Transcript Lecture 10 - Understanding Experiments

Understanding
Experiments
Lecture 10
Section 3.5
Tues, Sep 19, 2006
Example




Suppose a drug is given to 100 patients suffering
from a particular disease.
After 2 weeks, 90% of the patients have
recovered.
The researchers conclude that the drug was
effective.
What is wrong with this?
Random Allocation





The assignment to the groups should be random
(a randomized design).
The subjects could be numbered 1 – 100.
Then use a random number generator to obtain
50 (distinct) random numbers from 1 – 100.
Those 50 subjects would be assigned to Group
1.
The rest would be assigned to Group 2.
Treatment and Control Groups


Treatment group.
Control group.
Random vs. Nonrandom Allocation



Would it be wrong to allow the individuals
choose whether to be in the treatment group or
the control group?
Would it be wrong for the researchers to decide,
subject by subject, who goes in which group?
Why?
Response Bias

Are the subjects in the treatment group aware of
the purpose of the experiment?


Are the subjects in the control group aware that
they are not receiving the drug?


If so, will they be more likely to report feeling well?
If so, will they be more likely to report feeling ill?
What can we do about this?
Placebos

Placebo.
Placebos
Placebos



Everybody in the treatment group gets is
administered the drug.
Everybody in the treatment group gets the
placebo.
The researchers look for differences in the
groups’ recovery rates.
Blinded Experiments



Of course, the subjects should not know
whether they are receiving the placebo or the
genuine treatment.
This is called a blinded experiment.
Single-blind experiment – The subjects do not
know which group they are in (but the
researchers do).
Experimenter Bias



Experimenter bias – A distortion of the
observations resulting from the experimenter’s
expectations.
This is similar to response bias except that it is
caused by the experimenter, not the subject.
How can we control for experimenter bias?
Double-Blind Experiments


Double-blind experiment – Neither the subjects
nor the researchers know which group is the
control group.
Then how will they ever know whether the drug
was effective?
The Placebo Effect

The placebo effect is when a subject responds to
the “treatment,” even though the treatment was
only a placebo.