these types of variables with confidence.