SOC 201 Chapter 5: SOC 201 Chapter : Chapter 5.12
Correlation Versus Causation
-One of the traps that researchers (and others!) can fall into is that of confusing
correlation (a measure of association) with causation.
-Bottom line:
-Just because two things are associated does not mean that one of them
causes the other.
-Before we conclude that there is a causal relationship between variables, we
should ask these questions:
1. Is there an association between the variables?
2. Does the variable we suspect is a “cause” occur before the variable we
suspect is an “effect”? (In the Western world, we believe that causes must
occur before effects.)
3. Is there something else that might be influencing both variables?
-For example, suppose research shows that there is a strong association between
ice-cream sales and deaths by drowning:
-As icecream sales go up, so too does the rate of death by drowning.
-Does it make sense to conclude that eating ice cream causes drowning?
1. There is an association between sales of ice cream and drowning
rates.
2. The sales of ice cream seem to go up before drowning rates do.
3. Another factor explains both: Increase in outside temperatures.
-In other words, when it gets hot, more people might cool off by eating ice cream
and by swimming; as the number of people swimming increases the so, too, does
the likelihood of more drownings.
-Recently, Bob Kingsbury, a state legislator from New Hampshire announced that
his research showed that going to kindergarten made children more likely to grow
up and commit crimes:
-The sources I have is [sic] I went to the [state] Department of Education
and got a list of kindergartens and I went to the safety department and got
the crime report. . . .
-In general, the towns with a kindergarten have 400 percent more crime
than other towns in the same county.
