Column

Are there different benefit segments? How many? How are they different?

Attribute importance weight considered when buying a car (BMW, Lexus and Mercedes). Data collected from 73 students (24 MBAs and 49 undergrad).

Column

Cluster Summary by Attribute (calculating the means)

The number of clusters in this dataset was selected using the majority rule based on 26 different criteria to determine the optimal number of clusters

  Group.1      Trendy     Styling Reliability Sportiness Performance    Comfort
1       1 -0.70539614 -0.08208834   0.7158620 -0.6405175   0.6850577 -0.1901877
2       2 -0.01577854 -0.42490717  -0.2815854  0.5005211  -0.0989237  0.5862104
3       3  1.14725137  0.85521724  -0.6566056  0.1634624  -0.9192806 -0.6979431

Are the Segments Identifiable?


 
   Cell Contents
|-------------------------|
|                       N |
|           N / Row Total |
|           N / Col Total |
|-------------------------|

 
Total Observations in Table:  73 

 
             | h_cluster 
seg_data$MBA |         1 |         2 |         3 | Row Total | 
-------------|-----------|-----------|-----------|-----------|
         MBA |        14 |         6 |         4 |        24 | 
             |     0.583 |     0.250 |     0.167 |     0.329 | 
             |     0.519 |     0.207 |     0.235 |           | 
-------------|-----------|-----------|-----------|-----------|
   Undergrad |        13 |        23 |        13 |        49 | 
             |     0.265 |     0.469 |     0.265 |     0.671 | 
             |     0.481 |     0.793 |     0.765 |           | 
-------------|-----------|-----------|-----------|-----------|
Column Total |        27 |        29 |        17 |        73 | 
             |     0.370 |     0.397 |     0.233 |           | 
-------------|-----------|-----------|-----------|-----------|

 
Statistics for All Table Factors


Pearson's Chi-squared test 
------------------------------------------------------------
Chi^2 =  7.03013     d.f. =  2     p =  0.02974588

The analysis shows that while older students (MBAs) tend to emphasize performance, the younger ones (undergrad) tend to emphasize style and comfort. This relationship is significant at the 3% level (p-value) which means you could target these clusters using the education level variable.