Table 2 shows a data set with 10 observations. K-Nearest Neighbors classification is performed with K = 3.

Table 2: Data set for K-Nearest Neighbors classification

i 1 2 3 4 5 6 7 8 9 10

Xi -0.06 0.22 0.36 -0.08 0.11 0.02 0.19 0.16 0.09 0.03

Yi A B B A B A B A B A

(1) Based on the euclidean distance, determine the predicted classes for these 10 observations, i.e., Yi,i = 1,...,10.

(2) Provide the confusion matrix and calculate the mis-classification error rate. (3) For a new data point X = 0.01, what is the corresponding predicted classes, i.e., Y ?