Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.

Skip to main content

Table 2 Results of intercept \(\eta _1\) and slope \(\beta _1\) when the degree of ICS=0.1, ICC=0.3, missing rate was 20%, sample size N was 50, missing mechanism was MAR, \(C=4\)

From: Multiple imputation methods for missing multilevel ordinal outcomes

Parameter

Method

Mean Est

Mean SE

Empirical SE

Rel Bias (%)

Cov Prob (%)

MSE

\(\varvec{\eta _1=-0.4}\)

       
 

Full

-0.40

0.20

0.20

-0.97

95.50

0.04

 

CCA

-0.19

0.21

0.22

53.07

79.70

0.09

 

FCS+CS

-0.37

0.21

0.20

7.06

95.80

0.04

 

FCS

-0.37

0.21

0.20

7.98

95.90

0.04

 

JM+CS

-0.34

0.23

0.22

15.09

94.18

0.05

 

JM

-0.33

0.23

0.22

16.31

95.08

0.05

\(\varvec{\beta _1=-0.2}\)

       
 

Full

-0.21

0.19

0.20

-4.48

92.40

0.04

 

CCA

-0.10

0.21

0.23

51.09

89.90

0.06

 

FCS+CS

-0.17

0.21

0.21

15.09

95.10

0.04

 

FCS

-0.17

0.21

0.21

16.22

94.70

0.04

 

JM+CS

-0.13

0.23

0.24

32.69

93.99

0.06

 

JM

-0.13

0.24

0.24

33.50

93.57

0.06