Understanding By Design Unit Template

Title of Unit
Curriculum Area
Developed By

Chi-Square Tests
AP Statistics- Chi-square Tests
Kevin Root

Grade Level
Time Frame

11th grade/12th grade

3/30/15-4/17/15

Identify Desired Results (Stage 1)

Content Standards
CCSS.MATH.CONTENT.HSS.IC.A.1
Understand statistics as a process for making inferences about population parameters based on a random sample from that population.
CCSS.MATH.CONTENT.HSS.IC.B.5
Use data from a randomized experiment to compare two treatments; use simulations to decide if differences between parameters are
significant.
CCSS.MATH.CONTENT.HSS.IC.B.6
Evaluate reports based on data.
CCSS.MATH.CONTENT.HSS.MD.A.2
(+) Calculate the expected value of a random variable; interpret it as the mean of the probability distribution.
CCSS.MATH.CONTENT.HSS.MD.B.7
(+) Analyze decisions and strategies using probability concepts (e.g., product testing, medical testing, pulling a hockey goalie at the end
of a game).

Understandings
Overarching Understanding
Students will see how chi square tests are comparing what we are
expecting to happen versus what actually is happening when we perform
the test or experiment.
Students will use statistical significance to prove whether there is a
relationship between two categorical variables.
Students will see and understand how chi square tests are important and
are prevalently used on everyday basis to make necessary decisions.
Students will understand how they will be able to identify which type of
test to use whether its comparing and contrasting types of chi square
tests, or chi square tests to other types of tests seen before.
Students will understand that we are using numerical values or counts
when using contingency tables and why we cannot use ratios or percents
for a frequency.

Essential Questions
Overarching

How are we able to

tell from a question
what type of test we
need to perform?
What keywords can
we pull out from a
problem?
What are ways we
can help ourselves
remember which test
to use?
What are some
everyday examples

Topical

How do the three

chi-square tests
differ from one
another?
How are they
similar?
What are the steps
necessary to
performing a chi
square test?
How can we use our
calculator as a
resource to be more

Related Misconceptions
Students will not know which type of chi square test to use based on the
way a problem is worded.
Students will not remember the differences between each test or the
steps necessary to perform a chi square test.
Students may forget how to use the calculator to help them find data that
is important to creating a proper conclusion.
Students will forget what work is necessary to show when performing a
chi square test.
Students may struggle to put their evidence and statistics into a proper
conclusion explaining what it means to someone who has no experience
with statistics within the context of the problem.
Students might not recognize when to perform a chi square test and
when to perform a test they have used before in previous chapters.
Students may think that there are observed count is the same as their
expected count or switch the two counts with one another.
Students may struggle identifying what their variables or categories are
within a problem given the context. This can impact which type of test
they use and could lead them to the wrong test.
Students will forget when using the formula for chi square tests that its a
summation of all observed and expected counts and not just one count.
Students may confuse when to reject or fail to reject the null hypothesis
based on their p-value they have found.
Students may be unsure what to do if the necessary assumptions are not
met for a certain type of problem.

Knowledge

efficient for finding

evidence needed for
a conclusion?
What similarities do
we notice between
chi square tests and
one sample and two
sample tests on
proportions and
means?
How are they
different and how
can we identify when
we need to use
these different types
of tests?
How do the graph
and the distribution
for a chi square test
change as degree of
freedom changes?
How can we
find/know what are
expected counts
versus observed
counts?
How does the critical
value relate to
degrees of freedom?

Objectives
Skills

Students will know

that we can analyze

using chi square
tests?
Why are chi square
tests necessary or
important to us?
How do we know that
our answer makes
sense? How can we
explain our answer to
someone who hasnt
used statistics
before?
How can we model
the information we
have in an organized
way to help us
interpret our results?
Matrices? Lists?
Tables?
Why can we not use
percents or ratios for
expected counts or
observed counts?
What should we do if
our assumptions are
not met for a test?
Can we perform the
test without these
assumptions?

