Chapter 9: Statistics for Classification

In the previous chapter, we covered regression problems where correlations, in the form of a numerical relationship between independent variables and dependent variables, are established.

Different from regression problems, classification problems aim to predict the categorical dependent variable from independent variables. For example, with the same Netflix stock price data and other potential data, we can build a model to use historical data that predicts whether the stock price will rise or fall after a fixed amount of time. In this case, the dependent variable is binary: rise or fall (let's ignore the possibility of having the same value for simplicity). Therefore, this is a typical binary classification ...

Get Essential Statistics for Non-STEM Data Analysts now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.