Question

1. The agglomerative clustering method that starts by placing each observation into its own cluster, and then progressively agglomerates each observation based on the desired linkage rule. The complete-linkage approach agglomerates the observation or sub-cluster in question to the sub-cluster having the shortest distance to the most distant observation in another sub-cluster.

Suppose that we have the following data (one variable). Use complete linkage to identify the clusters. Data: 0 0 1 3 3 6 7 9 10 10

Answer 1

We will use R to solve this problem

Use following codes for complete linkage

data1=c(0,0,1,3,3,6,7,9,10,10)

dataframe<-data.frame(data1)

distmat<-dist(dataframe, method="euclidean",diag=FALSE, upper=FALSE)

clust<-hclust(distmat, method="complete")

Cluster<-cutree(clust,2)

table(Cluster)

Cluster Distribution
	Cluster
1	5
2	5

dataframe<-cbind(dataframe,Cluster)

agg<-aggregate(. ~ Cluster,data = dataframe, mean)

Cluster Means
Cluster	data1
1	1.4
2	8.4

rect.hclust(clust,2)

plot(clust,label=,hang=-1)

#Dendogram