Table 2:

Results from Scenario 2 (n=5,000 and and $\sim$74% missingness) based on the naïve complete case analysis (CC), the multiple imputation by chained equations approach (MICE), and the proposed sieve inverse probability weighting approach (SIPW).

Analysis		Event 1		Event 2
		${\hat{\beta }}_{11}$	${\hat{\beta }}_{21}$	${\hat{\beta }}_{12}$	${\hat{\beta }}_{22}$
CC	% Bias	−19.870	−20.374	32.168	20.748
	MCSDa	0.045	0.093	0.064	0.122
	ASEb	0.043	0.090	0.063	0.122
	CPc	0.375	0.388	0.279	0.875
MICE	% Bias	−9.884	−11.248	−26.093	−26.087
	MCSDa	0.044	0.083	0.041	0.074
	ASEb	0.057	0.105	0.042	0.076
	CPc	0.931	0.866	0.216	0.647
SIPW	% Bias	0.408	0.256	0.405	−0.656
	MCSDa	0.058	0.118	0.068	0.126
	ASEb	0.056	0.117	0.068	0.125
	CPc	0.937	0.941	0.949	0.950

^aMonte Carlo standard deviation of the estimates. ^bAverage of the standard error estimates. ^cEmpirical coverage probability.