7th Math Unit 5
7th Math Unit 5
Standards of Excellence
Curriculum Frameworks
Mathematics
GSE Grade 7
Unit 5: Inferences
These materials are for nonprofit educational purposes only. Any other use may constitute copyright infringement.
Georgia Department of Education
Georgia Standards of Excellence Framework
GSE Grade 7 • Unit 5
Unit 5
Inferences
OVERVIEW ........................................................................................................................................... 3
STANDARDS FOR MATHEMATICAL PRACTICE .......................................................................... 3
STANDARDS FOR MATHEMATICAL CONTENT ........................................................................... 4
BIG IDEAS ............................................................................................................................................. 4
ESSENTIAL QUESTIONS .................................................................................................................... 4
CONCEPTS AND SKILLS TO MAINTAIN ........................................................................................ 5
FLUENCY .............................................................................................................................................. 5
SELECTED TERMS AND SYMBOLS ................................................................................................. 6
FORMATIVE ASSESSMENT LESSONS (FAL) ................................................................................. 7
SPOTLIGHT TASKS ............................................................................................................................. 7
3-ACT TASKS........................................................................................................................................ 7
TASKS .................................................................................................................................................... 8
• Is it Valid……………………………………………………………………………... ..... 10
• Snapshot ....................................................................................................................... 17
• Candy Populations ............................................................................................................ 20
• Predicting Population ........................................................................................................ 29
• Counting Trees ........................................................................................................... 34
• Human Box Plot ................................................................................................................ 36
• Shakespeare vs. Harry Potter ........................................................................................... 38
• Box and Whisker Plots – FAL ........................................................................................... 46
• Got Friends? ................................................................................................................... 47
• Travel Times to Work ...................................................................................................... 53
• Thumbs on Fire Part 2 ...................................................................................................... 58
• Emergency 911! Bay City .................................................................................................. 61
TECHNOLOGY RESOURCES .............................................................................................. 74
OVERVIEW
The units in this instructional framework emphasize key standards that assist students in developing a
deeper understanding of numbers. They have learned to recognize and express different representations
of rational numbers. Now they will learn how to apply the statistical aspect of mathematics to the
measures of center, variability and population. The Big Ideas that are expressed in this unit are
integrated with such routine topics as estimation, mental and basic computation. All of these concepts
need to be reviewed throughout the year.
The Evidence of Learning will tell you what your students will learn in this unit. Take what you need
from the tasks and modify as required. These tasks are suggestions, something that you can use as a
resource for your classroom.
1. Make sense of problems and persevere in solving them. Students make sense of information by
connecting visual, tabular, and symbolic representations of sample populations in real-life contexts.
2. Reason abstractly and quantitatively. Students’ reason about the values in data representations
based upon their relationship to the real number line.
3. Construct viable arguments and critique the reasoning of others. Students use data to make
inferences from sample sets. They construct viable arguments by referring to representations as evidence
of their inferences and question each other regarding these inferences.
4. Model with mathematics. Students generate representative samples in real-world contexts and
represent these visually, in tables, and symbolically to gain information from sample sets.
5. Use appropriate tools strategically. Students choose appropriate mathematical and visual
representations, including technology-based tools, to represent the data distributions.
6. Attend to precision. Students use precision to collect accurate measurement information from sample
populations and precise language when generating and interpreting data.
7. Look for and make use of structure. Students interpret data representations in tables, histograms,
box plots and scatter plots by examining the features of those representations.
8. Look for and express regularity in repeated reasoning. Students look to make generalized
comparisons between situations that involve bias using specific criteria.
MGSE7.SP.1 Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are
valid only if the sample is representative of that population. Understand that random sampling
tends to produce representative samples and support valid inferences.
MGSE7.SP.2 Use data from a random sample to draw inferences about a population with an
unknown characteristic of interest. Generate multiple samples (or simulated samples) of the same
size to gauge the variation in estimates or predictions. For example, estimate the mean word
length in a book by randomly sampling words from the book; predict the winner of a school
election based on randomly sampled survey data. Gauge how far off the estimate or prediction
might be.
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions
with similar variabilities, measuring the difference between the medians by expressing it as a
multiple of the interquartile range.
MGSE7.SP.4 Use measures of center and measures of variability for numerical data from
random samples to draw informal comparative inferences about two populations. For example,
decide whether the words in a chapter of a seventh‐grade science book are generally longer than
the words in a chapter of a fourth‐grade science book.
BIG IDEAS
• Understand that statistics can be used to gain information about a population by examining a
sample of the population; generalizations about a population from a sample are valid only if the
sample is representative of that population.
• Understand that random sampling tends to produce representative samples and support valid
inferences.
• Use data from a random sample to draw inferences about a population with an unknown
characteristic of interest.
• Generate multiple samples (or simulated samples) of the same size to gauge the variation in
estimates or predictions.
• Informally assess the degree of visual overlap of two numerical data distributions with similar
variability, measuring the difference between the centers by expressing it as a multiple of a
measure of variability.
• Use measures of center and measures of variability for numerical data from random samples to
draw informal comparative inferences about two populations.
ESSENTIAL QUESTIONS
• What are different sampling techniques used in real life?
• How do I determine an appropriate sample size?
FLUENCY
It is expected that students will continue to develop and practice strategies to build their capacity to
become fluent in mathematics and mathematics computation. The eventual goal is automaticity with
math facts. This automaticity is built within each student through strategy development and
practice. The following section is presented in order to develop a common understanding of the ideas
and terminology regarding fluency and automaticity in mathematics:
Fluency: Procedural fluency is defined as skill in carrying out procedures flexibly, accurately,
efficiently, and appropriately. Fluent problem solving does not necessarily mean solving problems
within a certain time limit, though there are reasonable limits on how long computation should take.
Fluency is based on a deep understanding of quantity and number.
Deep Understanding: Teachers teach more than simply “how to get the answer” and instead support
students’ ability to access concepts from a number of perspectives. Therefore students are able to see
math as more than a set of mnemonics or discrete procedures. Students demonstrate deep conceptual
understanding of foundational mathematics concepts by applying them to new situations, as well as
writing and speaking about their understanding.
Memorization: The rapid recall of arithmetic facts or mathematical procedures. Memorization is often
confused with fluency. Fluency implies a much richer kind of mathematical knowledge and experience.
Number Sense: Students consider the context of a problem, look at the numbers in a problem, make a
decision about which strategy would be most efficient in each particular problem. Number sense is not a
deep understanding of a single strategy, but rather the ability to think flexibly between a variety of
strategies in context.
Fluent students:
● flexibly use a combination of deep understanding, number sense, and memorization.
● are fluent in the necessary baseline functions in mathematics so that they are able to
spend their thinking and processing time unpacking problems and making meaning from them.
● are able to articulate their reasoning.
● find solutions through a number of different paths.
