Name___________________________________________Per________Date________________

AP Statistics
Experimental Design
Free Response Quiz

Free Response #3 1999

The dentists in a dental clinic would like to determine if there is a difference between the number of new cavities
in people who eat an apple a day and in people who eat less than one apple a week. They are going to conduct a study
with 50 people in each group.
Fifty clinic patients who report that they routinely eat an apple a day and 50 clinic patients who report that they
eat less than one apple a week will be identified. The dentists will examine the patients and their records to
determine the number of new cavities the patients have had over the past two years. They will then compare the
number of new cavities in the two groups.

a) Is this an observational study or an experiment? Justify your answer.

This is an observational study. There are no treatments being assigned to subjects, while dentists are only
observing some characteristic of the sample. Furthermore, there is no randomization of the subjects to
treatments taking place.
b) Explain the concept of confounding in the context of this study. Include an example of a possible confounding
variable.
Two variables would be confounded in this study if there effect on the number of new cavities cannot be
distinguished from one another. An example would be people who eat an apple a day might be more nutritious
conscience of what they eat on a regular basis.
c) If the mean number of new cavities for those who ate an apple day was statistically significantly smaller than
the mean number of new cavities for those who ate less than one apple a week, could one conclude the lower
number of new cavities can be attributed to eating an apple a day? Explain your response.
Not necessarily. Since this is not an experiment, we cannot establish a direct cause-and-effect relationship. Again
the confounding variables that are present might affect the outcome of the number of cavities.

Free Response #4 2003B

There have been many studies recently concerning coffee drinking and cholesterol level. While it is known that
several coffee-bean components can elevate blood cholesterol level, it is thought that a new type of paper coffee
filter may reduce the presence of some of these components in coffee.
The effect of the new filter on cholesterol level will studied over a 10-week period using 300 nonsmokers who each
drink 4 cups of caffeinated coffee per day. Each of these 300 participants will be assigned to one of two groups:
the experimental group, who will only drink coffee that has been made with the new filter, or the control group,
who will only drink coffee that has been made with the standard filter. Each participants cholesterol level will be
measured at the beginning and at the end of the study.
a) Describe an appropriate method for assigning the subjects to the two groups so that each group will have an
equal number of subjects.

Since there are a total of 300 subjects for the study and we need two groups, we could assign a person a number
from 1-300. We would then use a random number generator to decided what group each person goes in. For
instance, 1-150 would be in the treatment group with the filter, while the other 150 individuals would be in the
control group.
b) In this study, the researchers chose to include a group who only drank coffee that was made with the standard
filter. Why is it important to include a control group in this study even though cholesterol levels will be measured
at the beginning and at the end of the study?
There could be possible confounding variables, and the control group would be used as a baseline group for the
results that will be obtained. The control group allows for comparison, whether good or bad, on how the treatment
is affecting the subjects cholesterol.
c) Why would the researchers choose to use only nonsmokers in the study?
Since smoking is probably a variable that could affect cholesterol levels, it is best to control for the variable by
providing all non-smokers in the sample. This ensures that one variable, smoking in our case, is accounted for and
the variation in the treatment is not due to smoking or non-smoking. However, this will only allow us the opportunity
to generalize our findings to non-smokers.

Free Response #4 2003

Because of concerns about employee stress, a large company is conducting a study to compare two programs (tai chi
or yoga) that may help employees reduce their stress levels. Tai chi is a 1,200 year-old practice, originating in
China, that consists of slow, fluid movements. Yoga is a practice, originating in India, that consists of breathing
exercises and movements designed to stretch and relax muscles. The company has assembled a group of volunteer
employees to participate in the study during the first half of their lunch hour each day for a 10-week period. Each
volunteer will be assigned at random to one of the two programs. Volunteers will have their stress levels measured
just before beginning the program and 10 weeks later at the completion of it.
a) A group of volunteers who work together ask to be assigned to the same program so that they can participate in
that program together. Give an example of a problem that might arise if this permitted. Explain to this volunteer
group why random assignment to the two programs will address this problem.
Random assignment is needed to ensure that we are spreading out any variation in the sample as equally as possible.
If two volunteers who work in the same department or on the same project work together, a deadline to a project
could be moved back causing levels of stress to decrease, or some other factor that could not be accounted for.
We randomize to ensure that what we cannot control will not have as big of an effect on our sample.
b) Someone proposes that a control group be included in the design as well. The stress level would be measured for
each volunteer assigned to the control group at the start of the study and again 10 weeks later. What additional
information, if any, would this provide about the effectiveness of the two programs?
The control group provides a baseline comparison group. As a result the company could use the control group to
compare whether the change in stress levels is attributed to the treatments being imposed or some other factors
that may have not been accounted for in the original study.
c) Is it reasonable to generalize the findings of this study to all employees of this company? Explain.

It is not reasonable to generalize these findings because the participants are volunteers and only those strongly
having an opinion will participate.

