11/5/2012
1
Chapter 5
Correlation and Causation:
Birth Control by the Toaster Method
Toasters & Birth Control
•Study of factors related to the use of contraceptives
•Collected data on a wide range of behavioral and environmental
variables
•Variable most strongly related to contraceptive use was the
number of electrical appliances in the home.
•So . . . Should we start passing out free toasters in high schools?
No, because. . .
•It is not the strength but the nature of the
relationship that is relevant.
•Although there is correlation, toasters don’t cause
people to use contraceptives.
•Two variables may be associated without having a
causal relationship.
•There may be a mediating variable/third variable
involved. (In this case Socioeconomic Status)
The Third Variable Problem:
Goldberger and Pellagra
•1990s disease in the South
•Evidence pointed towards causal relationship of inside
plumbing/good sewarage vs. bad sewarage
•Goldberger thought the correlation to came to be, because families
with good plumbing were likely to be economically advantaged.
•He thought their economic status could be reflected in their diets
•His causal inference was a poor/low protein diet let to Pellagra
