4. Logistic Regression

Linear regression is useful for data with linear relations or applications for which a first-order approximation is adequate. There are many applications for which linear regression is not appropriate or optimal. Because the range of the linear model in Equation 3.3 is all of , using linear regression for data with continuous outcomes in or binary outcomes in {0,1} may not be appropriate. Logistic regression (LR) is an alternative regression technique naturally suited to such data.

- 4.1 Logistic Model
- 4.2 Maximum Likelihood Estimation
- 4.3 Iteratively Re-weighted Least Squares
- 4.4 Logistic Regression for Classification