If a regression analysis was to be completed on BMI: BMI is the Dependent variable. I would consider evaluating Activity level and High caloric diet as independent variables. These are two variables that are closely associated with BMI values. By studying the BMI of individuals who have a sedentary lifestyle against those with a moderate to highly active lifestyle we might be able to predict a trend in a BMI level. Same goes with individuals who have a high caloric intake versus an individual who has a low caloric intake. The regression analysis will help identify the relationship those two variables have to BMI. We then would have to study the data to see if it is statistically significant. We can use the correlation coefficient as our statistic. Holmes (2017) defines correlation coefficient as “the mathematical statistic for a population that provides us with a measurement of strength of a linear relationship between the two variables (p.561)
In a study done by Olajide (2011) a regression analysis was done on obesity (Dependent Variable). The independent variable studied was depravity. They considered environmental factors associated with degree of depravity may influence obesity rates and obesity related diseases. They found that in the least “depraved” group improving their dietary intake helped reduced obesity related illnesses. And in the most “depraved” group an increase in physical activity was the factor that most affected the probability of obesity related diseases (Olajide, 2011). They were able to conclude that interventions targeted to specific environmental factors would have an impact on obesity related diseases. The article looks at levels of physical activity and nutrition as having a correlation to obesity but not necessarily mean that they are the sole cause of obesity.
Holmes, A., Illowsky, B., & Dean, S. (2017). Introductory business statistics. OpenStax. https://openstax.org/details/books/introductory-business-statistics