Students will know the assumptions, hypothesis statements,

formulas, and conclusion that is necessary in order to perform a
chi-square test.
Students will know the differences between the three chi square
tests and know when to use them based on the given information
in a problem.
Students will know tricks or keywords within a question that can

Students will be able to

Students will be able to perform a chi square test of

goodness of fit, independence, or homogeneity.
Students will be able to create a proper conclusion
within the context of a problem based on the stats
they find from a chi square test.
Students will be able to use the calculator to find
statistics and parameters necessary to help perform

help decipher between which types of test to use (dependent vs

independent, same vs different, etc.).
Students will see how important chi square tests are and how
prevalently they are used in the real world to analyze data and
make decisions.
Students will know how to explain their reasoning for their answer
and how it makes sense clearly within the context and to someone
who hasnt used statistics before.
Students will know how to use their calculator as a resource for
conducting a chi square test and interpreting what this information
tells us about our conclusion.
Students will know when they have found two meaningful
categorical variables that can be used to compare its relationship.

a chi square test.

Students will be able to create a table of expected
counts using given information within a problem.
Students will be able to communicate clearly what
evidence they have found in writing and to group
members in order to make conclusions using a chi
square test.
Students will be able to show all of the work
necessary to give evidence for their conclusion.
Students will be able to explain what their evidence
means within the context of the problem to
someone who has never done statistics.
Students will be able to conduct their own
experiment, perform a chi square test, and make a
conclusion about how two variables are related.

Assessment Evidence (Stage 2)

Performance Task Description
Goal

Role
Audience
Situation
Product/Performance
Standards

Recognize students ability to indentify when to perform a chi square test and which type to use;
ability to perform all the necessary steps to make a conclusion for a particular question; ability to
apply statistics to a given situation and conclude what this means within the context; ability to use
the calculator as a resource to find important information necessary for a chi square test; ability to
move through to different types of testing setup like the AP exam they will take in May (multiple
choice and free response).
Summative Assessment
Myself, Mentor teacher (Sarah Johnson)
Classroom Test (1 hour class period)
Completed Test. Students will finish a two-part test of multiple choice and free response sections.
Students can come in for test corrections after completing the test to look at what mistakes they
made, how they can fix them, and to make sure they are ready for the AP exam in May

CCSS.MATH.CONTENT.HSS.IC.A.1
Understand statistics as a process for making inferences about population parameters based on a
random sample from that population.
CCSS.MATH.CONTENT.HSS.IC.B.5
Use data from a randomized experiment to compare two treatments; use simulations to decide if
differences between parameters are significant.
CCSS.MATH.CONTENT.HSS.IC.B.6
Evaluate reports based on data.
CCSS.MATH.CONTENT.HSS.MD.A.2

(+) Calculate the expected value of a random variable; interpret it as the mean of the probability
distribution.
CCSS.MATH.CONTENT.HSS.MD.B.7
(+) Analyze decisions and strategies using probability concepts (e.g., product testing, medical testing,
pulling a hockey goalie at the end of a game).

Other Evidence
Learning Plan (Stage 3)
Day in Unit

Lesson
Topic

Lesson Learning
Objective

Chi-Square
Goodness of
Fit

Students will be able to

perform a chi square test for
goodness of fit and know the
necessary steps needed to do
so (appropriate assumptions,
hypothesis statements,
formula, and conclusion).

Chi Square
Independen
ce

Students will be able to

perform a chi square test for
Independence and know the
necessary steps needed to do
so (appropriate assumptions,
hypothesis statements,
formula, and conclusion).

Description of how
lesson contributes to
unit-level objectives

Assessment activities

During this lesson we will

introduce what a chi square test
is and stay specific to chi square
tests of goodness of fit. We will
discuss the assumptions,
hypothesis statements, formula,
and degrees of freedom that are
necessary to know when
performing a chi square test on
univariate types of data. We
will also analyze what sample
size and degrees of freedom
does to the shape, center, and
distribution for chi square tests.
Students will perform these
types of examples and be able
to create a proper conclusion
that puts stats into words that
clearly states what it means
within its context.
During this lesson we will
continue to talk about chi
square test shifting gears to
tests of independence and we
will discuss the differences and
similarities with that of
goodness of fit tests. We will

Book Problems: 12.1, 12.3,

12.5, 12.9
These book problems are
specific to performing Goodness
of Fit tests.

