6.2.3 Parameters and Hyper-parameters

These are crucial for building and tuning models.

• In a linear regression model, parameters are the intercept and slope.
• Hyperparameters are sample size, the number of trees on a random forest model, the learning rate, the regularisation setting (λ) in ridge and lasso regression.

When modelling infectious diseases, it is important to understand the underlying patterns and dynamics of growth.