This case study presents an example of using a generalized linear model with a log-linear link to calculate an adjusted risk ratio to be able to assess the association between educational attainment and obesity in a cohort study of American adults. Both risk ratios and odds ratios can be calculated based on cohort study data, and risk ratios are more intuitive for practitioners to interpret. I present tips on how to estimate adjusted risk ratios, including a way to avoid non-convergence of the model. I then explain how to interpret risk ratios. In conclusion, generalized linear models with a log-linear link function can be a useful statistical analytic tool when a risk ratio is possible to calculate and is of greater interest than an odds ratio. [This content is provided in the format of an e-book.]