Skip to main content

Table 7 Summary of results for the PLINY case study (n=56)

From: Recommendations for the analysis of individually randomised controlled trials with clustering in one arm – a case of continuous outcomes

Model

Treatment estimate

Standard error

Residual variance

Random variance

Control variance

ICC

Ignore clustering

6.83

5.35

398.13

   

Random effects

      

Individual clusters of size 1

6.83

5.35

398.13

<0.0001

 

<0.0001a

One large cluster

6.83

5.35

398.13

<0.0001

 

<0.0001a

Artificial-clusters

6.93

5.48

394.01

4.84

 

0.0121a

Partially clustered

      

Individual clusters of size 1

6.83

5.35

398.13

<0.0001

 

<0.0001b

One large cluster

6.83

5.35

398.13

<0.0001

 

<0.0001b

Artificial-clusters

6.83

5.35

398.13

<0.0001

 

<0.0001b

Heteroskedastic

      

Individual clusters of size 1

6.83

5.29

338.50

<0.0001

449.54

<0.0001b

One large cluster

6.83

5.29

338.50

<0.0001

449.54

<0.0001b

Artificial-clusters

6.83

5.29

338.50

<0.0001

449.54

<0.0001b

  1. aICC across both arms of the trial
  2. bICC in the intervention arm only