You have been contacted by a hospital to analyze a data set on the
percentage of body fat (a measure of health) for a sample of 252 men.
Body fat is estimated through an underwater weighing technique. However,
your medical colleagues would like to come up with a way to estimate
body fat for men using a simpler method, based on easy to obtain body
measurements and information. The variables that are available to you
are described below. The data file can
be accessed through our course webpage:
http://www.math.mun.ca/~sneddon/st6590
If you plan on using Splus to do your data analysis, you can access the data by typing:
attach("/users/math/faculty/sneddon/DATA")
The data is in contained in bodyfat.dat
Your goal is to develop a model that estimates the percentage of body fat from some of the available explanatory variables (Are there some variables that it would be inappropriate for you to use in your model?). Since there are 2 measures of body fat provided, you can begin by working with either of the 2 measures in developing your model.
In developing your model, watch out for any unusual cases that may exist in the data.
Data Description:
The columns of the dataset contain the following variables. Each row corresponds to a different subject: