Skip to main content
. Author manuscript; available in PMC: 2018 Jul 1.
Published in final edited form as: Prev Med. 2017 Jul;100:279–284. doi: 10.1016/j.ypmed.2017.03.023

Table 1.

Negative binomial model of pre-baseline e-cigarette frequency and total cigarettes smoked over time.

Predictor Coefficient Std. Error z p-value IRR (95% ci)
Propensity score 0.07 0.04 1.56 .120 1.07 (0.98, 1.17)
Assessment days 0.10 0.22 4.75 <.001 1.11 (1.06, 1.16)
Sex 0.30 0.36 0.84 .401 1.04 (0.95, 1.14)
Student status -0.32 0.11 -2.77 .006 0.73 (0.58, 0.91)
Time 0.27 0.16 1.69 .091 1.29 (0.94, 1.81)
Time2 -0.11 0.04 -2.65 .008 0.90 (0.83, 0.97)
E-cigarette frequency 0.04 0.02 2.26 .024 1.13 (1.06, 1.21)
E-cigarette frequency × Time 0.03 0.01 2.79 .005 1.16 (1.09, 1.23)