. 2022 Mar 9;24(3):386. doi: 10.3390/e24030386

Table A9.

Triple of simulated prediction coverage rates averaged over the five different covariance structures for the linear model and $r = 10 %$ missing rates. The triple covers the sample sizes $(n_{1}; n_{2}; n_{3}) = (100, 500, 1000)$ using a significance level of $α = 0.05$ .

Coverage Rate for the Linear Model with r = 10% Missings
Imputation Method	$P I_{n, e m p Q}$	$P I_{n, R e s V a r}$	$P I_{n, w e i g h t e d}$
missForest	$(0.9398; 0.9544; 0.9542)$	$(0.9538; 0.9574; 0.9564)$	$(0.9402; 0.9370; 0.9340)$
mice_pmm	$(0.9376; 0.9514; 0.9584)$	$(0.9526; 0.9548; 0.9598)$	$(0.9372; 0.9356; 0.9388)$
mice_norm	$(0.9390; 0.9574; 0.9558)$	$(0.9490; 0.9590; 0.9564)$	$(0.9360; 0.9396; 0.9372)$
mice_rf	$(0.9390; 0.9598; 0.9552)$	$(0.9534; 0.9628; 0.9564)$	$(0.9368; 0.9416; 0.9360)$
gbm	$(0.9392; 0.9550; 0.9518)$	$(0.9498; 0.9568; 0.9536)$	$(0.9370; 0.9368; 0.9298)$
xgboost	$(0.9356; 0.9486; 0.9560)$	$(0.9524; 0.9504; 0.9556)$	$(0.9356; 0.9298; 0.9358)$
Fully observed	$(0.9370; 0.9468; 0.9522)$	$(0.9492; 0.9522; 0.9526)$	$(0.9362; 0.9288; 0.9312)$