Skip to main content

Table 5 Results From Fitting Complete-Case and Multiple Imputation Models to Data from the Long Island Breast Cancer Study Project [19] Assessing the Effect of a Gene-Environment Interaction where m = 10

From: The use of complete-case and multiple imputation-based analyses in molecular epidemiology studies that assess interaction effects

Genotype/Alcohol Status ORa CC
N = 2,063
(95% CI)
ORa MI
N = 3,064;m =10
(95% CI)
% Change in βCoefficient
Slow-Intermediate/Non-alcohol consumer 1.00 1.00  
Fast/Non-alcohol consumer 1.18
(0.88, 1.58)
1.14
(0.88, 1.48)
22.11%
Slow-Intermediate/< 15 grams 1.16
(0.89, 1.50)
1.11
(0.89, 1.39)
25.38%
Fast/< 15 grams 0.92
(0.69, 1.23)
0.95
(0.75, 1.20)
30.89%
Slow-Intermediate/15-30 grams 1.49
(0.99, 2.25)
1.27
(0.89, 1.82)
40.23%
Fast/15-30 grams 2.32
(1.35, 4.01)
1.68
(1.03, 2.75)
38.68%
Slow-Intermediate/30+ grams 0.72
(0.43, 1.21)
0.77
(0.49, 1.19)
17.40%
Fast/30+ grams 0.98
(0.52, 1.87)
0.86
(0.47, 1.56)
> 100%
  1. CC = Complete Case; CI = Confidence Interval; MI = Multiple Imputation;OR = Odds Ratio
  2. aEstimates are adjusted for age at diagnosis, education, race, caloric intake, smoking status and body mass index