. Author manuscript; available in PMC: 2015 Jul 20.

Published in final edited form as: Stat Med. 2014 Mar 5;33(16):2797–2813. doi: 10.1002/sim.6123

Table 2.

Ever smoking effect on CCA IMT from inverse-probability-weighting (IPW) estimation with five strategies for computing the propensity scores

Strategies

Δ̂

\sqrt{\hat{V} (\hat{Δ})}

95% CI^*

1: Full^**

45.50

28.60

(−10.56, 101.55)

2: MA with α^X^***

49.71

31.25

(−11.54, 110.97)

3: BAC with α^X

49.97

31.28

(−11.34, 111.29)

4: MA with α^Y

65.30

24.02

(18.22, 112.39)

5: BAC with α^Y

46.16

28.75

(−10.20, 102.53)

Δ̂: ever smoking effect estimate (μm); $\sqrt{\hat{V} (\hat{Δ})}$ : associated standard error;

( $\hat{Δ} \pm 1.96 \sqrt{\hat{V} (\hat{Δ})}$ );

^**

all covariates used for computing the propensity scores.

^***

For strategies 2–5, the labels refer to the technique (model averaging (MA) or BAC) and model (α^X or α^Y) used for the calculation of the propensity scores.