Skip to main content

Table 5 Cluster solutions and their respective model fit according to different indices. Arrow indicates whether higher (↑) or lower scores (↓) are indicative of better model fit, * indicates best model fit for each of the indices

From: Profiles and predictors of healthcare utilization: using a cluster-analytic approach to identify typical users across conventional, allied and complementary medicine, and self-care

 

Index

Cluster solution

Silhouette ↑

C-index ↓

Dunn index ↑

BIC ↓

Davies-Bouldin

index ↓

2 Clusters

0.14

0.37

0.20

885,194.80

2.58

3 Clusters

0.12

Inf

0.20

1,063,109.00*

3.75

4 Clusters

0.14

0.29

0.21

−80,894.13

1.95

5 Clusters

0.17

0.28

0.21

−41,601.08

1.81

6 Clusters

0.15

Inf

0.22*

− 8587.70

1.70

7 Clusters

0.18

0.24*

0.21

11,532.30

1.65*

8 Clusters

0.20

0.25

0.21

36,644.75

1.72

9 Clusters

0.21*

0.24*

0.21

54,450.64

1.75