Introduction to Correlation Analysis

Correlation analysis is one of the most useful types of analysis we can use with game data. It allows us to understand how the variables are related to one another. This is very useful for the methods we’ll talk about later in the course, such as dimension reduction or machine learning methods. It’s also important, as we discussed before, for inferential statistics.

How variables are related to each other

We can first start by understanding how some variables are related to one another. In general, there are different methods in statistics that allow us to understand the relationship between variables. Correlation analysis is a bivariate analysis, that is, an analysis between two variables that measure the strength of an association between two variables. In such an analysis, positive and negative are used as ways to indicate the type of association. A correlation of $0$ means no relation, and usually, the values go from $-1$ to $+1$, where $+1$ is a perfect positive association and $-1$ is a perfect negative or opposite association.