Skip to main content
EPJ Data Science

Table 2 Results of the pairwise comparison of the distributions of casualties

From: Views to a war: systematic differences in media and military reporting of the war in Iraq

Threshold

Number of events

A 2 statistic

(i)

(ii)

(iii)

(iv)

(v)

(i)-(ii)

(i)-(iii)

(i)-(iv)

(i)-(v)

1

9,004

18,157

17,533

18,548

19,369

1,098.13

1,103.76

1,095.52

1,088.41

2

4,273

4,813

4,611

4,940

5,201

84.11

81.82

87.03

85.04

5

1163

876

851

901

952

6.60

7.11

7.81

7.92

10

484

323

310

325

340

7.25

6.72

6.63

6.82

15

296

159

154

161

169

1.93

1.86

1.58

1.94

20

206

105

100

105

108

2.29

1.77

1.54

1.47

25

159

77

75

79

82

3.09

2.82

2.49

2.57

30

123

47

47

51

52

1.43

1.43

1.28

1.30

40

69

29

29

31

32

1.85

1.85

2.02

1.87

  1. The datasets are (i) ‘IBC Baghdad’, (ii) ‘SIGACT Baghdad’, (iii) ‘SIGACT 20 km’, (iv) ‘SIGACT 30 km’ and (v) ‘SIGACT 40 km’. We used a two-sample Anderson-Darling tests (adjusted for ties) for comparison. Bold font marks cases where the value of the Anderson-Darling statistic A 2 is smaller than the critical level A 0.05 2 =2.492 (large-sample approximation) and the hypothesis of two datasets being sampled from the same distribution can not be rejected at a 5% significance level.
Back to article page