Download Document

Name:
Date:
Block:
1.3 Experimental Design
Statistics - Chapter 1 - 1.3 Experimental Design - Notes
I. Survey – collecting opinions from individuals
A. Activity: Take the survey. Split into groups of two and find good and bad things about the survey.
B. Pitfalls with Surveys
a. Non-response – not enough people respond.
b. Voluntary Response – only a particular group will respond
c. Biased Sample – under or over represents a particular group.
d. Representative Sample – a sample that takes on all characteristics of a population.
e. Convenience Sample – a sample from what ever is readily available.
C. Elvis Presley Survey
On the twelfth anniversary of the death of Elvis Presley, a Dallas record company sponsored a national callin survey. Listeners of over 1000 radio stations were asked to call a 1-900 number (at a charge of $2.50) to
voice an opinion concerning whether or not Elvis was really dead. It turned out that 56% of the callers felt
that Elvis was alive.
1. Identify the population of interest and the sample actually used in the survey.
2. Do you think that 56% is an accurate reflection of beliefs of all Americans on this issue? If not, identify
some of the flaws in the sampling method.
D. Alf Landon Survey
In 1936, Literary Digest Magazine conducted the most extensive (to that date) public opinion poll in history.
They mailed out questionnaires to over 10 million people whose name and addresses they had obtained from
telephone books and vehicle registration lists. More than 2.4 million people responded, with 57% indicating
that they would vote for Republican Alf Landon in the upcoming Presidential election. (Incumbent
Democrat Franklin Roosevelt won the election, carrying 63% of the popular vote.)
1. Identify the population of interest and the sample actually used in this survey.
2. Offer an explanation as to how Literacy Digest’s prediction could have been so much in error. In particular,
comment on why its sampling method made it vulnerable to overestimating support for the Republican
candidate.
II. Observational Studies - the investigator passively observes and records information on individual with or
without a treatment. Some examples might be watching animals in the wild (no treatment) or given a patient or
group a drug, then watch & record what happens.
III. Experimental Study
A. Vocabulary
An experimental study has two groups, the experimental group and the control group. The experimental
group will receive the actual treatment, while the control group will receive a placebo or false treatment.
The experimenter needs a control group to be able to compare the results of the experiment to see if it (the
treatment) had any effect. A treatment is something that is actively imposed on the group (a drug, food,
behavior, environment, action, etc.).
B. Logic of Experimental Design
An experiment is necessary to establish a cause-and-effect relationship between variables. In contrast to an
observational study, one of the key characteristics of an experiment is that the experimenter actively imposes
the treatment on the subjects. The experimenter then can see the direct effect of the treatment. Lurking or
Confounding Variables may influence or be an underlying cause of a change in the response of the
experimental group.
Name:
Date:
Block:
C. Forms of Control help to eliminate lurking or confounding variables which allows us to have a cause-andeffect relationship.
1. Randomization – produces (usually SRS) produces groups of subjects that should be similar in all resects
before we apply treatments.
2. Comparison – ensures that influences besides the experimental treatments operate equally on all groups.
3. Blindness – the individuals do not know which group they are in.
4. Double Blind – the administrator does not who is in which group, and the individuals do not know who is in
which group.
5. Replication – repeating the experiment on numerous patients ensure the differences in results did not occur by
chance.
D. Activity: Parkinson Disease and Embryo Treatment
Current drug therapies or neuroprotective methods do not provide sufficient help to patients with Parkinson’s
disease. A promising new treatment for Parkinson’s disease involves injecting fetal tissue into the brain of the
patient to replace damaged brain cells and compensate for the loss of essential nerve cell groups. A clinical trial
involved 40 patients with Parkinson’s disease. Twenty were given the fetal tissue and 20 were not.
1. Identify the experimental group and the control group in this study and sketch a graphic of the experimental
design.
2. How would you suggest dividing the forty patients into the surgery group (experimental group) and the control
group?
3. Suppose the group who undergo surgery begin to feel more “positive” and “healthier” on subsequent patient
follow-up questionnaires. Would you be willing to conclude that this response could be attributed solely to the
injection of the cells? Explain.
The very fact that subjects in the treatment group realize that they are being given something that researchers
expect will improve their condition may affect their response differently than those of subjects who are not given
any treatment. This phenomenon has been detected in many circumstances, especially medical studies, and is
known as the placebo effect. Experimenters control for this confounding variable by administering a placebo
(referring to the “sugar pill” or empty drug given in medical studies) to those subjects in the control group. This
method of control is called blindness, since subjects are not told whether or not they are receiving the real
treatment or the placebo. Medical researchers know from long experience that roughly 1 in every 3 patients feels
better with only a sugar pill (Time, February 22, 1999). The placebo effect appears to be especially strong with
Parkinson’s patients.
4. In the Colorado study, the twenty patients in the control group were given a surgical procedure that only
involved cutting two holes in their skull without the injection of fetal tissue. Were the patients in this study blind
to whether they were in the control group or the treatment group? Explain the benefits of the approach.
5. The Colorado study caused a bit of controversy in the medical world. George Annas, director the law,
medicine, and ethics program at the Boston University School of Medicine, stated, “Not only is it ethical to do it
this way, it’s probably unethical to do it any other way” (Boston Glove, February 4, 1999). Do you believe that
the knowledge gained from this type of comparative experiment is worth the potential dangers of unnecessary
surgery?
6. Explain why it would be important for the person evaluating the health of the patient to also be blind to which
treatment group the patient is in.