Question

QUESTION 1)

Which of the following statements is correct?

Group of answer choices:

a) Logistic regression extends the idea of linear regression to the situation where the OUTCOME variable is categorical

b) Logistic regression extends the idea of linear regression to the situation where a PREDICTOR variable is categorical

c) Linear regression extends the idea of logistic regression to the situation where a PREDICTOR variable is categorical

d) Linear regression extends the idea of logistic regression to the situation where the OUTCOME variable is categorical

QUESTION 2)

Which statement is correct with regard to describing the odds of belonging to class 1 in a binary classification model?

Group of answer choices:

a) The ratio of the probability of belonging to class 1 to the probability of belonging to class 0

b) The probability of belonging to class 1

c) The ratio of the probability of belonging to class 0 to the probability of belonging to class 1

d) The probability of belonging to class 0

QUESTION 3)

What is the range for the value of Log Odds, or as it's called the logit?

Group of answer choices:

a) -  to +

b) 0 to +

c) 0 to 1

d) -1 to +1

QUESTION 4)

What is the interpretation of “log odds = 0” in a binary classification model?

Group of answer choices:

a) The probability of belonging to class 1 is zero

b) The probability of belonging to class 1 is undeterminable

c) The probability of belonging to class 1 is almost zero

d) The probability of belonging to class 1 is 0.5

QUESTION 5)

Which of the following statements is NOT a difference between Linear and Logistic Regression?

Group of answer choices:

a) Linear regression is more suitable for explanatory purpose, while logistic regression is more suitable for predictive purpose

b) In linear regression, the relationship between Y and the beta coefficients is non-linear. Whereas in logistic regression, the relationship between Y and the beta coefficients is linear.

c) Linear regression is more suitable for predictive purpose, while logistic regression is more suitable for explanatory purpose

d) In linear regression, the relationship between Y and the beta coefficients is linear. Whereas in logistic regression, the relationship between Y and the beta coefficients is non-linear.

Thank you so much for the help! (Data Analytics)

Answer 1

Question 1)
Right option is (a)
Because the logistics regression OUTCOME is categorical and for the linear regression it is continuous.

Question 2)
Right option is (a)
The ratio of probability of the belonging to class 1 to probability of class 0 odd in favour is the ratio of the probability of the event divided by the probability of the complementary event .

Question 3)
Option (a) is correct
Because the odd range is from 0 to 1 so the log of odds ranges from - infinity to + infinity.

Question 4)
Right option is (d)
Because as the log odd is 0 so p/(1-p) = exp(0)=1
So P = 1-p
P=0.5

Question 5)
Right option is (b) in the linear regression, the relationship between y and the beta coefficient is non linear. Whereas in the logistic regression, the relationship between y and the beta coefficient is linear.
The linear regression relation is linear so it's called as linear regression and the logistic regression relation is non linear.