Table 2 Random effects person-by-rater D-studies results.

From: Evaluating the role of ChatGPT in enhancing EFL writing assessments in classroom settings: A preliminary investigation

Number of persons (p)

Number of raters (r)

ChatGPT3.5

ChatGPT4

Teachers

G

Phi

G

Phi

G

Phi

30

1

0.66

0.65

0.89

0.88

0.80

0.77

30

2

0.80

0.79

0.94

0.93

0.89

0.87

30

3

0.86

0.85

0.96

0.96

0.93

0.91

30

4

0.89

0.88

0.97

0.97

0.94

0.93

30

5

0.91

0.90

0.98

0.97

0.95

0.94

30

6

0.92

0.92

0.98

0.98

0.96

0.95

30

7

0.93

0.93

0.98

0.98

0.97

0.96

30

8

0.94

0.94

0.98

0.98

0.97

0.96

30

9

0.95

0.94

0.99

0.98

0.97

0.97

30

10

0.95

0.95

0.99

0.99

0.98

0.97