Applied Machine Learning - Ch7: Linear Regression

What is regression?

Regression is a statistical modeling technique used to understand and predict the relationship between a dependent variable and one or more independent variables.

What are the main types of regression?

Linear Regression (straight-line relationship), Non-linear Regression (curved relationships), Logistic Regression (binary outcomes)

What is linear regression?

It's a method to model the relationship between a numerical predictor and a numerical target using a straight line.

When should we use linear regression?

When both the dependent and independent variables are continuous and numeric.

What is the goal of linear regression?

To find the best-fitting line that minimizes the difference between predicted and actual values (errors).

What are predictor and target variables?

Predictor (X): The input/independent variable. Target (Y): The output/dependent variable we want to predict.

What is the linear regression equation?

Y = a + bX. Where: a is the intercept, b is the slope, X is the independent variable, and Y is the predicted value.

What are residuals?

The difference between the actual and predicted values.

What is Sum of Squared Errors (SSE)?

The total of the squared differences between actual and predicted values. Lower SSE indicates a better model

What is R-squared?

Also called the coefficient of determination, it tells how well the model explains the variability of the target variable. Ranges from 0 to 1.

How can linear regression be used to predict exam scores?

Example: Y = 8.5X + 44. If a student studied for 6 hours: Y = 8.5 * 6 + 44 = 95

What is multiple linear regression?

A method to model the relationship between one target variable (Y) and two or more predictor variables (X1, X2, ..., Xn)

What does a multiple regression equation look like?

Y = b0 + b1X1 + b2X2 + ... + bnXn

What are the main steps to perform linear regression in Python?

1. Import libraries.

2. Load data.

3. Extract features and target.

4. Build and fit the model.

5. Evaluate with SSE or R-squared. 6. Visualize and make predictions.