If a regression analysis was to be completed on body mass index (BMI), what could be an independent variable in that analysis? Why? If we could, what...

A logical
independent variable to use in regression analysis on BMI might be a measure for class, such as
annual family income. As class has an intense affect on people's ability to access healthy food,
it can easily be tied to various health outcomes, such as BMI. Other independent variables might
include number of home-cooked meals eaten per week versus fast food versus restaurants, a
variable to measure time spent working out, and possibly a dummy variable or some other way of
indicating whether respondents are following an intentional diet.

Examining
the R^2 value from the regression analysis would show the extent to which the model explained
BMI among respondents.

It should be noted that BMI is a highly controversial
measure. Many challenge the extent to which it is backed by any real data and argue that it
simply social prejudice against heavier people in the language of science. It is commonly argued
that it is a flawed measure that fails to take into account the natural variance in body types /
builds and furthers already unhealthy cultural attitudes that idealize thinness even when the
steps necessary to take it are unhealthy. This points to a general lesson about statistics:
they're only as useful as the values they measure, and without a critical understanding of what
you're measuring, you risk unhelpful interpretations of your data.