Table 1. Parameter Estimates and with the 95% Bootstrap CIs.
|
Parameters (95% bootstrap CIs) |
||||
|---|---|---|---|---|
| Pmin | Pmax | PD50 | k | |
| Cannabis | 0.02 (0.01, 0.02) | 0.36 (0.27, 0.71) | 11 (6, 33)a | 1.50 (1.07, 2.01) |
| PPR | 0.04 (0.00, 0.05) | 0.38 (0.19, 1.00) | 11 (5, 80)a | 1.81 (0.80, 5.93) |
| Alcohol | 0.01 (0.01, 0.01) | 0.10 (0.06, 0.17) | 4 (3, 10) | 2.48 (1.47, 6.17) |
| Cocaine | 0.05 (0.04, 0.06) | 0.97 (0.46, 1.00) | 18 (9, 27) | 1.82 (1.31, 3.57) |
Abbreviations: CI, confidence interval; PPR, prescription opioid pain reliever.
Data from the United States National Surveys on Drug Use and Health, 2002–2011.
a
As the bootstrap procedure yields non-symmetrical CIs, the upper bound of the PD50 estimate falls outside of the observed range of at most 30 days of continuous drug use before the assessment time. This phenomenon reflects that Pmax upper bound is not always attained within an interval of 30 days.