Skip to main content

Table 2 The inconsistency in the illustrative examples

From: A graphical tool for locating inconsistency in network meta-analyses

 

a)

b)

c)

d)

e)

 

Q

df

p

Q

df

p

Q

df

p

Q

df

p

Q

df

p

Q inc

9.17

3

0.027

7.50

3

0.058

11.67

3

0.009

4.17

1

0.041

16.67

10

0.082

Q ( 1 : 2 ) inc

0.00

2

1

6.82

2

0.033

6.82

2

0.033

0.00

0

1

0.00

9

1

Q ( 1 : 3 ) inc

5.36

2

0.069

5.36

2

0.069

0.00

2

1

   

15.62

9

0.075

Q ( 1 : 4 ) inc

            

15.62

9

0.075

Q ( 1 : 5 ) inc

            

15.62

9

0.075

Q ( 1 : 6 ) inc

8.33

2

0.016

0.00

2

1

8.33

2

0.016

0.00

0

1

15.62

9

0.075

Q ( 2 : 3 ) inc

0.00

2

1

6.82

2

0.033

6.82

2

0.033

0.00

0

1

15.62

9

0.075

Q ( 2 : 4 ) inc

            

15.62

9

0.075

Q ( 2 : 5 ) inc

            

15.62

9

0.075

Q ( 2 : 6 ) inc

            

15.62

9

0.075

Q ( 3 : 4 ) inc

8.33

2

0.016

0.00

2

1

8.33

2

0.016

0.00

0

1

16.67

9

0.054

Q ( 3 : 5 ) inc

            

16.67

9

0.054

Q ( 3 : 6 ) inc

            

16.67

9

0.054

Q ( 4 : 5 ) inc

9.09

2

0.011

6.82

2

0.033

11.36

2

0.003

0.00

0

1

16.67

9

0.054

Q ( 4 : 6 ) inc

8.93

2

0.012

5.36

2

0.069

10.71

2

0.005

   

16.67

9

0.054

Q ( 5 : 6 ) inc

9.09

2

0.011

6.82

2

0.033

11.36

2

0.003

0.00

0

1

16.67

9

0.054

  1. The Q statistic for inconsistency as well the Q statistic after detaching the effect of design d are given for each of the scenarios a) to e) in Figure 3. In addition, the degrees of freedom (df) of the corresponding chi-squared distribution and the p value (p) are shown.