Table 2.
Negative binomial regression on number of barriers to treatment in Mexico, 2011
| Variable | IRR | SE | p | 95% C.I. |
|---|---|---|---|---|
| Traveling to U.S.a |
0.992 |
0.164 |
0.961 |
0.717, 1.373 |
| Transnationala |
1.015 |
0.143 |
0.917 |
0.770, 1.337 |
| Drug dependence |
1.937 |
0.249 |
0.000 |
1.504, 2.494 |
| Traveling to U.S. x femaleb |
0.311 |
0.115 |
0.002 |
0.150, 0.643 |
| Transnational x femaleb |
0.656 |
0.172 |
0.109 |
0.392, 1.099 |
| Drug dependence x femaleb |
1.084 |
0.610 |
0.886 |
0.358, 3.276 |
| Female |
1.014 |
0.173 |
0.935 |
0.725, 1.417 |
| Age |
0.993 |
0.005 |
0.875 |
0.983, 1.003 |
| Less than High school |
1.085 |
0.155 |
0.986 |
0.818, 1.437 |
|
Region
c
|
|
|
|
|
| North central |
1.657 |
0.381 |
0.028 |
1.055, 2.602 |
| Northwest |
1.618 |
0.383 |
0.043 |
1.016, 2.576 |
| Northeast |
2.522 |
0.557 |
0.000 |
1.634, 3.892 |
| West |
3.364 |
0.794 |
0.000 |
2.116, 5.348 |
| Central |
1.989 |
0.409 |
0.001 |
1.327, 2.980 |
| South central |
2.386 |
0.625 |
0.001 |
1.426, 3.992 |
| South | 2.008 | 0.667 | 0.036 | 1.046, 3.857 |
Note. CI, confidence interval; IRR, incidence rate ratio; SE, standard error. IRRs can be interpreted as the estimated rate ratio for a 1-unit increase in the independent variable, given the other variables are held constant in the model. For example, compared to non-dependent, individuals reporting drug dependence are associated with an increased ratio for number of barriers of IRR = 1.937, while holding all other variables in the model constant. The corresponding p-value is less than 0.001.
aMexicans who have not visited the United States was reference category.
bInteraction term.
cMexico City was reference category.
*p < .05, **p < .01, ***p < .001.