PROBLEMS:
1. A study of young children found that those with more body fat tended to have more "controlling" mothers; the San Francisco Chronicle (november 9,
1994) concluded that "Parents of Fat Kids Should Lighten Up."
    a) Was this an observational study or a randomized controlled experiment?
    b) Did the study find an association between mother's behavior and her child's level of body fat?
    c) If controlling behavior by the mother causes children to eat more, would that explain an association between controlling behavior by the mother and her
child's level of body fat?
    d) Suppose there is a gene which causes obesity.  Would that explain the association?
    e) Can you think of another way to explain the association?
    f) Do the data support the Chronicle's advice on child-rearing?
Discuss each briefly.

2. Can people tell the difference between Coke and Pepsi?  Design an experiment to find out.  Explain why your design is a good one.  You should address
the issues of a) representativeness, b) bias c) confounding factors.
WARNING: This is a good problem to discuss in class. Be Prepared!

3. p. 728, number 6
4. p. 729, number 8 (under Section 10.2 "additional exercises).
5. p. 729, number 7 (under Chapter 10 Review Exercises)

6. Download the Old Faithful Data into your favorite Statistics software package.  If you are using DataDesk/ActivStats, then that data is part of the package.
We'll investigate the nature of the time between eruptions of Old Faithful geyser.
a) Make a histogram of the "interval" variable.  Describe it in words.
b) Suppose you were a Park Ranger and a tourist asked you how long it would be until the next eruption.  What would you say?
c) Change the bin-widths of your histogram to make them wider and smaller.  Which width do you prefer?  Why?

There is some information about the software packages you might use over here.