Table 4.
Hierarchical linear modeling results for Alcoholics Anonymous (AA) attendance predicting anger for the outpatient and aftercare samplesa
| Variable | b [95% CI] | t(df) | P |
| Outpatient sample | |||
| Baseline anger | 0.5700 [0.5059, 0.6341] | 17.48 (403) | <.0001 |
| Lagged AA attendance | −0.0023 [−0.0225, 0.0179] | −0.23 (192) | .8217 |
| Lagged AA Attendance × Anger | 0.0008 [−0.0012, 0.0028] | 0.81 (347) | .4186 |
| Lagged AA Attendance x Time | −0.0126 [−0.0403, 0.0152] | −0.89 (213) | .3726 |
| Aftercare sample | |||
| Baseline anger | 0.6098 [0.5393, 0.6803] | 17.03 (270) | <.0001 |
| Lagged AA attendance | −0.0028 [−0.0200, 0.0138] | −0.34 (226) | .7369 |
| Lagged AA Attendance × Anger | 0.0000 [−0.0013, 0.0014] | 0.05 (287) | .9611 |
| Lagged AA Attendance × Time | 0.0028 [−0.0174, 0.0230] | 0.27 (458) | .7858 |
a
Control and other variables included in these tested models but not shown above include age, gender, ethnicity, marital status, employment status, number of prior alcohol treatments, treatment assignment, treatment site, Gender x Time, and AA Attendance x Intake Level of Dependent Variable.