Students should explore these concepts using models and real life examples. Students should understand
the concepts involved and be able to recognize and/or demonstrate them with words, models, pictures
and/ or numbers.
The websites below are interactive and include a math glossary suitable for middle school students. Note
– Different sources use different definitions. Please preview any website for alignment to the
definitions given in the frameworks. The definitions below are from the CCSS glossary
http://www.corestandards.org/Math/Content/mathematics-glossary/glossary, when applicable.
• Range
• Sample
• Simple Random Sampling
More information on Formative Assessment Lessons may be found in the Comprehensive Course Guide.
SPOTLIGHT TASKS
A Spotlight Task has been added to each MGSE mathematics unit in the Georgia resources for middle
and high school. The Spotlight Tasks serve as exemplars for the use of the Standards for Mathematical
Practice, appropriate unit-level Mathematics Georgia Standards of Excellence, and research-based
pedagogical strategies for instruction and engagement. Each task includes teacher commentary and
support for classroom implementation. Some of the Spotlight Tasks are revisions of existing Georgia
tasks and some are newly created. Additionally, some of the Spotlight Tasks are 3-Act Tasks based on
3-Act Problems from Dan Meyer and Problem-Based Learning from Robert Kaplinsky.
3-ACT TASKS
A Three-Act Task is a whole group mathematics task consisting of 3 distinct parts: an engaging and
perplexing Act One, an information and solution seeking Act Two, and a solution discussion and
solution revealing Act Three.
More information along with guidelines for 3-Act Tasks may be found in the Comprehensive Course
Guide.
TASKS
Task Type Standards
Task Name Content Addressed Addressed
Grouping Strategy
Scenarios to help determine if
Learning Task a sample is valid and
Is It Valid? MGSE7.SP.1
Individual/Partner representative of the
population
MGSE7.SP.1
Problem Solving Use samples to make
Counting Trees MGSE7.SP.2
Task estimations about a larger
MGSE7.SP.3
Partner/SmallGroup population
MGSE7.SP.4
Franklin, C., Kader, G., Mewborne, D., Moreno, J., Peck, R., Perry, M., Scheaffer, R. (2007).
Guidelines for assessment and instruction in statistics education (gaise) report: A pre-k- 12
curriculum framework. Alexandria, VA: American Statistical Association.
MGSE7.SP.1. Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are valid only if
the sample is representative of that population. Understand that random sampling tends to produce
representative samples and support valid inferences.
COMMON MISCONCEPTIONS
• Students have a hard time determining when a survey is biased. This lesson seeks to help them
build a concrete checklist of things to look for in finding bias.
• One sample is not always a good representation of the entire population. Many samples must be
taken in order for the survey to be valid. One way to address this misconception is to compare
results from one sample versus results from multiple samples.
ESSENTIAL QUESTIONS
• What are different sampling techniques used in real life?
MATERIALS
• Is It Valid? Student Sheet
GROUPING
Individual / Partner
TASK COMMENTS
Prior to the task, make sure that students are familiar with the following terms: sample and simple
random sample. These terms are found in this framework. Explain to students that when sampling
populations, there are factors that can affect the results of a survey. Present the following scenarios to
help introduce the concepts of convenience sampling, voluntary response, and bias.
100 Atlanta residents were asked, “Who’s the better quarterback, Matt Ryan or the Patriots Tom
Brady?” Explain this is an example of bias. Bias occurs when poor sampling methods are used. The
result of the sampling systematically favors certain outcomes.
The school wanted to know what is the most preferred school meal severed. Only students who
bought school lunch responded. Explain this is an example of voluntary response. Voluntary
response sampling occurs when people themselves choose to respond to a general appeal. Often,
people that volunteer to respond to questions have strong opinions, often negative ones, that may not
represent the population well.
The school counselor created a survey to determine students’ perspective of school. Since she was
hosting the student of the month function, she decided to just survey those students. Explain this is
an example of convenience sampling. Convenience sampling is choosing individuals that are easiest
to reach.
Both convenience sampling and voluntary responses are poor sampling methods that lead to sampling
bias.
TASK DESCIPTION
Is It Valid?
PART I
A survey is a method of collecting information. These pieces of information, numbers and facts, are
called data.
Complete the survey questions below within your class. Listed below, you will find some possible ways
for how to complete the survey.
• Have the questions on posters around the room and let each student put their name on the poster
based on their personal data.
• Have the questions on a piece of paper. Give each student 5 small stickers. (The small star
stickers work well.) Pass the papers around the room and have students put their sticker on their
data.
For each of the problems below, answer the questions in regard to population, samples, and
surveys.
After the 2000 census, the United States Census Bureau reported that 7.4% of
Georgia residents were between the ages of 10 and 14.
10. Was a parameter or a statistic reported? Explain your reasoning. This is an example of a statistic
since it includes actual data.
11. What is the population for this survey? Every person in the United States
The manager of the Millcreek Mall wants to know the mean age of the people who shop at the mall and
the stores in which they typically shop. He hires Barker Market Research Company to collect the data.
Dennis works for the Barker Market Research Company and has been put in charge of collecting data
for the Millcreek Mall. Dennis decides to interview 100 people one Saturday because it is the mall’s
busiest shopping day.
13. What is the population for this survey? The population is everyone who comes to the mall.
14. Is the sample size for the survey appropriate? The sample size is too small for the population.
The 100 people are not a representative sample of the entire population.
PART II
There are three key things to look for when determining if a survey is biased.
15. Is the survey voluntary? Voluntary surveys only get respondents who feel strongly about the
survey topic.
16. Does the survey exclude any group? If your survey results are addressed toward a certain
group or section of the population and leaves out other respondents it is biased.
17. Is the sample size appropriate? If you want to make inferences about an entire city for
example, yet only ask people on one street, the sample size is too small and not representative
of all parts of the population.
In the summaries below, determine if the sample taken is representative of the population without
bias shown:
18. ABC Family is a television channel that targets families and young adults to view their station.
ABC Family regularly posts online poll questions to their website. In 2010, ABC Family polled
their viewers to ask about airing Rated “R” movies after 8pm on their channel. Almost 200,000
people responded, and 85% of them disagreed with airing Rated “R” movies.
Solution: Voluntary Response- ABC Family is only asking from data from their viewers, which may
tend to be more conservative since it is a family targeted television station.
19. Mrs. Jones wants to know how the 5th grade feels about recess time. Mrs. Jones labels every
student in the 5th grade with a number. She then draws 50 numbers out of a hat and surveys these
students. Mrs. Jones determines that 5th graders would like more recess time than they currently
have.
Solution: This is a Simple Random Sample (SRS). Mrs. Jones gave each child in the 5th grade the
same chance of being selected.
