Variable | Coefficient | Standard Error |
---|---|---|
Age* | ||
Linear component | 0.0900 | 0.0112 |
Nonlinear component | −0.0276 | 0.0114 |
Diabetes | 0.2333 | 0.0821 |
Regular use of multivitamins | −0.1665 | 0.0568 |
Family history of colon cancer | 0.3159 | 0.0820 |
Years of education* | ||
Linear component | 0.0744 | 0.0204 |
Nonlinear component | −0.0757 | 0.0212 |
Race/ethnicity | ||
Hawaiian | −0.2410 | 0.1284 |
Japanese | 0.0140 | 0.0844 |
Latino | −0.3967 | 0.0977 |
White | −0.3406 | 0.0892 |
Body mass index | ||
Linear component | 0.0075 | 0.0146 |
Nonlinear component | 0.0121 | 0.0177 |
Alcoholic drinks per day | ||
Linear component | −0.0886 | 0.3046 |
Nonlinear component | 0.4092 | 0.7886 |
Regular use of NSAIDs | ||
Yes, not currently | −0.0464 | 0.0731 |
Yes | −0.2370 | 0.0887 |
Pack-years of smoking† | ||
Linear component | 0.0627 | 0.0498 |
Nonlinear component 1 | −1.8515 | 2.1240 |
Nonlinear component 2 | 2.2999 | 2.6795 |
Estrogen use | ||
Yes, not currently | −0.0443 | 0.0719 |
Yes | −0.2450 | 0.0724 |
↵* Continuous variables were modeled using restricted cubic splines with three knots. Therefore, continuous variables contain one coefficient for the linear component (displayed first) and a non-linear component (displayed in the next row and denoted with a single quotation mark).
↵† Unable to obtain a natural spline using 3 knots and therefore restricted cubic splines with 4 knots were used for this variable.
NSAIDS, nonsteroidal anti-inflammatory drugs.