My mother prepares a delicious dish called sopa seca, which is basically a spaghetti-based recipe and which translates literally from Spanish as dry soup. While it may sound like a misnomer or even an oxymoron, the name of the dish makes more sense when we learn how it is cooked. Something similar happens with the logistic regression, a model that despite its name is used to solve classification problems rather than regression ones. The logistic regression model is an extension of the linear regression models we saw in the previous chapter, and thus its name. To understand how we can use a regression model to classify, let us began by rewriting the core of the linear model but this time including a small twist as follows:

Where, f is some function known to us as the inverse link function. Why do we call f the inverse link function instead of just the link function? The reason is that traditionally people thought about these kinds of functions as functions linking the...