Table II.
Relative Standard Deviation (in Per Cent) in Population Parameter Estimates for the Different Methods When Data Were MCAR, MAR and MNAR
MCAR | MAR | MNAR | ||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
CLmale | CLfemale | BSV | ResErr | CLmale | CLfemale | BSV | ResErr | CLmale | CLfemale | BSV | ResErr | |
ALL | 3.0 | 3.8 | 13 | 11 | 3.0 | 3.8 | 13 | 11 | 3.0 | 3.8 | 13 | 11 |
EST | 3.4 | 4.6 | 15 | 11 | 3.7 | 4.5 | 15 | 11 | 3.6 | 4.2 | 16 | 11 |
MOD | 3.4 | 4.5 | 15 | 11 | 3.5 | 4.4 | 15 | 11 | 3.5 | 4.7 | 17 | 11 |
MI | 3.5 | 4.6 | 16 | 11 | 3.5 | 4.6 | 16 | 11 | 3.4 | 4.5 | 17 | 11 |
SIWT | 3.7 | 6.2 | 12 | 11 | 3.8 | 6.3 | 13 | 11 | 4.7 | 4.7 | 12 | 11 |
SImode | 3.9 | 6.1 | 11 | 11 | 6.3 | 10 | 12 | 11 | 5.4 | 3.6 | 11 | 11 |
CC | 4.6 | 5.5 | 17 | 14 | 4.5 | 5.3 | 16 | 15 | 5.4 | 4.3 | 18 | 15 |
The between-subject variability (BSV) and the residual error (ResErr) were estimated as variances