CLUSTER ANALYSIS Devashish
CLUSTER ANALYSIS Devashish
CLUSTER ANALYSIS Devashish
JUSTIFICATION- Since all the value are in interval scale so we will use clustering method to
fulfill our objective.
INFERENCE-
Coefficient Stage Cluster First Next
Stage Cluster Combined s Appears Stage
Cluster 1 Cluster 2 Cluster 1 Cluster 2
37 12 20 34 19 4 38 34
41.294117 7.2941176
38 1 12 6 36 37 39 5
7.7058823
39 1 8 49 38 13 0 5
Since the difference between clusters are decreasing, so we can infer that there are 2 clusters
that can be formed.
ANOVA
Cluster Error
Mean Square df Mean Square df F Sig.
dont buy product not from
an established brand 23.645 1 1.301 38 18.169 .000
buy only new products tried
& tested as safe 5.682 1 1.627 38 3.493 .069
I know most cosmetic
brands 7.471 1 1.288 38 5.802 .021
one company cannot
provide complete 2.945 1 1.512 38 1.948 .171
personalcare solution
plan shopping trips
carefully 2.231 1 1.233 38 1.809 .187
personal care companies
need to do a lot of research 19.236 1 1.273 38 15.114 .000
The F tests should be used only for descriptive purposes because the clusters have been chosen to
maximize the differences among cases in different clusters. The observed significance levels are not
corrected for this and thus cannot be interpreted as tests of the hypothesis that the cluster means are
equal.
Cluster
1 2
dont buy product not from
an established brand 3.55 2.00
buy only new products tried
& tested as safe 3.09 2.33
I know most cosmetic
brands 2.91 3.78
one company cannot
provide complete 2.45 3.00
personalcare solution
plan shopping trips
carefully 2.64 3.11
personal care companies
need to do a lot of research 3.73 2.33