20. The City of Smallville wants to know how its citizens feel about a new industrial park in town.
Surveyors stand in the Smallville Mall from 8am-11am on a Tuesday morning and ask people
their opinion. 80% of the surveyed people said they disagreed with a new industrial park.
Solution: This is convenience sampling. People at a mall are “easy to reach”, but not every individual
in Smallville has an equal chance of being chosen. For example, people that work and are not at the
mall on Tuesday morning have no chance of being chosen.
21. The National Rifle Association (NRA) took a poll on their website, www.nra.com, and asked the
question, “Do you agree with the 2nd Amendment: the Right to Bear Arms”? 98% of the people
surveyed said “Yes”, and 2% said “No”.
Solution: This is voluntary response. The NRA only asked people on their website, which are more
likely to be “pro 2nd amendment.”
Is it Valid?
As you enter the room, please complete the five survey questions posed by your teacher.
PART I
A survey is a method of collecting information. These pieces of information, numbers and facts, are
called data.
1. What color is your hair? Brown ______ Blond ______ Red ______ Black _______
3. About how many text messages do you send in a day? 0-20 _____ 21-40 ______ >40 ______
4. About how much time do you spend on homework? 0-15 min _____ 16-30 min _____ 31-45 min ______
46-60 min _______ > 60 min ______
5. What month were you born? Jan – March _____ April – June _____ July-Sept. ____ _Oct-Dec
______
8. How would you record your results from question 1 as a piece of data?
9. How would you describe your results from question 2 as a parameter for the population?
For each of the problems below, answer the questions in regard to population, samples, and
surveys.
After the 2000 census, the United States Census Bureau reported that 7.4% of
Georgia residents were between the ages of 10 and 14.
10. Was a parameter or a statistic reported? Explain your reasoning.
The manager of the Millcreek Mall wants to know the mean age of the people who shop at the mall and
the stores in which they typically shop. He hires Barker Market Research Company to collect the data.
Dennis works for the Barker Market Research Company and has been put in charge of collecting data
for the Millcreek Mall. Dennis decides to interview 100 people one Saturday because it is the mall’s
busiest shopping day.
PART II
There are three key things to look for when determining if a survey is biased.
15. Is the survey voluntary?
In the summaries below, determine if the sample taken is representative of the population, without
bias shown:
18. ABC Family is a television channel that targets families and young adults to view their station.
ABC Family regularly posts online poll questions to their website. In 2010, ABC Family polled
their viewers to ask about airing Rated “R” movies after 8pm on their channel. Almost 200,000
people responded, and 85% of them disagreed with airing Rated “R” movies.
19. Mrs. Jones wants to know how the 5th grade feels about recess time. Mrs. Jones labels every
student in the 5th grade with a number. She then draws 50 numbers out of a hat and surveys these
students. Mrs. Jones determines that 5th graders would like more recess time than they currently
have.
20. The City of Smallville wants to know how its citizens feel about a new industrial park in town.
Surveyors stand in the Smallville Mall from 8am-11am on a Tuesday morning and ask people
their opinion. 80% of the surveyed people said they disagreed with a new industrial park.
21. The National Rifle Association (NRA) took a poll on their website, www.nra.com, and asked the
question, “Do you agree with the 2nd Amendment: the Right to Bear Arms”? 98% of the people
surveyed said “Yes”, and 2% said “No”.
In this task, students will determine how many tiles of each color are on the screen.
MGSE7.SP.1 Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are valid
only if the sample is representative of that population. Understand that random sampling tends to
produce representative samples and support valid inferences.
MGSE7.SP.2 Use data from a random sample to draw inferences about a population with an
unknown characteristic of interest. Generate multiple samples of the same size to gauge the variation
in estimates or predictions.
COMMON MISCONCEPTIONS
• Students may believe that one random sample is not representative of the entire population.
Many samples must be taken in order to make an inference that is valid. By comparing the
results of one random sample with the results of multiple random samples, students can correct
this misconception.
ESSENTIAL QUESTIONS
• How can random samples be used to make predictions about populations?
• How are proportions used to estimate information about populations?
MATERIALS
• Snapshot flipchart
https://drive.google.com/file/d/0B0S_r7_2OlzNSEoxVnU0OVh3QlE/edit?usp=sharing (works
with Promethean, SMART board and Mimio)
• Snap cubes or linking cubes or centimeter cubes
GROUPING
Small Groups
TASK DESCRIPTION
Open the Snapshot flipchart. Ensure the Spotlight tool has been selected (the screen should be black
with a circular view of the images
hidden). https://drive.google.com/file/d/0B0S_r7_2OlzNSEoxVnU0OVh3QlE/edit?usp=sharing
A snapshot freezes a moment in time. A series of snapshots becomes a picture record of an event. For
this task, you'll use Snap Cubes within a flipchart to create snapshots.
Snapshot
A snapshot freezes a moment in time. A series of snapshots becomes a picture record of an event. For
this task, you'll use Snap Cubes within a flipchart to create snapshots.
Use your data to predict how many of each color there are in the chart. Be ready to show your data and
explain how you arrived at your prediction.
Write whether or not your prediction was reasonably accurate. What would you do differently next
time, if anything, to make a closer prediction?
In this task, students will draw inferences about a population of M&Ms based upon random samples of
M&Ms using proportional reasoning developed in unit three.
MGSE7.SP.1 Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are valid
only if the sample is representative of that population. Understand that random sampling tends to
produce representative samples and support valid inferences.
MGSE7.SP.2 Use data from a random sample to draw inferences about a population with an
unknown characteristic of interest. Generate multiple samples of the same size to gauge the variation
in estimates or predictions.
BACKGROUND KNOWLEDGE
In order for students to be successful, the following skills and concepts need to be maintained:
*It is very important that students already know how to set up a proportion in order to solve this
task. This is not a learning task, but a performance task that helps to further develop student
reasoning about samples and populations not proportions.
COMMON MISCONCEPTIONS
• Students may believe that one random sample is not representative of the entire population.
Many samples must be taken in order to make an inference that is valid. By comparing the
results of one random sample with the results of multiple random samples, students can correct
this misconception.
ESSENTIAL QUESTIONS
• How can random samples be used to make predictions about populations?
• How are proportions used to estimate information about populations?
• How do I determine an appropriate sample size?
MATERIALS
• M&Ms *Trial Sized may be easier
• Small plastic bags
• Paper plates or paper towels
• Task Sheet
GROUPING
Small Groups
TASK DESCRIPTION
Begin the lesson with a Number Talk. Number talks are a great way for students to use mental math to
solve and explain a variety of math problems. A Number Talk is a short, ongoing daily routine that
provides students with meaningful ongoing practice with computation. Number Talks should be
structured as short sessions alongside (but not necessarily directly related to) the ongoing math
curriculum. It is important to keep Number Talks short, as they are not intended to replace current
curriculum or take up the majority of the time spent on mathematics.
