8.4 Suppose we produce ten bootstrap samples from a data set containing red and
ID: 2910099 • Letter: 8
Question
8.4 Suppose we produce ten bootstrap samples from a data set containing red and green classes. We then apply a classification tree to each bootstrap sample and, for a specific value of X, produce 10 estimates of P(Class is Red|X):
There are two common ways to combine these results together into a single class prediction. One is the majority vote approach discussed in the notes. The second approach is to classify based on the average probability. What is the final classification under the majority vote method?:
a) red
b) green
0.1,0.15, 0.2,0.2,0.55,0.6, 0.6,0.65,0.7, and 0.75Explanation / Answer
In the majority vote method, the class that receives the maximium votes is assigned to X.
From the 10 estimates of P(Class is Red|X), we claasify X according to its probabilities of being Red
0.1 -> Green (Since P(Green)=0.9 and P(Red) =0.1)
0.15 -> Green
0.2 -> Green
0.2 -> Green
0.55 -> Red
0.6 -> Red
0.6 -> Red
0.65 -> Red
0.7 -> Red
0.75 -> Red
Thus we see that as per estimates of P(Class is Red|X), class Red receives the maximum votes (6 votes) vs Class Green which receives only 4 votes.
Thus the final classification under the majority vote method is Red.
Answer: a) Red.
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.