1.  Consider the personal data collected in class.  We're going to focus on three variables: commute time, hours of TV
watched, and weight.  For each of these variables, do the following:
    a) Classify as quantitative/qualitative, continuous/discrete.
    b) Without looking at any graphics, describe the shape you would expect for the distribution of this variable:  symmetric,
skewed?  Explain why.
    c) What's a typical value for this variable for students in 110A?
    d) Make a histogram or stem and leaf plot of these variables. Describe the distribution.  Are there outliers? Gaps? What is
the shape?

2.  People with short commutes have more time to watch TV.  Do you see any evidence that the length of the commute is
related to the amount of TV watched?  What is this evidence?  Can you give an explanation for your conclusion?

3. Are weight and the amount of TV watched related?  This is an ambitious question, so lets make it simpler: is there
evidence that the hours of TV watched and weight are related in  our data set?  Use any means you like to answer this
question, but be sure to support your answer with the necessary graphs or numbers.

4. Is there a relationship between height and income?  For men age 25-34, a large (tens of thousand of people) national study provided the following
summary statistics:
Average height approximately 70 inches, with SD of 3 inches
Average income $29,800 with SD of $14400 .
The correlation between height and income was r = 0.2

a) What is the regression equation for predicting income from height?
b) Graph it.
c) Generally, people who are one inch taller make how much more?
d) What's the average income of men who are 56 inches tall?
e) True or false and explain: These data show that if you wear elevator shoes, you can make more money.

5.  Let's examine the relation between TV watching and weight in our data in more detail.  Does the amount of TV watched predict
weight?
a) Plot weight (y axis) vs. TV time.  (Use the classdata.)
b) What is the correlation?  (If you click on the small arrow in the upper-left corner of the scatterplot, you will get a menu.  Choose the "correlations" option.)
c) Find the regression equation. (Again, use the menu on the upper left corner of the scatterplot.)
d) Interpret the regression equation.
e) Look at the residuals; do you see any patterns that suggest the assumptions might not hold? (See the DataDesk Hints.)
f) Are men and women different with respect to this relationship?  There are several ways of exploring this.  See DataDesk Hints  for some hints.  Also, you might want to view the ActivStats tutorial at:  7-2, "Case Study: Fuel Efficiency in Cars".   This is an excellent tutorial for using DataDesk.    Does the women's scatterplot look different than the men's?   What about the regression lines?