In fact, teachers need to spend only 5 to 15 minutes on Number Talks. Number Talks are most effective
when done every day. As previously stated, the primary goal of Number Talks is computational fluency.
Students develop computational fluency while thinking and reasoning like mathematicians. When they
share their strategies with others, they learn to clarify and express their thinking, thereby developing
mathematical language. This in turn serves them well when they are asked to express their mathematical
processes in writing. In order for students to become computationally fluent, they need to know
particular mathematical concepts that go beyond what is required to memorize basic facts or procedures.
All Number Talks follow a basic six-step format. The format is always the same, but the problems and
models used will differ for each number talk.
1. Teacher presents the problem. Problems are presented in a word problem or a written algorithm.
2. Students figure out the answer. Students are given time to figure out the answer. To make sure
students have the time they need, the teacher asks them to give a “thumbs-up” when they have
determined their answer. The thumbs up signal, given at chest level, is unobtrusive- a message to the
teacher, not the other students.
3. Students share their answers. Four or five students volunteer to share their answers and the teacher
records them on the board.
4. Students share their thinking. Three or four students volunteer to share how they got their answers.
(Occasionally, students are asked to share with the person(s) sitting next to them.) The teacher
records the student's thinking.
5. The class agrees on the "real" answer for the problem. The answer that together the class determines is
the right answer is presented as one would the results of an experiment. The answer a student comes
up with initially is considered a conjecture. Models and/or the logic of the explanation may help a
student see where their thinking went wrong, may help them identify a step they left out, or clarify a
point of confusion. There should be a sense of confirmation or clarity rather than a feeling that each
problem is a test to see who is right and who is wrong. A student who is still unconvinced of an
answer should be encouraged to keep thinking and to keep trying to understand. For some students, it
may take one more experience for them to understand what is happening with the numbers and for
others it may be out of reach for some time. The mantra should be, "If you are not sure or it doesn't
make sense yet, keep thinking."
6. The steps are repeated for additional problems.
Similar to other procedures in your classroom, there are several elements that must be in place to
ensure students get the most from their Number Talk experiences. These elements are:
1. A safe environment
2. Problems of various levels of difficulty that can be solved in a variety of way
3. Concrete models
4. Opportunities to think first and then check
5. Interaction
6. Self-correction
For this Number Talk, begin with the following problem, “What is 0.75 as a percent?” Record the
problem on the far left side of the board. Provide students with wait time as they work to mentally solve
this problem. When majority of the students have given the “thumbs up” signal, call on several students
(3-4) to share their answer and the strategy they used to solve. Record the information provided by the
students exactly how it is told to you. It is important to allow students ownership of their thinking.
Record, “What is ¾ as a percent?” on the board next to the previous problem. Provide students with
wait time as they work to mentally solve this problem. When majority of the students have given the
“thumbs up” signal, call on several students (3-4) to share their answer and the strategy they used to
solve. Record the information provided by the students exactly how it is told to you.
Record, “What is 0.5 as a percent?” on the board towards the right. Provide students with wait time as
they work to mentally solve this problem. When majority of the students have given the “thumbs up”
signal, call on several students (3-4) to share their answer and the strategy they used to solve. Record
the information provided by the students exactly how it is told to you.
Record, “What is 15/30 as a percent?” on the board towards the far right. Provide students with wait
time as they work to mentally solve this problem. When majority of the students have given the
“thumbs up” signal, call on several students (3-4) to share their answer and the strategy they used to
solve. Record the information provided by the students exactly how it is told to you.
At the end of the Number Talk, discuss the strategies used to find the answers. The purpose of this
number talk is to discuss and develop strategies for converting decimals and fractions to percent. Some
of the strategies students may use are setting up proportions and finding the unknown, multiplying the
decimal with 100, use properties of place value to determine the percent is 100 times greater than the
number and changing the fraction to a decimal and multiplying by 100. Talk with the students about
which strategy was most efficient (quick, easy and accurate).
Allow for a maximum of 15 minutes to conduct the Number Talk before moving into the lesson.
M&M Populations
NOTE: The following solutions are based upon a group of five sets of 10 M&Ms. Numbers will vary
depending on sample sizes that teachers create for their students.
1. Count the number of EACH color of M&Ms and record your answers in a frequency table. Make
sure to label your frequency table clearly.
Solution:
Students may choose a variety of different frequency tables, including a tally chart or line plot.
2. Using the results from your group, fill in the following chart and find the number of M&Ms for
each person in your group and the total number of M&Ms.
Find the percentage of each color of M&Ms for your sample.
Orange 1 1 2 1 1 6 𝟔
=12%
𝟓𝟎
Yellow 1 1 1 2 1 6 𝟔
=12%
𝟓𝟎
Green 1 2 1 1 2 7 𝟕
=14%
𝟓𝟎
Blue 1 3 2 1 1 8 𝟖
=16%
𝟓𝟎
Brown 4 2 1 2 3 12 𝟏𝟐
=24%
𝟓𝟎
Total 10 10 10 10 10 50 100%
Number
of
M&Ms
in
Sample
4. Do you think your sample could predict the number of M&Ms in a larger bag? Why or why not?
Yes, because we have a small, random sample that we can use to make predictions for a larger
bag of M&Ms, as long as they are the same kind of M&Ms.
*Teachers should point out that samples need to be representative. For example, it does not
make sense to use Mini-M&Ms to estimate for a large bag of Peanut M&Ms.
5. Do you think that the percentages of each color of M&Ms are the same as other groups? Why or
why not?
No. Other groups received different samples of M&Ms. Percents may be close to one another
but they will not be the exact same.
6. Using your data values, estimate the number of M&Ms for EACH color for a bag of 1000
candies. (Hint: Use a proportion)
Students will use proportional reasoning to estimate the different percentages of each M&M
color in a given population.
It is important to help students recognize that this type of reasoning is ONLY truly valid when
using valid, random samples.
