1 logistic regression question 1 k-means clustering question 1 hierarchichal clustering question 1 silhouette index calculation question.
how to calculate and interpret the odds
how to compare and interpret the probability
ways of calculating the distances:
squared euclidiant
manhattan
euclidian
he say in the exam he will ask either 1 or 2.
ways of calcualting linkage:
single (take the minimum distance)
complete (take the maximum distance)
average (take the average distance)
centroids (take the distance of centers)
I guess it might be either 1 or 2, as others somehow computational heavy.
calculate a1 (in-cluster distances then average)
calculate b1 (point to cluster distances then average then pick the minimum)
calculate s1 (b1-a1)/max(b1,a1)
calculate s_k (mean of all s_i for that cluster)
calculate the index (mean of all s_k for all clusters)
s-value close to 1 is better.