Which type of numeric value does a logistic regression model estimate?
A. Probability
B. A p-value
C. Any integer
D. Any real number
2 Comments on “Which type of numeric value does a logistic regression model estimate?”
Jack Huangsays:
Why is the answer A?
0
0
Mayukh Msays:
@JackHuang. A is correct because Logistic regression gives the output for each target variable in terms of probability for 0 or 1. E.g. the output of a logistic regression looks like 0(0.974) 1(0.026). We then apply a rectifier logic on this regression output to get the actually binary classifier output as 0 or 1. In this case if rectification threshold is 0.5 or even 0.9, the output is 0, but if the system is very precise like 0.999, the output will still be 1.
Why is the answer A?
0
0
@JackHuang. A is correct because Logistic regression gives the output for each target variable in terms of probability for 0 or 1. E.g. the output of a logistic regression looks like 0(0.974) 1(0.026). We then apply a rectifier logic on this regression output to get the actually binary classifier output as 0 or 1. In this case if rectification threshold is 0.5 or even 0.9, the output is 0, but if the system is very precise like 0.999, the output will still be 1.
0
0