These results are based on a logistic regression analysis, which measures the effect of one or more independent variables on a dichotomous dependent variable (in this case: diabetic or not diabetic)   This analysis results in odds ratios. For example, the risk of obese people becoming or not becoming a diabetic can be set against the risk for people with normal weight. The analysis automatically corrects for the effects of other variables, in this case age, sex, ethnic origin, education level, and level of wealth. The report includes a table with the outcomes of this analysis.