In this chapter, we began with an overview of statistical modeling and how to write model formulas in R. Then, we also saw how to fit our data using linear methods. More specifically, we showed you how to use linear regression, generalized linear models, and generalized additive models to model your data and use statistical methods to assess the fit of your model to help choose the best one. Next, we showed you how to use analysis of variance to fit your data to a linear model when all the explanatory variables are categorical. Finally, we also saw how to use exploratory methods such as linear discriminant analysis, principal component analysis, and hierarchical clustering to separate your data into groups. While linear models are the most commonly used statistical models in scientific computing, there are times when nonlinear methods are preferable. Now that you know how to use linear methods to model your data, you will move on to nonlinear methods in the next chapter, where you will find out how to use non-parametric regression for exploratory analysis.

References:

Crawley, Michael J. 2005. Statistics: An Introduction Using R. Chinchester: John Wiley & Sons. Ltd.