. Author manuscript; available in PMC: 2017 Sep 10.

Published in final edited form as: Stat Med. 2016 Mar 21;35(20):3537–3548. doi: 10.1002/sim.6943

Table 5.

Analysis Results for Post-Surgery Pain Data

Method	α̂_Z	SE(α̂_Z)	95% CI	p-value
t-test^a	−0.007	0.061	(−0.127,0.113)	0.909
Multiple regression^b	0.013	0.056	(−0.097,0.123)	0.816
PS covariate adjustment^c	0.015	0.063	(−0.108,0.138)	0.812
PS covariate adjustment^d	0.015	0.055	(−0.093,0.123)	0.785
PS covariate adjustment^e	0.015	0.055	(−0.093,0.123)	0.785

Two sample t-test without adjusting for any confounding factors

Multiple regression model including all observed covariates

$Variance estimate = {\hat{Var}}_{C} ({\hat{α}}_{Z})$

$Variance estimate = {\hat{Var}}_{B} ({\hat{α}}_{Z})$ with total 500 rounds of bootstrapping

$Variance estimate = {\hat{Var}}_{A} ({\hat{α}}_{Z})$