Book Problems: 12.15, 12.17,

12.27
These book problems are
specific to performing
Independence tests.

Chi-Square
Homogeneit
y

Students will be able to

perform a chi square test for
homogeneity and know the
necessary steps needed to do
so (appropriate assumptions,
hypothesis statements,
formula, and conclusion).

Chi-Square
M&M
Activity/Eye
Dominance
Activity

Students will be performing the

experiment themselves and
making their own conclusion
about the data they find in
these activities.

look at how to use the

calculator to find our statistics
necessary for performing this
test and how to find our
expected counts for our table.
The conclusion is the same,
however the wording changes
when we are talking about the
context and what relationship
we are testing.
During this lesson we will
continue to talk about chi
square test and looking
specifically at the third type of
test being homogeneity. We will
look at how this is different from
the other tests and also how it
is very similar to a test of
independence. We will compare
how between the tests and find
ways we can decide what type
of test is necessary to use. We
still will have to know how to
find our expected counts and be
able to create a table of these
values.
Students will be coming back
from spring break so they will
not have seen much of this
information for a bit. I want to
start them out with two
activities that look at all three
types of chi square tests that
help refresh their memories on
the differences and similarities.
Students will be actually
performing the experiment
finding expected counts, but
also observed counts from their
experiment. They will need to
perform all the steps necessary
in order to make a conclusion
about their data.

Chi-squared Worksheet:
Students must be able to
indentify what type of test to
use, and then perform the
necessary steps to find their
answer and make a conclusion.

Warm-up Activity: Which

Test???
Students will be given a couple
examples of chi square test
situations and must identify
which test to use and perform
the test.

Mixed
ReviewKAHOOT
Game

Chi Square
Review

Chi-Square
Test

Students will be playing a

mixed review game with
hypothesis tests called
KAHOOT. Students will be
learning how to differentiate
between different types of
tests using their group
members and must come to
conclusions as a group. This is
a mixed review not specific to
chi square to help them
continually seeing examples of
tests that will be on their AP
exam.
Students will be working on a
multiple choice review
worksheet and will be able to
work with their group members
to complete it. They will be
able to work collaboratively
discussing ideas, topics they
may have misconceptions on,
and use each other as
resources to prepare for their
test.
TEST

All objectives apply here, but

students also must be prepared
for other types of tests we have
used in previous chapters.
Students will be allowed to use
their notes, but must work with
their group members to figure
out which test they need to use.

Exit slip: This will ask students

how they feel this review helped
them prepare for their
upcoming test and how it could
have been improved. As well as
what areas they still need work
on or where they feel
comfortable with their
understanding.

Review: All objectives apply.

None

TEST

TEST

Chi-Squared Test

NAME

AP Statistics

Multiple Choice (5 pts. each)

1) The following data were obtained from a company that manufactures special plastic containers that are to hold a specified volume of hazardous
material. On each of the three 8 hour shifts workers are asked to make 500 of the containers. Some containers do not meet specifications as
required by the companys customer because they are too small, others because they are too large.
H0: the proportion of containers conforming to specifications is the same for all three shifts
Ha: the proportion of containers conforming to specifications is different for the three shifts

Which
a)
b)
c)
d)
e)

Shift
8 am
4 pm
Midnight
Total

Conformance to specifications
Too Small
Meet Specs.
Too Large
36
452
12
24
443
33
12
438
50
72
1333
95

Total
500
500
500
1500

of the following statements is a correct conclusion?

The proportion of containers conforming to specification is the same for all three shifts.
The proportion of containers conforming to specification is not the same for all three shifts.
The mean number of containers conforming to specification is not the same for all three shifts.
There is no relationship between conformance to specifications and shifts.
There is a relationship between conformance to specifications and shifts.

