Page 310 - Statistics for Dummies

294
Part V: Statistical Studies and the Hunt for a Meaningful Relationship
However, if you made a scatterplot and examined the correlation between ice
cream consumption versus murder rates in New York City, you would also
see a strong linear relationship (this one is uphill). Yet no one would claim
that more ice cream consumption causes more murders to occur.
What’s going on here? In the first case, the data were collected through a
well-controlled medical experiment, which minimizes the influence of other
factors that may affect blood pressure. In the second example, the data were
based just on observation, and no other factors were examined. Researchers
subsequently found out that this strong relationship exists because increases
in murder rates and ice cream sales are both related to increases in tempera-
ture. Temperature in this case is called a confounding variable; it affects both
X and Y but was not included in the study (see Chapter 17).
Whether two variables are found to be causally associated depends on how the
study was conducted. I’ve seen many instances in which people try to claim
cause-and-effect relationships just by looking at scatterplots or correlations.
Why would they do this? Because they want to believe it (in other words for
them it’s “believing is seeing,” rather than the other way around). Beware of this
tactic. In order to establish cause and effect, you need to have a well-designed
experiment or a boatload of observational studies. If someone is trying to estab-
lish a cause-and-effect relationship by showing a chart or graph, dig deeper
to find out how the study was designed and how the data were collected, and
evaluate the study appropriately using the criteria outlined in Chapter 17.
The need for a well-designed experiment in order to claim cause and effect
is often ignored by some researchers and members of the media, who give
us headlines such as “Doctors can lower malpractice lawsuits by spending
more time with patients.” In reality, it was found that doctors who have fewer
lawsuits are the type who spend a lot of time with patients. But that doesn’t
mean taking a bad doctor and having him spend more time with his patients
will reduce his malpractice suits; in fact, spending more time with them may
create even more problems.

3/25/11 8:13 PM
26_9780470911082-ch18.indd 294
26_9780470911082-ch18.indd 294 3/25/11 8:13 PM