NOTE: The following solutions are taken from the above samples. Answers will vary as
students use varying sample sizes and amounts
Orange 𝟔 𝒙
=
𝟓𝟎 𝟏𝟎𝟎𝟎
𝟓𝟎𝒙 = 𝟔(𝟏𝟎𝟎𝟎)
𝟓𝟎𝒙 = 𝟔𝟎𝟎𝟎
𝟔𝟎𝟎𝟎
𝒙= = 𝟏𝟐𝟎 M&Ms
𝟓𝟎
Yellow 𝟔 𝒙
=
𝟓𝟎 𝟏𝟎𝟎𝟎
𝟓𝟎𝒙 = 𝟔(𝟏𝟎𝟎𝟎)
𝟓𝟎𝒙 = 𝟔𝟎𝟎𝟎
𝟔𝟎𝟎𝟎
𝒙= = 𝟏𝟐𝟎 M&Ms
𝟓𝟎
Green 𝟕 𝒙
=
𝟓𝟎 𝟏𝟎𝟎𝟎
𝟓𝟎𝒙 = 𝟕(𝟏𝟎𝟎𝟎)
𝟓𝟎𝒙 = 𝟕𝟎𝟎𝟎
𝟕𝟎𝟎𝟎
𝒙= = 𝟏𝟒𝟎 M&Ms
𝟓𝟎
Blue 𝟖 𝒙
=
𝟓𝟎 𝟏𝟎𝟎𝟎
𝟓𝟎𝒙 = 𝟖(𝟏𝟎𝟎𝟎)
𝟓𝟎𝒙 = 𝟖𝟎𝟎𝟎
𝟖𝟎𝟎𝟎
𝒙= = 𝟏𝟔𝟎 M&Ms
𝟓𝟎
Brown 𝟏𝟐 𝒙
=
𝟓𝟎 𝟏𝟎𝟎𝟎
𝟓𝟎𝒙 = 𝟏𝟐(𝟏𝟎𝟎𝟎)
𝟓𝟎𝒙 = 𝟏𝟐𝟎𝟎𝟎
𝟏𝟐𝟎𝟎𝟎
𝒙= = 𝟐𝟒𝟎 M&Ms
𝟓𝟎
DIFFERENTIATION
Extension
• Have students create an accurate circle (pie) graph to represents the percentages of each sample
and compare them between each sample group to discuss random sampling
• Students can create a circle graph in Excel using data entries found in this task, and also use the
same method to create circle graphs for the entire population of M&Ms to make comparisons
Intervention
• Small groups can be given examples to help guide them through this performance task
• Sample sizes and population sizes can be adjusted to help guide students through this task
Candy Populations
1. Count the number of EACH color of candies and record your answers in a frequency table. Make
sure to label your frequency table clearly.
2. Using the results from your group, fill in the following chart and find the number of M&Ms for
each person in your group and the total number of M&Ms.
Find the percentage of each color of M&Ms for your sample.
Orange
Yellow
Green
Blue
Brown
Total
Number
of
M&Ms
in
Sample
4. Do you think your sample could predict the number of M&Ms in a larger bag? Why or why not?
5. Do you think that the percentages of each color of M&Ms are the same as other groups? Why or
why not?
6. Using your data values, estimate the number of M&Ms for EACH color for a bag of 1000
candies. Record your data in the table below.
Orange
Yellow
Green
Blue
Brown
In this task, students will use populations, samples, and proportions in order to make predictions about
total population size.
STANDARDS FOR MATHEMATICAL CONTENT
MGSE7.SP.1 Understand that statistics can be used to gain information about a population by
examining a sample of the population. Understand that random sampling tends to produce
representative samples and support valid inferences.
MGSE7.SP.2 Use data from a random sample to draw inferences about a population with an unknown
characteristic of interest. Generate multiple samples of the same size to gauge the variation in estimates
or predictions.
STANDARDS OF MATHEMATICAL PRACTICES
1. Make sense of problems and persevere in solving them.
2. Reason abstractly and quantitatively.
3. Construct viable arguments and critique the reasoning of others.
6. Attend to precision.
7. Look for and make use of structure.
COMMON MISCONCEPTIONS
Students struggle with determining how many items should be in a sample space in order for it to reflect
the given population.
BACKGROUND KNOWLEDGE
In a previous unit, students studied how to set up and solve proportions. They will need this information
in order to solve and make predictions.
ESSENTIAL QUESTIONS
MATERIALS
• Predicting Populations Student Sheet
• Paper bag with a 40 fish crackers in it
• Black Marker
GROUPING
TASK DESCRIPTION
If the population size of a group is unknown, the sample size can be used to make predictions and
calculate this number. When predicting deer population, a group of deer are captured, marked, and then
distributed back into the population. Later, a sample is taken and the number of marked deer is
compared to the total number of deer in the sample. A proportion can be set up to find the ratio of
marked deer to total sample deer.
For example:
A forest has too many deer for us to count. We take a group of 100 deer and mark them then distribute
them evenly throughout the population. Several days pass, then we take a sample of 120 deer and find
that 20 of them are marked. We can set up a proportion to calculate the total population size.
20 100
i.e. = x = 100(120) / 20
120 𝑥
Goldfish Lab
You have a bag with fish crackers in it. We are going to “tag” a sample of the fish and make a
prediction about the total population of fish found in the bag.
1. Remove 10 crackers from the bag.
2. Tag them by marking on them with a marker.
3. Put the fish back in the bag and shake them up.
4. Remove 20 fish crackers.
5. Set up a proportion and make a prediction for how many fish are in the bag total.
𝟒 𝒕𝒂𝒈𝒈𝒆𝒅 𝟏𝟎
𝒊. 𝒆. = ; 𝒙 = 𝟓𝟎 is the estimated population
𝟐𝟎 𝒊𝒏 𝒕𝒉𝒆 𝒔𝒂𝒎𝒑𝒍𝒆 𝒙
We will fill in the following chart based on the data from each group.
1. What is the average estimated population for your class? Find the mean of the last column.
2. Count the number of fish in the bag. What was the actual population size? 40
3. Is this a census or a survey? Justify your response. This is a survey since you take a part of the
population.
4. What is your percent of error based on the estimated population and actual population?
6. If there is a population of 800 deer, what would be a good sample size? Justify your answer.
25 – 40% of the population makes a good sample size. So you would need about 200 deer in
your sample group.
Goldfish Lab
You have a bag with fish crackers in it. We are going to “tag” a sample of the fish and make a
prediction about the total population of fish found in the bag.
We will fill in the following chart based on the data from each group.
2. Count the number of fish in the bag. What was the actual population size?
4. What is your percent of error based on the estimated population and actual population?
6. If there is a population of 800 deer, what would be a good sample size? Justify your answer.
MGSE7.SP.1. Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are valid only if
the sample is representative of that population. Understand that random sampling tends to produce
representative samples and support valid inferences.
MGSE7.SP.2. Use data from a random sample to draw inferences about a population with an unknown
characteristic of interest. Generate multiple samples (or simulated samples) of the same size to gauge the
variation in estimates or predictions. For example, estimate the mean word length in a book by randomly
sampling words from the book; predict the winner of a school election based on randomly sampled
survey data. Gauge how far off the estimate or prediction might be.
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions with
similar variabilities, measuring the difference between the medians by expressing it as a multiple of the
interquartile range.
MGSE7.SP.4. Use measures of center and measures of variability for numerical data from random
samples to draw informal comparative inferences about two populations. For example, decide whether
the words in a chapter of a seventh-grade science book are generally longer than the words in a chapter
of a fourth-grade science book.
