If I wanted to know whether consumption of cola is associated with lower bone mineral density in women using the data shown in the accompanying table represent the typical number of cans of soda consumed in a week and the bone mineral density of the femoral neck for a sample of 15 women. The data were collected through a prospective cohort study. How would I find the least-squares regression line treating cola consumption per week as the explanatory variable, then determine for each additional cola consumed per week how much the bone mineral would decrease by g/cm2 on average? How would I then interpret the intercept?
# Colas per Week Bone Mineral # Colas per Week Bone Mineral
Density (g/cm2) Density (g/cm2)
0 0.897 4 0.873
0 0.882 5 0.875
1 0.891 5 0.871
1 0.879 6 0.867
2 0.888 7 0.862
2 0.871 7 0.872
3 0.868 8 0.865
3 0.876