Logistic Regression Quiz! #23

Test your knowledge!

Hello Everyone,

Welcome to another edition of this newsletter focused on MCQs on a very important topic in machine learning.

Whether you are targeting FAANG companies or other companies in general, Logistic Regression is one of the most favourite topics of interviewers. This algorithm may look simple, but candidates still fail to answer very basic questions related to this topic.

The reason is, candidates keep running after latest algorithms coming in the market everyday without understanding the building blocks (Linear Regression, Logistic Regression, Decision Tree etc.) of machine learning. Keeping yourself updated with the latest trends and technologies is a good thing, but it shouldn’t come at the cost of ignoring the basics.

Again a reminder, your dream companies will always evaluate your performance on the fundamentals. So, prepare them well.

The quiz answers and brief explanations will be provided in the next edition of the newsletter.

---

1. What is the shape of a sigmoid function?

   1. Bell shape

   2. S shape

   3. U shape

   4. Z shape

2. Logistic Regression can only work for the binary classification problems.

   1. True

   2. False

3. Logistic Regression is a ___________ model.

   1. Parametric

   2. Non-parametric

4. Logistic Regression is derived from _______.

   1. Linear Regression

   2. Decision Tree

   3. Random Forest

   4. Gradient Boosting Machines (GBM)

5. Logistic Regression is a Generalized Linear Model (GLM).

   1. True

   2. False

6. Which of the following defines log of odds in a binary logistic regression model? Please note that p is the probability of favourable event.

   1. log(p) - log(1-p)

   2. log(p) + log(1-p)

   3. log(p) / log(1-p)

   4. None of the above

7. Coefficients of independent variables in a logistic regression model can be negative.

   1. True

   2. False

8. Log Odds can be negative in a binary logistic regression model.

   1. True

   2. False

9. The predicted probability of an outcome class can be negative in a binary logistic regression model.

   1. True

   2. False

10. Which of the following methods is more suitable to calculate parameters in a logistic regression model?

    a. Ordinary Least Squares (OLS)

    b. Maximum Likelihood Estimation (MLE)

11. What is the relationship between odds ratio and probability?

    1. probability = (odds ratio/(1+odds ratio))

    2. probability = (odds ratio/(1-odds ratio))

    3. probability = odds ratio*(1+odds ratio)

    4. probability = odds ratio*(1-odds ratio)

12. What are the odds of getting number ‘2’ on a fair dice?

    1. 1:5

    2. 2:5

    3. 3:5

    4. None of the above

13. What is the range of logit (log odds) function used in a logistic regression model?

    1. (-infinity, infinity)

    2. (0, infinity)

    3. (-infinity, 0)

    4. (0,1)

14. Which of the following is used to convert the output of a logistic regression model to a class label?

    1. Encoding

    2. Threshold value

    3. Feature selection

    4. Confusion matrix

15. Which loss function is generally used in a logistic regression model?

    1. Squared Loss

    2. Log Loss

    3. None of the above

16. Is Mean Squared Error (MSE) a suitable evaluation metric for a logistic regression model?

    1. Yes

    2. No

17. Which of the following is not generally used as an evaluation metric in a logistic regression model?

    1. Precision

    2. Recall

    3. F1-score

    4. RMSE

Was this QUIZ helpful?

---

Curious about a specific AI/ML topic? Let me know in comments.

Also, please share your feedbacks and suggestions. That will help me keep going. Even a “like” on my posts will tell me that my posts are helpful to you.

See you soon!

-Kavita

---

P.S. Let’s grow our tribe. Know someone who is curious to dive into ML and AI? Share this newsletter with them and invite them to be a part of this exciting learning journey.