How to respond to this post: Your reporting approach for both logistic and linear regression were equally solid. The regression coefficients, R-squared values, and significance levels are central to interpreting these models. I would also add that presenting standardized coefficients (beta values) can be especially helpful when comparing the relative influence of predictors measured on different scales. In public health practice, this assists in prioritizing interventions by quantifying which factors exert the greatest influence on outcomes like BMI (Schober & Vetter, 2020). Lastly, I appreciate your insight into how each analysis type serves public health differently. Logistic regression is often used to classify individuals at risk (predicting high BMI status), whereas linear regression helps quantify how much a variable like cholesterol shifts BMI levels on a continuous scale. Together, these approaches offer both breadth and depth to epidemiologic analyses and intervention design. While one tells us who is at risk, and the other tells us how much a risk factor impacts an outcome