Table A8.

Monte-Carlo mean of the $MSE$ for the Airfoil Dataset summarizing the same information as in Figure 2 Using the XGBoost prediction method.

Mean Monte-Carlo $\mathit{MSE}$ of the Airfoil Dataset Using XGBoost
Prediction Method	$r=10\%$	$r=20\%$	$r=30\%$	$r=40\%$	$r=50\%$	$r=60\%$	$r=80\%$
missForest	$10.342$	$19.538$	$29.366$	$49.054$	$46.262$	$64.705$	$61.934$
mice_pmm	$17.886$	$31.541$	$42.823$	$52.425$	$60.276$	$66.325$	$74.428$
mice_norm	$12.910$	$22.596$	$31.275$	$39.078$	$45.623$	$50.780$	$58.684$
mice_rf	$19.303$	$33.487$	$44.539$	$53.246$	$59.839$	$64.895$	$71.973$
gbm	$9.705$	$18.905$	$28.625$	$37.793$	$45.518$	$50.977$	$53.598$
xgboost	$10.383$	$20.300$	$31.008$	$46.056$	$48.145$	$60.292$	$59.109$
Fully observed	$1.691$