Logistic regression models comparing students that use a given source with those that do not
| Source of cigarettes | Predictor | Odds ratio | 95% CI |
|---|---|---|---|
| “My friends give them to me.”2-150 | Ethnicity | 1.72 | 1.78–3.43 |
| Gender | 1.54 | 1.19–1.87 | |
| Ethnicity × gender | 0.61 | 0.39–0.96 | |
| “I buy them from a store”2-151 | Ethnicity | 1.72 | 1.30–2.28 |
| Gender | 1.54 | 1.19–2.00 | |
| “I buy them from a vending machine.”2-152 | Ethnicity | 4.31 | 2.99–6.20 |
| Gender | 2.42 | 1.63–3.58 | |
| “I take cigarettes without any adults knowing.”2-153 | Ethnicity Gender | 1.04 0.61 | 0.78–1.40 0.48−0.79 |
n = 1916. The dependent variables are coded so that use of a source = 1 and its non-use = 0. Ethnicity is coded with white students = 1 and black students = 0. Gender is coded with males = 1 and females = 0.
↵2-150 Model χ2[3] = 44.82, p<0.001.
↵2-151 Model χ2[2] = 25.80, p<0.001.
↵2-152 Model χ2[2] = 84.04, p<0.001.
↵2-153 Model χ2[2] = 15.00, p<0.001.
CI = confidence intervals.