2) In a 2 test of goodness-of-fit to determine if the five flavors of Skittles candies are evenly distributed, the test statistic is 5.5. What is the
p-value?
a) .1097
b) .0879
c) .3579
d) .2397
e) .0014
3) Which of the following statements is true?
a) The 2 test statistic measures the extent to which the observed counts differ from (dont fit) those expected when H 0 is true.
b) A small value for 2 indicates that the observed counts are not significantly different than those expected when H 0 is true.
c) For the 2 test, the associated p-value is the area under the appropriate 2 curve to the left of the calculated test statistic.
d) 2 tests can only be used on univariate categorical data sets.
e) For a sample of size n, the degrees of freedom associated with the goodness-of-fit test are n 1.
4) It is generally agreed that the use of the 2 distribution is appropriate when the
a) sample size is at least 30.
b) sample size is large enough so that all the observed counts are at least 5.
c) sample size is large enough so that all the expected counts are at least 5.

d) sample size is large enough so that at least one of the expected counts is at least 5.
e) sample size is large enough so that at least one of the observed counts is at least 5.
5) Which of the following statements is false?
a) All 2 curves are unimodal.
b) Each degree of freedom has a different 2 curve associated with it.
c) As the degree of freedom decreases, the 2 distribution approaches a normal distribution.
d) The 2 distribution is a continuous distribution.
e) The2 test statistic never has a negative value.
6) The manager of a business office performed a 2 test to determine if the number of employees who called in sick was not evenly distributed
throughout the work week (Monday Friday). If H0: the number of employees who called in sick is evenly distributed throughout the work week,
which of the following is a type II error?
a) We decide that the number of employees who called in sick is not evenly distributed throughout the work week when it really is evenly
distributed.
b) We decide that the number of employees who called in sick is evenly distributed throughout the work week when it really is not evenly
distributed.
c) We decide that the number of employees who called in sick is not evenly distributed throughout the work week when it really is not evenly
distributed.
d) We decide that the number of employees who called in sick is evenly distributed throughout the work week when it really is evenly
distributed.
7) Independent random samples of 100 men and 100 women were drawn and each of the individuals sampled was asked the following question, Are
you for or against the use of the death penalty? The following table displays the results.
If H0: males & females have the same opinion in regards to the use of the death penalty, what type of 2 test would be appropriate to use for this
data?
For
Against
Total
a) Goodness-of-fit
Male
72
28
100
b) Independence
Female
52
48
100
c) Homogeneity
Total
124
76
200
8) For the table in question #7, how many degrees of freedom are there?
a) 200
b) 199
c) 4
d) 3

e) 1

9) A study investigated the possible association between seat position on a bus and whether the rider experiences motion sickness. The following
table classifies each person in a random sample of bus riders by the location of his or her seat and whether nausea was reported. Which of the
following statements is correct?
Nausea
No Nausea
Front
58
870
Middle
166
1163
Rear
193
806

a)
b)
c)
d)

Since
Since
Since
Since

the p-value
the p-value
the p-value
the p-value

is
is
is
is

less than , we can conclude that where you sit on the bus causes motion sickness.
greater than , we cannot conclude that where you sit on the bus causes motion sickness.
less than , we can conclude that where you sit on the bus is associated with motion sickness.
greater than , we can conclude that where you sit on the bus is not associated with motion sickness.

10) Two different professors teach an introductory Statistics course. The table shows the distribution of final grades they reported. We
wonder whether one of these professors is an easier grader. Why is it not appropriate to perform a 2 test? (expected are in parentheses)
a) We do not have counts of categorical data.
Prof. Alpha
Prof. Beta
b) Not all expected counts are at least 5.
A
3 (6.667)
9 (5.333)
c) These classes do not represent reasonable random samples of students for these professors.
B
11 (12.778)
12 (10.222)
d) The observed counts are too small.
C
14 (12.222)
8 (9.778)
D
9 (6.111)
2 (4.889)
11) Some people believe that a full moon elicits unusual behavior in people. Researchers performed a 2
F
3 (2.222)
1 (1.778)
test of independence on the number of violent crimes for weeks during a full moon versus the number of
violent crimes during weeks when the moon is not full. The appropriate p-value for this hypothesis test is 0.043. If = 0.05, which of the
following conclusions is correct?
a) We can conclude that full moons do cause people to perform more violent crimes.
b) We can conclude that full moons do not cause people to perform more violent crimes.
c) We can conclude that there is sufficient evidence to suggest an association between the phase of the moon and the number of violent
crimes.
Employed full
Not employed
Total
d) We can conclude that there is
not sufficient evidence to suggest an
time
full time
association between the phase
of the moon and the number of violent
Earned at least a
52
40
92
crimes.
high school diploma
Did not earn a high
school diploma
Total

12) Criminologists have long debated

between weather and violent crime.
according to the season. If H0: number of homicides is
how many homicides do we expect to happen during the
a) 328
c) 340.25
b) 25%
d) 82

30

35

65

82

75

157

Winter
328

Spring
334

Summer
372

Fall
327

whether there is a relationship

1361 homicides are classified
evenly distributed through the four seasons,
winter?

