Skip to main content
. Author manuscript; available in PMC: 2022 Nov 1.
Published in final edited form as: Addict Behav. 2021 Jul 15;122:107052. doi: 10.1016/j.addbeh.2021.107052

Table 2.

Final model of time invariant and time varying co-variates on changes in alcohol use and binge drinking among veterans.

Days of alcohol use Days of binge drinking
IRR [95% CI] IRR [95% CI]
Time invariant co-variates Intercept Slope Intercept Slope
Control variables
 Age 1.01 [1.00, 1.02] 1.00 [0.99, 1.02] 1.00 [0.99, 1.01] 0.99 [0.97, 1.02]
 Sex (female) 1.90 [1.76, 2.04] 1.00 [0.99, 1.01] 2.05 [1.87, 2.23] 1.00 [0.98, 1.02]
 Race/ethnicity (racial/ethnic minority) 0.80 [0.73, 0.88] 1.02 [1.01, 1.03] 0.57 [0.50, 0.65] 1.04 [1.02, 1.05]
 Combat severity 1.04 [1.02, 1.05] 0.99 [0.97, 1.00] 1.04 [1.02, 1.05] 0.99 [0.98, 1.00]
 Adverse childhood experiences 1.00 [0.98, 1.2] 1.03 [1.02, 1.04] 1.05 [1.03, 1.07] 1.00 [1.00, 1.01]
Mental health
 PTSD positive screen 1.09 [1.01, 1.17] 1.02 [1.01, 1.04] 1.24 [1.13, 1.36] 1.00 [0.99, 1.01]
Time varying covariates B [95% CI] B [95% CI]
Negative reactions to COVID-19
 Time 2 0.29 [0.23, 0.35] 0.39 [.32, .46]
 Time 3 0.10 [0.04, 0.16] 0.39 [.32, .46]
 Time 4 - -
Loneliness
 Time 2 −0.02 [−0.016, −0.012] −.004 [−.007, −.002]
 Time 3 −0.01 [−0.012, −0.006] −0.01 [−0.01, −0.005]
 Time 4 −0.01 [−0.01, −0.006] .01 [.007, .02]
Economic hardship
 Time 2 0.004 [−0.03, 0.04] .12 [.04, .19]
 Time 3 0.004 [−0.03, 0.04] .03 [−.06, .12]
 Time 4 0.004 [−0.03, 0.04] .11 [0.01, 0.21]
Growth parameters IRR [95% CI] IRR [95% CI]
 Intercept 21.8 [19.0, 25.1] 10.2 [9.46, 12.4]
 Slope 0.99 [0.97, 1.01] 0.88 [0.86, 0.90]
Residual Variance B [95% CI]
 Intercept 0.07 [0.05, 0.09] 0.10 [0.08, 0.12]
 Slope 0.05 [0.03, 0.08] 0.02 [−0.03, 0.04]
Model fit criteria
 AIC 20629.113 14317.311
 BIC 20744.741 14437.757
 aBIC 20668.521 14358.360

Note: bold indicates confidence interval does not include 0 or 1.

AIC = Akaike information criteria; BIC = Bayesian information criteria; aBIC = sample size adjusted Bayesian information criteria. Effects of time invariant co-variates are represented by Incident Rate Ratios (IRR), which is the exponentiated value of the log mean effect. Effects of the time varying co-variates are represented by traditional beta (B) coefficients, and represent the effect of the time varying co-variate on the contemporaneous outcome above the underlying growth model.