Modern Scala Projects

LR function

We said before that LR is harder than the logit function. However, the LR formulation, as we shall see, is a good fit for this problem. We want to make a prediction on the fate of a sample being either benign or malignant. In other words, a prediction on a particular breast cancer tissue sample can only take one of two mutually exclusive values, based on feature measurements such as clump thickness, uniformity of cell size, and many more. Each of these feature measurements can be X1, X2, and X3, respectively.

This brings us to the beginning of a formulation of the LR function.

The core concept behind the LR function is the so-called inverse function, which is written down as:

Here is a brief interpretation of the preceding equation: ...