Q. How can you improve a linear regression model that is underfitting?
A.
Add more features
B.
Reduce the number of features
C.
Increase regularization
D.
Use a simpler model
Show solution
Solution
To improve a linear regression model that is underfitting, you can add more features to capture the underlying patterns in the data.
Correct Answer:
A
— Add more features
Learn More →
Q. In linear regression, what does multicollinearity refer to?
A.
High correlation between the dependent variable and independent variables
B.
High correlation among independent variables
C.
Low variance in the dependent variable
D.
Independence of residuals
Show solution
Solution
Multicollinearity refers to a situation where independent variables in a regression model are highly correlated with each other.
Correct Answer:
B
— High correlation among independent variables
Learn More →
Q. In the context of linear regression, what does the term 'overfitting' refer to?
A.
The model performs well on training data but poorly on unseen data
B.
The model is too simple to capture the underlying trend
C.
The model has too many features
D.
The model is perfectly accurate
Show solution
Solution
Overfitting occurs when a model learns the training data too well, capturing noise and leading to poor performance on unseen data.
Correct Answer:
A
— The model performs well on training data but poorly on unseen data
Learn More →
Q. In which scenario would you use linear regression?
A.
Predicting customer churn
B.
Forecasting sales revenue based on advertising spend
C.
Classifying emails as spam or not spam
D.
Segmenting customers into different groups
Show solution
Solution
Linear regression is suitable for forecasting sales revenue based on advertising spend, as it involves predicting a continuous variable.
Correct Answer:
B
— Forecasting sales revenue based on advertising spend
Learn More →
Q. What assumption is made about the residuals in linear regression?
A.
They should be normally distributed
B.
They should be correlated with the predictors
C.
They should have a non-constant variance
D.
They should be positive
Show solution
Solution
One of the key assumptions of linear regression is that the residuals (errors) should be normally distributed.
Correct Answer:
A
— They should be normally distributed
Learn More →
Q. What does the coefficient in a linear regression model represent?
A.
The strength of the relationship between variables
B.
The predicted value of the dependent variable
C.
The error in predictions
D.
The number of features in the model
Show solution
Solution
The coefficient in a linear regression model represents the strength and direction of the relationship between the independent variable and the dependent variable.
Correct Answer:
A
— The strength of the relationship between variables
Learn More →
Q. What is the assumption of linearity in linear regression?
A.
The relationship between the independent and dependent variables is linear
B.
The residuals are normally distributed
C.
The independent variables are uncorrelated
D.
The dependent variable is categorical
Show solution
Solution
The assumption of linearity states that the relationship between the independent and dependent variables should be linear.
Correct Answer:
A
— The relationship between the independent and dependent variables is linear
Learn More →
Q. What is the effect of multicollinearity in a linear regression model?
A.
It improves model accuracy
B.
It makes coefficient estimates unstable
C.
It has no effect on the model
D.
It simplifies the model
Show solution
Solution
Multicollinearity can make coefficient estimates unstable and difficult to interpret in a linear regression model.
Correct Answer:
B
— It makes coefficient estimates unstable
Learn More →
Q. What is the effect of outliers on a linear regression model?
A.
They have no effect
B.
They can significantly skew the results
C.
They improve the model's accuracy
D.
They only affect the intercept
Show solution
Solution
Outliers can significantly skew the results of a linear regression model, affecting both the slope and intercept.
Correct Answer:
B
— They can significantly skew the results
Learn More →
Q. What is the primary purpose of linear regression in machine learning?
A.
To classify data into categories
B.
To predict a continuous outcome variable
C.
To cluster similar data points
D.
To reduce dimensionality of data
Show solution
Solution
Linear regression is used to predict a continuous outcome variable based on one or more predictor variables.
Correct Answer:
B
— To predict a continuous outcome variable
Learn More →
Q. What is the role of the intercept in a linear regression equation?
A.
It represents the slope of the line
B.
It is the predicted value when all predictors are zero
C.
It indicates the strength of the relationship
D.
It is not relevant in linear regression
Show solution
Solution
The intercept in a linear regression equation represents the predicted value of the dependent variable when all independent variables are zero.
Correct Answer:
B
— It is the predicted value when all predictors are zero
Learn More →
Q. Which of the following applications is NOT suitable for linear regression?
A.
Predicting house prices based on features
B.
Estimating the impact of temperature on ice cream sales
C.
Classifying images into categories
D.
Forecasting stock prices based on historical data
Show solution
Solution
Classifying images into categories is not suitable for linear regression, as it is a classification task rather than a regression task.
Correct Answer:
C
— Classifying images into categories
Learn More →
Q. Which of the following is a common application of linear regression?
A.
Image classification
B.
Stock price prediction
C.
Customer segmentation
D.
Anomaly detection
Show solution
Solution
Linear regression is commonly used for predicting continuous outcomes, such as stock prices based on historical data.
Correct Answer:
B
— Stock price prediction
Learn More →
Q. Which of the following is a common assumption made by linear regression models?
A.
The relationship between variables is non-linear
B.
The residuals are normally distributed
C.
The predictors are categorical
D.
There is no multicollinearity among predictors
Show solution
Solution
One common assumption of linear regression is that the residuals (errors) are normally distributed.
Correct Answer:
B
— The residuals are normally distributed
Learn More →
Q. Which of the following is NOT a limitation of linear regression?
A.
Assumes a linear relationship
B.
Sensitive to outliers
C.
Can only handle numerical data
D.
Can model complex relationships
Show solution
Solution
Linear regression cannot model complex relationships, which is a limitation, but it can handle numerical data and is sensitive to outliers.
Correct Answer:
D
— Can model complex relationships
Learn More →
Q. Which of the following techniques can be used to improve a linear regression model?
A.
Adding more irrelevant features
B.
Feature scaling
C.
Using a more complex model
D.
Ignoring outliers
Show solution
Solution
Feature scaling can help improve the performance of a linear regression model, especially when predictors are on different scales.
Correct Answer:
B
— Feature scaling
Learn More →
Showing 1 to 16 of 16 (1 Pages)
