Math105 A, Intro Stats                                      Name(s)                                                      :
Central College, Fall 2006
Activity 3
Televisions and Life Expectancy

The following table provides information on Y = Life Expectancies (in years) for a sample of 22 countries.  It also lists X = the Number of People Per Television Set in each country.
 
Country Life
Expectancy		 People
per TV		 Country Life
Expectancy		 People
per TV
Angola 44 200 Mexico 72 6.6
Australia 76.5 2 Morocco 64.5 21
Cambodia 49.5 177 Pakistan 56.5 73
Canada 76.5 1.7 Russia 69 3.2
China 70 8 South Africa 64 11
Egypt 60.5 15 Sri Lanka 71.5 28
France 78 2.6 Uganda 51 191
Haiti 53.5 234 United Kingdom 76 3
Iraq 67 18 United States 75.5 1.3
Japan 79 1.8 Vietnam 65 29
Madagascar 52.5 92 Yemen 50 38
  1. Which of the countries listed above has the fewest people per television set?  How many people is that? Which has the most people per television set?  How many people is that?



     
  2. Create a scatterplot of X = people per television set and Y = life expectancy.  Make a rough, but well labeled copy of this scatterplot below. Does there appear to be an association between the two variables?  If so, describe the association (is it strong, weak, positive, negative).
     


     
     
     




     

     
     
     

  3. Calculate the correlation between life expectancy and  people per television set.
     


     
     
     
     

  4. Since the association is so strongly negative, one might conclude that simply sending television sets to the countries with lower life expectancies would cause their inhabitants to live longer.  Comment on this argument; do you agree or disagree with it?  Explain.





     
     
     
     

  5. If two variables have a correlation close to +1 or -1, indicating a strong linear relationship between them, does it follow that there must be a cause-and-effect relationship between them?  Explain.
     




     
     
     

    This example illustrates the very important distinction between association and causation.  Two variables may be strongly associated (as measured by correlation) without a cause-and-effect relationship existing between them.  Often the explanation is that both variables are related to a third variable not being measured; this variable is often called a lurking or confounding variable.
     

  6. In the case of life expectancy and televisions sets, suggest a lurking variable that is associated with both a country's life expectancy and with the prevalence of television sets in the country.





  7. Read the attached article "Correlation, causation confused."