Table 5.
The MIMIC model of the latent factor score of the 10 criteria | Crude regression coefficient (SE)a | Adjusted regression coefficient (SE)b | Adjusted regression coefficient (SE): without DIFc | Adjusted regression coefficient (SE): with DIFd |
---|---|---|---|---|
Gender | ||||
Female versus male | −0.22 (0.04)*** | — | −0.17 (0.06)** | −0.20 (0.06)*** |
Age in years | ||||
18–25 versus ≥ 35 years | 0.50 (0.06)*** | — | 0.53 (0.07)*** | 0.53 (0.07)*** |
26–34 versus ≥ 35 years | 0.37 (0.08)*** | — | 0.37 (0.09)*** | 0.38 (0.09)*** |
Race/ethnicity | ||||
African‐American versus White | 0.19 (0.06)*** | — | 0.16 (0.07)* | 0.16 (0.08)* |
Hispanic versus White | 0.21 (0.07)*** | — | 0.15 (0.07)* | 0.24 (0.08)** |
Other versus White | −0.09 (0.11) | — | −0.01 (0.11) | 0.03 (0.12) |
Education | ||||
< High school versus ≥ college | 0.37 (0.06)*** | — | 0.01 (0.06) | 0.01 (0.06) |
High school versus ≥ college | 0.28 (0.05)*** | — | 0.12 (0.05)* | 0.12 (0.05)* |
Family income | ||||
< $40 K versus ≥ $75 K | 0.24 (0.07)*** | — | 0.02 (0.08) | 0.02 (0.08) |
$40 K–$74,999 versus ≥ $75 K | 0.11 (0.07) | — | −0.02 (0.07) | −0.02 (0.07) |
Weekly marijuana use | ||||
Yes versus no | 1.17 (0.05)*** | 1.15 (0.05)*** | 0.14 (0.05)** | 0.14 (0.05)** |
First marijuana use ≤ 15 years | ||||
Yes versus no | 0.39 (0.04)*** | 0.37 (0.04)*** | 1.18 (0.06)*** | 1.19 (0.06)*** |
Substance abuse treatment | ||||
Yes versus no | 0.56 (0.08)*** | 0.55 (0.07)*** | 0.44 (0.06)*** | 0.45 (0.06)*** |
Serious psychological distress | ||||
Yes versus no | 0.41 (0.04)*** | 0.46 (0.05)*** | 0.37 (0.07)*** | 0.37 (0.07)*** |
Poor/fair self‐rated health | ||||
Yes versus no | 0.26 (0.08)*** | 0.29 (0.08)** | 0.15 (0.09) | 0.16 (0.09) |
Major depression, past year | ||||
Yes versus no | 0.24 (0.05)*** | 0.30 (0.05)*** | 0.03 (0.07) | 0.03 (0.07) |
Other substance use disorders, past year | ||||
Yes versus no | 0.41 (0.04)*** | 0.37 (0.04)*** | 0.24 (0.04)*** | 0.24 (0.04)*** |
Note: Sample sizes are unweighted; all other results are weighted figures. DIF, differential item functioning; SE, standard error.
The unadjusted MIMIC model included one variable listed in that row.
The adjusted model included one variable listed in that row, adjusting for gender, age, race/ethnicity, education, and family income.
The adjusted model included all variables listed in the first column.
The adjusted model included all variables listed in the first column and DIF variables (Figure 3).
p < 0.05;
p < 0.01;
p < 0.001.