TASK COMMENTS
Tasks and lessons from the Mathematics Assessment Project are specifically designed to help teachers
effectively formatively assess their students. The way the tasks and lessons are designed gives the
teacher a clear understanding of what the students are able to do and not do. Within the lesson, teachers
will find suggestions and question prompts that will help guide students towards understanding. For
more information access the MAP website:
http://www.map.mathshell.org/materials/background.php?subpage=summative
The task, Counting Trees, is a Mathematics Assessment Project Assessment Task that can be found at
the website: http://www.map.mathshell.org/materials/tasks.php?taskid=386&subpage=expert
The PDF version of the task can be found at the link below:
http://www.map.mathshell.org/materials/download.php?fileid=1148
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions with
similar variabilities, measuring the difference between the medians by expressing it as a multiple of the
interquartile range.
ESSENTIAL QUESTIONS
• How does the data describe its center, spread, and representation of the population?
• How do I display data on a number line?
MATERIALS
• String
• Index cards
GROUPING
Whole Group
TASK COMMENTS:
This task serves as a mini-lesson on constructing a box plot. The following activity can be used as a
mini lesson for the Shakespeare vs. Harry Potter task.
TASK DESCRIPTION
The following numbers represent the ages in months of a class of 7th graders.
Boys
142 125
134 147
137 131
139 129
Girls
140 131
129 128
141 131
134
Instruct students to create a stem and leaf plot (extension) or any other method to organize their data for
all students using the data above.
All students
12 5, 8, 9, 9
13 1,1,1,4,4,7,9
14 0,1,2,7
Assign students in the class a number from the data above. Have students line up in order from least to
greatest. Have the students in the audience identify the median of the data (134). Label this data point
the median. Looking only at the lower half of the data, have students determine the median (129).
Inform students this is called the lower quartile or Q1, label this on the human display. Looking only at
the upper half of the data, have students determine the median (140). Inform students this is called the
upper quartile or Q3, label this on the human display.
Using string, create a box around Q1, median and Q3. Notate the two extreme data points (125, 147) as
the minimum and maximum. Using two pieces of string, stretch one piece from Q1 to the minimum and
the other string from Q3 to the maximum.
Ask the students in the audience to record the human display of a box plot in their notebooks. Be sure
the label the key components of the plot. Have students return to their seats, and reiterate the steps for
creating the box plot by reviewing the steps used in the demonstration.
Instruct students to complete the 5-number summary using the recreated box plot.
Minimum 125
Q1 129
Median 134
Q3 140
Maximum 147
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions with
similar variabilities, measuring the difference between the medians by expressing it as a multiple of the
interquartile range.
MGSE7.SP.4 Use measures of center and measures of variability for numerical data from random
samples to draw informal comparative inferences about two populations. For example, decide whether
the words in a chapter of a seventh‐grade science book are generally longer than the words in a chapter
of a fourth‐grade science book.
ESSENTIAL QUESTIONS
• How does the data describe its center, spread and representation of the population?
• What are ways to summarize numerical data set?
MATERIALS
• Shakespeare vs. Harry Potter Task Sheet
• Number cube
• Graphing Calculator (optional)
GROUPING
Small Group
TASK COMMENTS:
Prior to the task, students may need a mini-lesson about the following concepts: box plots, dot plots, 5-
number summary and interquartile range.
TASK DESCRIPTION
Many skeptics feel that there has been a “dumbing down” of America’s youth of the past decades. To
determine if there is any truth to this claim, we will compare two pieces of literature: Shakespeare’s
Macbeth and JK Rowling’s Harry Potter and the Chamber of Secrets.
Is there a difference in the length of the words used in a Shakespeare play compared to a Harry Potter
book? Today you will sample words from both pieces of literature to determine who used longer words.
Below are excerpts from a Shakespeare Novel and a Harry Potter book.
Follow the steps below to determine which piece of literature uses longer words.
1. Roll a number cube once for each line of Macbeth below. Move to the word that corresponds to
the number you roll (1 = first word in the line, 2 = second word in the line, etc.).
2. Count the letters in that word, and record the number in the table below in the “Letter Count”
columns.
Sample:
Line Number Letter Line Number Letter
Count Count
1 6 9
2 9 10
3 12 11
4 10 12
5 4 13
6 7 14
7 15
8
Comment: student data will vary because they are using number cubes to generate the word that they
count letters for in each line.
3. Now, roll the number cube to see which words you will count in the Harry Potter excerpt. You
will count the letters in two words from each line. Roll the die and move to the word that
corresponds to that number. After counting the number of letters in that word, roll the dice again
and move to another word in the same line. Then, move to the next line and repeat the process
for each of the lines in the passage. Record your numbers in the chart that follows in the “Letter
Count” columns.
1. October arrived, spreading a damp chill over the grounds and into the
2. castle. Madam Pomfrey, the nurse, was kept busy by a sudden
3. spate of colds among the staff and students. Her Pepperup potion
4. worked instantly, though it left the drinker smoking at the ears for
5. several hours afterward. Ginny Weasley, who had been looking
6. pale, was bullied into take some by Percey. The steam pouring from
7. under her vivid hair gave the impression that her whole head was on fire.
Sample:
Line Number Letter Letter
Count Count
Word 1 Word 2
1 1 7
2 4
3 13
4 7
5 9
6 5
7 7
Comment: student data will vary because they are using number cubes to generate the word that they
count letters for in each line.
4. Find the mean of the Shakespeare word sample and the Harry Potter word sample. Do this by
adding the letter counts for both passages, separately. Then divide the sum for each passage by
the total number of words (15 for Shakespeare; 14 for Harry Potter).
Comment:
There may be more efficient ways of finding the mean (instead of the method below).
Solution: (sample)
Shakespeare:
𝒕𝒐𝒕𝒂𝒍 𝒍𝒆𝒕𝒕𝒆𝒓𝒔 𝒄𝒐𝒖𝒏𝒕𝒆𝒅 𝟔 + 𝟗 + 𝟏𝟐 + 𝟏𝟎 + 𝟒 + 𝟕 + ⋯ 𝟏𝟐𝟎
= =
# 𝒐𝒇 𝒘𝒐𝒓𝒅𝒔 𝒄𝒐𝒖𝒏𝒕𝒆𝒅 𝟏𝟓 𝟏𝟓
= 𝟖 𝒍𝒆𝒕𝒕𝒆𝒓𝒔⁄𝒘𝒐𝒓𝒅
Harry Potter:
𝒕𝒐𝒕𝒂𝒍 𝒍𝒆𝒕𝒕𝒆𝒓𝒔 𝒄𝒐𝒖𝒏𝒕𝒆𝒅 𝟏 + 𝟒 + 𝟏𝟑 + 𝟕 + 𝟗 + 𝟓 + 𝟕 + 𝟕 + ⋯
=
# 𝒐𝒇 𝒘𝒐𝒓𝒅𝒔 𝒄𝒐𝒖𝒏𝒕𝒆𝒅 𝟏𝟒
𝟏𝟐𝟔
= = 𝟗 𝒍𝒆𝒕𝒕𝒆𝒓𝒔⁄𝒘𝒐𝒓𝒅
𝟏𝟒
5. Find the five number summary using the data you found for Shakespeare and Harry Potter.
Enter your data into the table below:
Sample:
Shakespeare Harry Potter
Minimum 1 Minimum 1
Q1 2 Q1 3
Median 3 Median 4.5
Q3 5 Q3 6
Maximum 8 Maximum 9
6. Create a box plot for the word counts you found for Shakespeare and Harry Potter. Make sure to
label your number line:
Solution:
7. Looking at the box plots and the mean, would you agree that there has been a “dumbing down”
of America’s youth over the past decades? Support your answer with numerical data you found
in steps #4-8.
