Surveys, Experiments, and Observational studies

1
Surveys, Experiments, and Observational studies
Warm Up
Lesson Presentation
Lesson Quiz
Holt Algebra 2
Holt McDougal Algebra 2
2
Warm Up 1/16/14 Identify the population and the
sample.
1. Fifty teenagers are randomly selected and
asked whether they have siblings.
population teenagers sample the 50 selected
teenagers
2. Fifteen passengers on a flight are asked about
the quality of the flight attendants service.
population passengers on the flight sample the
15 people asked
3. To determine how many cats have blue eyes, the
eye colors of 10 cats at each of 10 animal
shelters in different states are recorded.
population cats sample the 100 cats whose eye
colors are recorded
3
Objectives
Focus on the commonalities and differences
between surveys, experiments, and observational
studies.
4
Vocabulary
experiment observational study controlled
experiment control group treatment
group randomized comparative experiment
5
You have already seen that a survey is one way to
collect data. Although surveys are useful,
different situations require different techniques
for gathering data. Individuals are people,
animals, or objects that are described by data.
If you collect data on the fuel efficiency of
cars and trucks, the individuals are vehicles.
Variables are used to describe individuals. Fuel
efficiency, measured in miles per gallon, is an
example of a variable.
6
(No Transcript)
7
For data from an experiment to be useful, the
experiment must be carefully designed. In a
controlled experiment, two groups are studied
under conditions that are identical except for
one variable. The effects of the treatment are
determined by comparing the control group and the
treatment group.
8
Often, to demonstrate a cause and effect
hypothesis, an experiment must show two things.
First, that a phenomenon occurs with the
treatment and second, that the phenomenon does
not occur in the absence of the treatment.
In a randomized comparative experiment, the
individuals are assigned to the control group or
the treatment group at random, in order to
minimize bias. An experiment that is not a
randomized comparative experiment may be subject
to bias, and any conclusions drawn from the
experiment may not be valid.
9
Example 1 Identifying Experiments and
Observational Studies
Explain whether each situation is an experiment
or an observational study.
A. A researcher wants to know if a soil additive
makes a fern grow more quickly. He grows one
specimen in treated soil and one in untreated
soil.
The researcher applies a treatment, so the
situation is an experiment.
B. To find out whether car accidents are more
likely on rainy days, a researcher records the
weather conditions during 50 randomly selected
accidents for the past year.
The researcher gathers data without controlling
the individuals or applying a treatment. The
situation is an example of an observational study.
10
EVERYONE! Write this whole problem in your notes
as an example of my expectations. Check It Out!
Example 1
A scientist measures the height of 20 birds
nests, and counts the number of eggs to see if
there is a relationship. Is this experiment or an
observational study? Explain.
It is an observational study because an
observation is being conducted without
controlling the environment in any way
11
Example 2 Evaluating a Published Report
The study described in the report is a
randomized comparative experiment. Describe the
treatment, the treatment group, and the control
group.
The treatment is bathing in Epsom salt. The
treatment group consists of the fifty subjects
who bathe in the Epsom salt, and the control
group consists of the fifty subjects who did not.
12
Check It Out! Example 2
The study described in the report is a
randomized comparative experiment. Describe the
treatment, the treatment group, and the control
group.
The treatment is using the old and new websites
to make purchases. The treatment group consists
of users of the website using the new website to
make purchases. The control group consists of
users of the website using the old website to
make purchases
13
Example 3 Designing an Experiment or
Observational Study
Explain whether the research topic is best
addressed through an experiment or an
observational study. Then explain how you would
set up the experiment or the observational study.
The treatment may affect health, so it is not
ethical to assign individuals to a treatment
group. Perform an observational study. Randomly
choose one group of people who already use
tanning beds at least twice a month and another
group which does not. Monitor the incidence of
skin diseases in both groups.
14
Check It Out! Example 3
Explain whether the research topic is best
addressed through an experiment or an
observational study. Then explain how you would
set up the experiment or the observational study.
1000 mg of vitamin is not known to have any
negative effects, so conduct an experiment.
Randomly choose one group of people to take the
supplements, randomly choose another group
of people to not take the supplements, and
monitor the cholesterol levels in both groups.
15
Example 4 Evaluating Data Collection Methods
Classify each method as a survey, an experiment,
or observational study, and explain which would
be most reliable.
Method A Method B Method C
Choose 50 people who have at least one serving of soy a day and 50 who dont, and check their cholesterol levels. Randomly choose 100 people. Ask how many servings of soy they have a week, and ask if their cholesterol levels are high. Randomly choose 50 people to eat at least one serving of soy a day, and 50 people not to, and monitor their cholesterol levels.
16
Continued Example 4 Evaluating Data Collection
Methods
Method A observational study Method B survey
Method C experiment
In Method A, the members of the study are
self-selected. They may have a healthy diet in
general. In Method B, the results are
self-reported, so they may not be accurate.
Method C is most reliable.
17
Check It Out! Example 4
Classify each method as a survey, an experiment,
or an observational study, and explain which
would be most reliable.
18
Check It Out! Example 4
Method A experiment Method B survey Method C
observational study
Method B is least reliable, because there is no
basis for comparison. Method C has a comparison
group, but the members are self-selected, which
could lead to bias. In method A, the members of
each group are randomly selected, so method A is
the most reliable.
19
CLOSING COMPLETE the following five problems as
your TOTD.
HOMEWORK Finish Practice B AND Finish Problem
Solving (DATA GATHERING) AND BEGIN problem
solving for Surveys
20
Ticket out the door Part 1
A researcher wants to study the effects of a
vitamin supplement on insomnia. Fifty people with
insomnia volunteer for the study.
1. All of the volunteers are given a vitamin
supplement daily and the amount of sleep they get
is monitored for a month. Is the situation an
experiment or an observational study?
experiment
2. Which method would be more reliable, an
experiment or an observational study? Explain.
An experiment would be more reliable because the
volunteers may not already be taking vitamin
supplements.
21
3. Describe how the study could be made into a
randomized controlled experiment. In your answer,
identify the treatment, the treatment group, and
the control group.
Ticket out the door Part 2
Randomly select 25 of the volunteers and give
them the supplement. Do not give the other 25
thesupplement. Monitor the amount of sleep that
bothgroups get. The treatment is the supplement.
The treatment group is the 25 people given the
supplement. The control group is the 25 people
notgiven the supplement.