Recall & Review
beginner
What is multiple linear regression?
Multiple linear regression is a method to predict a number by using two or more input features. It finds a straight line (or plane) that best fits the data points in multiple dimensions.
Click to reveal answer
beginner
Write the general formula for multiple linear regression.
The formula is: y = b0 + b1*x1 + b2*x2 + ... + bn*xn + e, where y is the predicted value, b0 is the intercept, b1 to bn are coefficients, x1 to xn are input features, and e is the error term.
Click to reveal answer
beginner
Why do we use multiple linear regression instead of simple linear regression?
Because multiple linear regression can use many features to make better predictions, while simple linear regression uses only one feature. This helps capture more information from the data.
Click to reveal answer
intermediate
What does the coefficient (like b1) represent in multiple linear regression?
Each coefficient shows how much the predicted value changes when that feature increases by one unit, keeping other features constant.
Click to reveal answer
intermediate
How do we measure how well a multiple linear regression model fits the data?
We use metrics like R-squared, which tells us the percentage of variation in the target explained by the features, and Mean Squared Error (MSE), which measures average prediction error.
Click to reveal answer
What does the intercept (b0) in multiple linear regression represent?
Which metric tells how much of the target's variation is explained by the model?
If a coefficient b2 is negative, what does it mean?
Multiple linear regression can be used when:
What is the error term (e) in the regression formula?
Explain how multiple linear regression uses features to make predictions.
Describe two ways to evaluate the performance of a multiple linear regression model.