TABLE 2.
Zero-inflated gamma regression models for an expected problem drinker possible self in 8th grade predicting alcohol consumption in 9th grade
| 9th grade alcohol consumption |
||||||||
|---|---|---|---|---|---|---|---|---|
| Predictors | Model 1 | Model 2 | ||||||
|
|
||||||||
| B | SE | 95% CI | p | B | SE | 95% CI | p | |
| Step 1: Predicting NO ALCOHOL CONSUMPTION | ||||||||
|
| ||||||||
| Expected problem drinker possible self | −1.7 | 1.1 | −3.9–0.5 | 0.127 | −1.6 | 1.1 | −3.8–0.6 | 0.164 |
| Family structure | −0.2 | 0.5 | −1.2–0.7 | 0.651 | ||||
| (0=Two-parent, 1=Single-parent) | ||||||||
| Family cohesion | 0.1 | 0.5 | −0.9–1.0 | 0.866 | ||||
| (0=Effective, 1=Ineffective) | ||||||||
| Parental alcohol problems | −0.8 | 0.3 | −1.4–−0.2 | 0.006 | ||||
| Perceived friends’ influence | 0.1 | 0.2 | −0.3–0.5 | 0.592 | ||||
| Gender (0=Boy, 1=Girl) | −0.6 | 0.5 | −1.6–0.3 | 0.201 | ||||
| 8th grade alcohol consumption in the last 12 months | −2.0 | 0.4 | −2.9–−1.2 | <0.001 | −2.0 | 0.5 | −3.0–−1.0 | <0.001 |
|
| ||||||||
| Step 2: Predicting LEVEL OF ALCOHOL CONSUMPTION | ||||||||
|
| ||||||||
| Expected problem drinker possible self | 1.0 | 0.5 | 0.1–2.0 | 0.038 | 0.5 | 0.5 | −0.5–1.5 | 0.294 |
| Family structure | 1.3 | 0.4 | 0.5–2.1 | 0.002 | ||||
| (0=Two-parent, 1=Single-parent) | ||||||||
| Family cohesion | 0.2 | 0.4 | −0.5–1.0 | 0.517 | ||||
| (0=Effective, 1=Ineffective) | ||||||||
| Parental alcohol problems | −0.1 | 0.1 | −0.4–0.1 | 0.375 | ||||
| Perceived friends’ influence | −0.2 | 0.1 | −0.5–0.1 | 0.268 | ||||
| Gender (0=Boy, 1=Girl) | 1.5 | 0.4 | 0.7–2.3 | <0.001 | ||||
| 8th grade alcohol consumption in the last 12 months | 0.1 | 0.1 | −0.0–0.2 | 0.067 | 0.1 | 0.0 | 0.0–0.2 | 0.027 |
|
| ||||||||
| −2 Log Likelihood | 413.4 | 378.5 | ||||||
Note: B = logistic regression coefficient for step 1 and gamma regression coefficient for step 2; SE = standard error; CI = confidence interval