13) The following two-way table resulted from classifying each individual in a random sample of residents of a small city according to level of
education (with categories earned at least a high school diploma and did not earn a high school diploma) and employment status (with
categories employed full time and not employed full time).
If the null hypothesis of no association between level of education and employment status is true, which of the following expressions gives the
expected number who earned at least a high school diploma and who are employed full time?

a)

92 52
157

b)

92 82
157

c)

82 52
92

d)

65 52
92

e)

92 52
82

14) A geneticist hypothesizes that half of a given population will have brown eyes and that the remaining half will be split evenly between blueand green-eyed people. In a random sample of 60 people from this population, the individuals are distributed as shown in the table below. What is
the value of the 2 statistic for these data?

a)
b)
c)
d)

Less than 1
At least 1, but less than 10
At least 10, but less than 20
At least 20, but less than 50

Brown eyes
34

Green Eyes
15

Blue eyes
11

e) At least 50
Mixed Inference:
15) A car dealer believes that each of the five colors of a certain car is equally likely to be chosen by the customer. At the end of a month, the
dealer sees that 21 red cars, 10 blue cars, 15 white cars, 17 black cars, and 7 light taupe cars are sold. Using the appropriate hypothesis test for
the dealers belief, what is the test statistic?
a) z = 8.86
b) t = 8.86
c) 2 = 8.86
d) p = .065
e) df = 4
16) Having done poorly on their math final exams in June, six students repeat the course in summer school and take another exam in August. The
mean difference in final exam scores is 2.8 with standard deviation of 1.95. If we consider these students representative of all students who
might attend this summer school in other years, does the evidence suggest that the program is worthwhile?
a) No, the sample size is too small.
b) No, the average change in exam scores is only 2.8.
c) Yes, the p-value is less than 0.01
d) Yes, all the students showed an increase in exam scores
e) It cannot be determined since we were not given the actual scores for the six students.

17) A researcher wanted to see whether there is a significant difference in resting pulse rates for men and women. A random sample of 28 men
had a mean resting pulse rate of 72.75 with standard deviation of 5.372. A random sample of 24 women had a mean resting pulse rate of 72.625
with standard deviation of 7.699. What is the p-value of the appropriate test to determine if there is evidence of a significant difference in
mean resting pulse rates for men and women?
a) 0.0668
b) 0.9471
c) 0.4735
d) 40.23
e) 23
18) The painful wrist condition called carpal tunnel syndrome can be treated with surgery or less invasive wrist splints. In a study of 176
patients, among the half that had surgery, 80% showed improvement after three months, but only 54% of those who used the wrist splints
improved. Do these data provide evidence that there is a significant difference in the proportion of patients who improved with surgery than
with wrist splints?
a) Yes, since psurgery is larger than pspl int
b) Yes, since the p-value is less than 0.001.
c) No, since the pooled p is greater than 0.5.
d) No, since the p-value is 4.189 which is greater than 0.1.
e) It cannot be determined since the number showing improvement in each group is not given.
19) National data in the 1960s showed that about 44% of the adult population had never smoked cigarettes. In 1995 a national health survey
interviewed a random sample of 881 adults and found that 525 had never been smokers. What is the standard error for the sampling distribution
of sample proportions?
a) 9.323
b) 0.000
c) 0.596
d) 0.017
e) 0.44
20) The infamous researcher, Dr. Evil, claims to have found a drug that causes people to grow taller. The coach of the Basketball team at Texas
Tech University has expressed interest but demands evidence. Ten people are randomly selected from students at Texas Tech, their heights
measured, the drug administered, and two hours later, their heights measured again. If the hypotheses tested were no height change vs. an
increase in height, what would the appropriate hypothesis test be?
a) 1-sample t test on means (or matched pairs)
b) 1-sample z test on proportions
c) 2-sample t test on means
d) 2-sample z test on proportions
e) 2 test