Free Response #4 2001

Students are designing an experiment to compare the productivity of two varieties of dwarf fruit trees. The site
for the experiment is a field that is bordered by a densely forested area on the west (left) side. The field has
been divided into eight plots of approximately the same area. The students have decided that the test plots should
be blocked. Four trees, two of each of the two varieties, will be assigned at random to the four plots within each
block, with one tree planted in plot.
The two blocking schemes showing below are under consideration. For each scheme, one block is indicated by the
white region and the other block is indicated by the gray region in the figures.
Blocking Scheme A

Blocking Scheme B

Key
Block 1
Block 2

Forest

Forest

a) Which of the blocking schemes, A or B, is better fit for this experiment? Explain your answer.
Blocking scheme A is better because we are blocking on the location with respect to the forest. Plots near the
forest are probably more productive as they probably have exposure to more nutrient rich soil.
b) Even though the students have decided to block, they must randomly assign the varieties of trees to the plots
within each block. What is the purpose of this randomization in the context of this experiment?
The randomization is used to spread the differences out that may occur within each block or more specific each
plot of soil. Some soil may be exposed to more light, while other soil may be exposed to more water and wind. By
randomizing we try to ensure that we are equally spreading this variation out amongst the levels of soil.

Free Response #3 2002 Form B

A preliminary study conducted at a medical center in St. Louis has shown that treatment with small, low-intensity
magnets reduces the self-reported level of pain in polio patients. During each session, a patient rested on an
examining table in the doctors office while the magnets, embedded in soft pads, were strapped to the body at the
site pain. Sessions continued for several weeks, after which pain reduction was measured.
A new study is designed to investigate whether magnets also reduce pain in patients suffering from herniated disks
in the lower back. One hundred male patients are available for the new study.
a) Describe an appropriate design for the new study. Your discussion should briefly address treatments used,
methods of treatment assignment, and what variables would be measured. Do not describe how the data would be
analyze.

A completely randomized design would be diagramed as follows:

Treatment 1
Low Intensity
Magnets

50 male

patients

Randomize

100 male

patients

50 male

Compare selfreported pain levels

of both groups

Treatment 2
No Magnets
Control

patients

We will split the 100 male patients into two treatment groups: A low intensity magnet group and a no magnet group(
control group) or even a placebo group. We will randomize which group each male will go to by flipping a coin: Heads
will be in the magnet group and tails will go to the control/placebo group. We will compare the self-reported pain
levels of both groups at the end of this study.
b) Would you modify the design above, if, instead 100 male patients, there were 50 male and 50 female patients
available for the study? If so, how would you modify your design? If not, why not?
Yes, because males and females may have different levels of pain toleration I would block on gender. A blockrandomize design would look as follows:

Randomize

50 females

Randomize

Block by Gender

100 patients;
50 males
50 females

50 males

25 males

25 males

25 females
25 females

Treatment 1:
Magnets
Treatment 2:
Control

Treatment 1:
Magnets
Treatment 2:
Control

Compare the
self-reported
pain levels of
males

Compare the
self-reported
pain levels of
females

We will block by gender. Treatment groups will be decided by a random number generator for each group. Each
male will be numbered 1-50 and each female will be numbered 1-50. 1-25 will get the treatment while 26-50 will be
placed in the control/placebo group. We will compare the results of each treatment within each block.

Free Response 2007 #3 Form B

The United States Department of Energy is conducting an experiment to compare the heat gain in houses using two
different types of windows, A and B. Six windows of each type are available for the experiment. The Department
has constructed a house with 12 windows as shown on the floor plan below.
North

West

East

Window

South

In the interior of the house, each window is surrounded by a window box to capture and measure the amount of
heating coming in through the window and to isolate the heat gain for each window.
a) A randomized block experiment will be used to compare the heat gain for the two types (A and B) of windows.
How you would you group the window boxes into blocks? (Clearly indicate your blocks using the window box
numbers.) Justify your choice of blocks.
A blocked-randomized design would look as follows:
Treatment 1 (A)
2 Windows

Block 2 (East)
4 Windows
2,3,4,5
Block 3 (South)
4 Windows
6,7

Block 4 (North)
2 Windows
1,12

Compare the heat

gain.

Treatment 2 (B)
2 Windows

Randomize

12 Windows

Block by Location

Block 1 (West)
4 Windows
8,9,10,11

Treatment 1 (A)
2 Windows
Treatment 2 (B)
2 Windows
Treatment 1 (A)
1 Window

Compare the heat

gain.

Compare the heat

gain.

Treatment 2 (B)
1 Window
Treatment 1 (A)
1 Window
Treatment 2 (B)
1 Window

Compare the heat

gain.

An alternative to this approach is to use a matched pairs design matching by location.

Block 1 : 10 , 11

Block 2: 8,9

Block 3: 2,3

Block 4: 4,5

Block 5: 6,7

Block 6:1, 12

We block because heat gain could be affected by a couple of elements looking at the print. The doors could affect
the heat gain as well as the side of the building because of how the sun rises and sets.
b) For the design in part (a), describe how you would assign window types (A and B) to the numbered window boxes.
Since there are two treatment groups, we could flip a coin or use an even/odd table to determine which group will
get the treatments.