Solution: The overall mean number of words was higher for Harry Potter (4.68) as compared to
Shakespeare’s mean of 3.54. Each piece of literature shared the minimum value of 1, but Harry
Potter’s maximum value was higher than Shakespeare. With is evidence, it is clear that there has not
been a “dumbing down” of America’s youth.
8. Do you believe the comparison above could help you conclude the word counts for ALL Harry
Potter and Shakespeare Literature? Why or why not?
Solution: Since each Harry Potter novel and each piece of literature by Shakespeare varies, it is not
wise to conclude that the words counts would be similar for other types of literature written by these
authors. A sample taken from another book or poem may yield different answers.
DIFFERENTIATION
• Extension
If available, students can use graphing calculators to input the five number summary and create
the double box-and-whisker plot.
• Intervention: Students can create individual box-and-whisker plots for each piece of literature
before creating the double box-and-whisker plot. These images are from a graphing calculator;
students should add numbers to their number lines when they create their own box-and-whisker
plots.
3. Now, roll the number cube to see which words you will count in the Harry Potter excerpt. You
will count the letters in two words from each line. Roll the die and move to the word that
corresponds to that number. After counting the number of letters in that word, roll the dice again
and move to another word in the same line. Then, move to the next line and repeat the process
for each of the lines in the passage. Record your numbers in the chart that follows in the “Letter
Count” columns.
1. October arrived, spreading a damp chill over the grounds and into the
2. castle. Madam Pomfrey, the nurse, was kept busy by a sudden
3. spate of colds among the staff and students. Her Pepperup potion
4. worked instantly, though it left the drinker smoking at the ears for
5. several hours afterward. Ginny Weasley, who had been looking
6. pale, was bullied into take some by Percey. The steam pouring from
7. under her vivid hair gave the impression that her whole head was on fire.
Harry Potter:
Line Number Letter Letter
Count Count
Word 1 Word 2
1
2
3
4
5
6
7
4. Find the mean (𝑥̅ ) of the Shakespeare word sample and the Harry Potter word sample. Do this
by adding the letter counts for both passages, separately. Then divide the sum for each passage
by the total number of words (15 for Shakespeare; 14 for Harry Potter).
5. Find the five number summary using the data you found for Shakespeare and Harry Potter.
Enter your data into the table below:
6.Create a box plot for the word counts you found for Shakespeare and Harry Potter. Make sure
to label your number line:
7.Looking at the box plots and the mean, would you agree that there has been a “dumbing down” of
America’s youth over the past decades? Support your answer with numerical data you found in steps #4-
8. Do you believe the comparison above could help you conclude the word counts for ALL Harry Potter
and Shakespeare Literature? Why or why not?
• Utilize what they know about box and whisker plots to evaluate sets of data
• Assimilate multiple sets of data related to a single entity, and combine this data in order to make
value judgments about that entity, particularly when the information found in the data seems to
be contradictory
• Compare entities and make decisions about “good,” “better,” and “best” based upon distribution
of summary data (medians, quartiles, interquartile range, and the interaction between different
types of data).
MGSE7.SP.4 Use measures of center and measures of variability for numerical data from random
samples to draw informal comparative inferences about two populations. For example, decide whether
the words in a chapter of a seventh-grade science book are generally longer than the words in a chapter
of a fourth-grade science book.
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions with
similar variabilities, measuring the difference between the medians by expressing it as a multiple of the
interquartile range.
COMMON MISCONCEPTIONS
Students have difficulties distinguishing between measures of center and measures of variability.
It is essential to focus questions on the context of the situation and seeing what can be learned or
inferred from the data. In addition, the questions should focus on the key ideas of statistics, such as
variability, center of the data, and shape of the data.
ESSENTIAL QUESTIONS
• How does the data describe its center, spread and representation of the population?
• What is the difference between the measure of center and measure of variation?
MATERIALS
GROUPING
Individual/Partner
TASK COMMENTS
Prior to completing the task, teachers may need to review box plots, dot plots, interquartile range,
measures of center, and measures of variability.
TASK DESCRIPTION
TE Learning Task: Got Friends?
Is there a difference between the number of programmed numbers in the number of programmed
telephone numbers in girls’ cell phones and the number in boys’ cell phones?
When Mrs. Causey, an AP Statistics teacher at Olviedo High School in Seminole County, Florida,
polled her students, she got the following data:
Males 5 20 26 40 46 47 49 50 51
51 56 57 60 61 68 71 72 72 73
74 75 82 82 84 86 97 100 100 104
104 106 124 171 205 207 232 360
Females 20 46 50 58 62 65 70 72 72
80 86 87 88 90 92 94 94 109 112
114 116 122 125 129 137 137 138 142 142
149 163 170 186 199 204 249
Solution:
Males Females
Minimum 5 Minimum 12
Q1 51 Q1 72
Median 73 Median 101.5
Q3 102 Q3 140
Maximum 360 Maximum 249
3. Create side-by-side (stacked) box plots for the two sets of data above.
If there are not graphing calculators available, have the students find the statistics by hand that
are required for the 5 Number Summary. (using the median)
Solution:
The Males are represented by the box plot on the top, females on the bottom.
4. Compare the box plots above. Do you notice a difference in their shape, center, and spread?
Solution:
Shape: the female’s box plot is more symmetric, with the median lying approximately in the middle of
the box. The whiskers also appear to be approximately equal in length. This leads to the conclusion
that the female distribution is symmetric. There appears to be no outliers. The male distribution is
much more skewed. The right whisker is very long, which means it is reaching out to a potential
outlier in the male data (360).
Center (median): The center for the males is 73, while the center for the females is 101.5. This means
that females seem to have more numbers programmed in their phone than males.
Spread: The spread of the males is much greater than for females. This is due to extreme values on
the upper end of the male data.
5. Which gender group has the greater interquartile range? Does this align with the group with the
most programmed phone numbers?
The IQR for the males is 51, the IQR for the females is 68.
6. It is important that you have “data integrity”. For example, it is important that data be reported
accurately and truthfully. Do you think that this is the case here? Do you see any suspicious
observations?
