3. As a class, build a predictive model. Everyone in the class should write his or her weight, height, and gender on a piece of paper (no names please!). If the sample is too small (you need about 20–30 students), add more students from another class.

a. Create a regression (causal) model for height versus weight for the whole class and one for each gender.

If possible, use a statistical package (e.g., SPSS) and a spreadsheet (e.g., Excel) and compare their ease of use. Produce a scatter plot of the three sets of data.

b. Based on your plots and regressions, do the relationships appear to be linear? How accurate were the models (e.g., how close to 1 is the value of R2)?

c. Does weight cause height, does height cause weight, or does neither really cause the other? Explain.

d. How can a regression model like this be used in building or aircraft design? Diet? Food selection? A longitudinal study (e.g., over 50 years) to determine whether students are getting heavier and not taller or vice versa?