Understanding Logistic Regression

Introduction

Logistic regression is one of the most frequently used classification algorithms (classifiers). Logistic regression estimates class membership probabilities, which is done by predicting the log odds from a kind of regression model. Logistic regression can be generalized to multiclass classification. However, let’s start with binary outcomes, for example:

• Predict the likelihood of patients getting certain diseases based on the symptoms.

• Predict whether a student will get residency based on their scores and the characteristics of the medical college.

We can think about tons of examples. Most of the time, we are dealing with binary outcomes.

The logit link function

Instead of continuous outcomes, we predict class membership using logistic regression, but we can still formulate logistic regression in the way we formulate linear regression. We'll have intercept and coefficients.