Skip to main content

Table 5 Classification performance of the LR measures selected in the study

From: How effective are lexical richness measures for differentiations of vocabulary proficiency? A comprehensive examination with clustering analysis

 

Mean silhouette

SD (silhouette)

Number of misspecifications

Classification accuracy

D

0.6611

0.1732

2

96.23%

Types

0.6289

0.2187

3

94.34%

RootTTR

0.6469

0.1539

3

94.34%

V1

0.6124

0.1933

3

94.34%

Uber

0.6431

0.1577

5

90.57%

LogTTR

0.6318

0.1664

6

88.68%

V2

0.5876

0.1837

6

88.68%

Honore H

0.5277

0.2022

6

88.68%

V1TR

0.4845

0.2065

8

84.91%

TTR

0.5532

0.1703

10

81.13%

Tokens

0.5408

0.1804

11

79.25%

Yule I

0.5121

0.1773

12

77.36%

RE

0.4295

0.202

16

69.81%

V2TR

0.5221

0.1705

16

69.81%

Yule K

0.7028

0.189

17

67.92%

Vm

0.7126

0.1797

17

67.92%

E

0.4754

0.1698

18

66.04%

Sichel S

0.4482

0.168

26

50.94%