Page 282 - Statistics for Dummies

266
Part V: Statistical Studies and the Hunt for a Meaningful Relationship
standing out in big, bright, happy, colorful visuals. Then look at the back of
the page and you see it’s entirely filled in black with words written in 3-point
font. Embedded somewhere on that page, you can find one or more tiny
tables that show the number and nature of side effects reported by each
treatment group (subjects who received an actual treatment) as well as the
control group (subjects who were administered a placebo).
If the control group is on a placebo, you may expect the subjects not to report
any side effects, but you would be wrong. If you are taking a pill, you know it
could be an actual drug, and you are being asked whether or not you’re expe-
riencing side effects, you might be surprised at what your response would be.
If you don’t take the placebo effect into account, you have to believe that any
side effects (or positive results) reported are actually due to the drug. This
gives an artificially high number of reported side effects because at least some
of those reports are likely due to the placebo effect and not to the drug itself.
If you have a control group to compare with, you can subtract the percentage
of people in the control group who reported the side effects from the per-
centage of people in the treatment group that reported the side effects, and
examine the magnitude of the numbers that remain. You’re in essence look-
ing at the net number of reported side effects due to the drug, rather than the
gross number of side effects, some of which are due to the placebo effect.
The placebo effect has been shown to be real. If you want to be fair about exam-
ining the reported side effects (or positive reactions) of a treatment, you have
to also take into account the side effects (or positive reactions) that the control
group reports — those reactions that are due to the placebo effect only.
Standard treatments
In some situations, such as when the subjects have very serious diseases,
offering a fake treatment as an option may be unethical. One famous example
of a breech in ethics occurred in 1997. The U.S. government was harshly
criticized for financing an HIV study that examined new dosage levels of AZT,
a drug known at that time to cut the risk of HIV transmission from pregnant
mothers to their babies by two-thirds. This particular study, in which 12,000
pregnant women with HIV in Africa, Thailand, and the Dominican Republic
participated, had a deadly design. Researchers gave half of the women vari-
ous dosages of AZT, but the other half of the women received sugar pills. Of
course, had the U.S. government realized that a placebo was being given to
half of the subjects, it wouldn’t have supported the HIV study. It’s not ethical
to give a fake treatment to anyone with a deadly disease for which a standard
treatment is available (in this case, the standard dosage of AZT).
When ethical reasons bar the use of fake treatments, the new treatment is
compared to at least one existing or standard treatment that is known to be
an effective treatment. After researchers have enough data to see that one of
the treatments is working better than the other, they generally stop the exper-
iment and put everyone on the better treatment; again, for ethical reasons.

3/25/11 8:13 PM
25_9780470911082-ch17.indd 266 3/25/11 8:13 PM
25_9780470911082-ch17.indd 266