Linear Regression Quiz

What is the equation for linear regression?

• y = b0 + b1x

• y = mx + c

• y = ax^2 + bx + c

• y = ex

What is the goal of linear regression?

• To find the relationship between variables and predict values.

• To cluster data points into groups.

• To calculate the distance between data points.

• To identify non-linear relationships in data.

What is the method of updating b0 and b1 values in Gradient Descent?

• Multiplication of errors.

• Iterative optimization of weights.

• Random sampling of data points.

• Statistical hypothesis testing.

What is the goal of Polynomial Regression?

• To fit a linear relationship between the variables.

• To fit a polynomial relationship between the variables.

• To group data into clusters.

• To minimize data variability.

What is the difference between Ridge Regression and Lasso Regression?

• Ridge regression minimizes absolute coefficients, while Lasso eliminates some coefficients.

• Ridge regression is used for non-linear relationships, Lasso for linear ones.

• Ridge regression uses a quadratic penalty, Lasso uses an absolute penalty.

• Both are identical in terms of regularization.

What is Mean Absolute Error (MAE)?

• The average of the difference between the original and predicted values.

• The mean of squared differences of actual and predicted values.

• The mean of root squared differences between actual and predicted values.

• The sum of squared differences between data points and the mean of the response variable.

What is the main disadvantage of Mean Absolute Error (MAE)?

• It is not differentiable.

• It is sensitive to outliers.

• It gives the direction of the error.

• It is easy to interpret.

What is the difference between Mean Squared Error (MSE) and Mean Absolute Error (MAE)?

• MSE takes the average of squared differences.

• MAE is more sensitive to outliers.

• MSE is not differentiable.

• MAE gives the direction of the error.

What does Root Mean Squared Error (RMSE) represent?

• The mean of root squared subtraction between actual and predicted values.

• The sum of squared differences between predicted and observed data points.

• The sum of squared differences between predicted points and the mean of the response variable.

• The average difference between original and predicted values.

What is R2 / Coefficient of Determination used for?

• To estimate the ratio of the variance of the dependent element explained by the target element.

• To calculate the mean of squared differences of actual values.

• To find the sum of squared differences between predicted points.

• To measure the absolute error in predictions.