In this chapter, we took a crash course in univariate analysis. We took a closer look at the ways used to compute covariance, the Pearson r score, and the Pearson r² score, as well as the methods deployed to interpret this data. We then took a look at the baseball dataset again and explored the question, Is there a relationship between scoring and winning? It may be a surprise to the reader, but we found out that the relationship between the two variables is weak. We also looked at regression analysis, which allows us to estimate unknown output variables based on the covariance of the existing data. We also spent time knowing about the pitfalls of blindly using simple linear regression.

The next chapter looks more at prediction, but this time from the perspective of Bayesian analysis. Bayesian probability is a form of conditional probability where we estimate the likelihood of events happening based on the evidence of past probabilities.