elhamyali / health-survey-data-analysis-of-bmi Goto Github PK

In this analysis, I analyzed survey data of 20,000 people sampled from the United States to explore health behaviors associated with lower Body Mass Index (BMI), a standardized measure of healthy weight and obesity.

• What is the association between physical activity and BMI among people in the United States? Is BMI lower in physically active people?
• What is the relationship between smoking and physical activity? If someone smokes, is he or she more or less likely to be physically active? Are smokers more likely to have higher or lower BMI?

This analysis uses the National Health and Nutrition Examination Survey (NHANES) data from ~20,000 participants surveyed in years 2009-2012 found in the NHANES R package.

Survey weighted multiple and logistic regression in R

1. Whites are undersampled and have higher weights. While Black, Mexican, Hispanic people are oversampled and have lower weights since each sampled person in these minority groups represents fewer US people.

2. The average BMI in the US adult population is 28.73.

3. The distribution of BMI differ between people who are physically active versus those who are not physically active. We can see this association when we compare BMI with a boxplot and formally test for a difference in mean BMI.

4. If someone smokes, they are less likely to be physically active.

5. Oddly, people who smoke are less likely to be physically active and have a higher BMI on average. And people who are physically active have a lower BMI on average.

6. People who are physically active tend to have lower BMI no matter their smoking status, and this is true even if they didn't answer the question. Smokers have lower BMI in general. The difference in BMI comparing physically active people to non-physically active people is slightly smaller in smokers than in non-smokers.

7. The association of physical activity with BMI could vary by smoking status. The interaction between physical activity and smoking has a small p-value, which suggests the association does vary by smoking status. The difference between physically active and non-physically active people is larger in magnitude in the non-smoker population.

8. Physically active people tend to have lower BMI, as do smokers, despite having similar effect sizes.