Solution:
There appears to be a suspicious value in the male data. 360 programmed numbers seems to be well
outside the range of the other values.
7. Can you think of any reason someone might make up a response or “stretch the truth” in
reporting his or her number of programmed telephone numbers?
Solution:
Students may feel the need to exaggerate their answers due to peer pressure of classmates. Good
sampling techniques, such as writing out the numerical amount, instead of calling it out in front of
the class, may help produce more accurate results.
8. If you DO see a difference between the two groups, can you suggest a possible reason for that
difference?
Solution:
Females tend to have more numbers in their phone. Females may be more likely to talk on the phone,
which could lead to more programmed numbers in their phone. The parents of females may have
given them a cell phone earlier to use for safety reasons.
9. Do you think that a study of cell phone programmed numbers for a 7th grade math class would
yield similar results? Why or why not?
Solution:
No. The data for 7th grade may yield the same shape of distribution, but the amount of programmed
numbers may increase with the grade level.
DIFFERENTIATION
Extension
• Ask students to generate data points that will change the box and whisker plots significantly
and explain why such changes would affect the numbers for the box and whisker plots.
Intervention
• Work through the 5 Number Summary - boys or girls with the students and let them do the
other 5 Number Summary by themselves. The 5 Number Summary was introduced in 6th
grade.
Got Friends?
Is there a difference between the number of programmed numbers in the number of programmed
telephone numbers in girls’ cell phones and the number in boys’ cell phones?
When Mrs. Causey, an AP Statistics teacher at Olviedo High School in Seminole County, Florida,
polled her students, she got the following data:
Males 5 20 26 40 46 47 49 50 51
51 56 57 60 61 68 71 72 72 73
74 75 82 82 84 86 97 100 100 104
104 106 124 171 205 207 232 360
Females 20 46 50 58 62 65 70 72 72
80 86 87 88 90 92 94 94 109 112
114 116 122 125 129 137 137 138 142 142
149 163 170 186 199 204 249
Males Females
Minimum Minimum
Q1 Q1
Median Median
Q3 Q3
Maximum Maximum
3. Create side-by-side (stacked) box plots for the two sets of data above.
4. Compare the box plots above. Do you notice a difference in their shape, center, and spread?
5. Which gender group has the greater interquartile range? Does this align with the group with the
most programmed phone numbers?
6. It is important that you have “data integrity”? For example, it is important that data be reported
accurately and truthfully. Do you think that this is the case here? Do you see any suspicious
observations?
7. Can you think of any reason someone might make up a response or “stretch the truth” in reporting
his or her number of programmed telephone numbers?
8. If you DO see a difference between the two groups, can you suggest a possible reason for that
difference?
9. Do you think that a study of cell phone programmed numbers for a 7th grade math class would
yield similar results? Why or why not?
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data distributions with
similar variabilities, measuring the difference between the medians by expressing it as a multiple of the
interquartile range.
MGSE7.SP.4. Use measures of center and measures of variability for numerical data from random
samples to draw informal comparative inferences about two populations. For example, decide whether
the words in a chapter of a seventh-grade science book are generally longer than the words in a chapter
of a fourth-grade science book.
COMMON MISCONCEPTIONS
• Students do not understand the difference between measures of center and measures of
variability
• Students believe that the mean is always the best, even though the median can be a better
measure
ESSENTIAL QUESTIONS
• How does the data describe its center, spread and representation of the population?
• What is the difference between the measure of center and measure of variation?
MATERIALS
• Student Task Sheet
• Calculators (Optional) *Use to efficiently calculate mean
GROUPING
Individual / Partners
TASK COMMENTS
Sample scenarios or problems may need to be discussed for students to make comparisons about the two
measures and determine which set of measures is best to use.
TASK DESCRIPTION
Here are the travel times from home to work in minutes for 15 workers in North Carolina, chosen at
random by the Census Bureau:
5 10 10 10 10 12 15 20 20 25 30 30 40 40 60
Solution:
𝟓 + 𝟏𝟎 + 𝟏𝟎 + 𝟏𝟎 + 𝟏𝟎 + 𝟏𝟐 + 𝟏𝟓 + 𝟐𝟎 + 𝟐𝟎 + 𝟐𝟓 + 𝟑𝟎 + 𝟑𝟎 + 𝟒𝟎 + 𝟒𝟎 + 𝟔𝟎 𝟑𝟑𝟕
𝒎𝒆𝒂𝒏 = = = 𝟐𝟐. 𝟒𝟕 𝒎𝒊𝒏𝒖𝒕𝒆𝒔
𝟏𝟓 𝟏𝟓
Here are the travel times in minutes of 19 randomly chosen New York workers:
5 10 15 15 15 15 20 20 20 20 30 30 40 40 45 60 60 65 85
Solution:
𝟓 + 𝟏𝟎 + 𝟏𝟓 + 𝟏𝟓 + 𝟏𝟓 + 𝟏𝟓 + 𝟐𝟎 + 𝟐𝟎 + 𝟐𝟎 + 𝟐𝟎 + 𝟑𝟎 + 𝟑𝟎 + 𝟒𝟎 + 𝟒𝟎 + 𝟒𝟓 + 𝟔𝟎 + 𝟔𝟎 + 𝟔𝟓 + 𝟖𝟓
𝒎𝒆𝒂𝒏 =
𝟏𝟗
𝟔𝟏𝟓
= = 𝟑𝟐. 𝟏 𝒎𝒊𝒏𝒖𝒕𝒆𝒔
𝟏𝟗
3. Compare the two means. Which state has a longer travel time when comparing the means?
Solution:
New York travel times are almost 10 minutes higher than North Carolina travel times.
4. Find the median of the North Carolina and New York travel times.
5. Compare the medians. Which state has a longer travel time when comparing the medians?
Solution:
Both states have a median travel time of 20 minutes.
6. Looking at the New York travel times, which number(s) affect the mean, but not the median?
Solution:
The extremely high numbers affect the mean. Numbers such as 65 and 85 pull the mean higher, but
do not affect the median. The median is the middle number, and is not influenced by high and low
numbers.
Find the Interquartile Range (IQR) of the North Carolina and New York travel times. What does the
IQR tell you about each set of data?
North Carolina:
a) Find the distance that upper quartile is away from the lower quartile.
Solution:
Look back at the original values given for North Carolina Drivers.
Find the value of Q3 and Q1. Subtract the value of Q1 from Q3.
30-10= 20
IQR is 20
New York:
a) Find the distance that upper quartile is away from the lower quartile.
Solution:
Look back at the original values of travel times for New York.
Find the value of Q3 and Q1. Subtract the value of Q1 from Q3.
45-15= 30
IQR is 30
8. Overall, which measure of center best describes travel time to work, the mean or the median?
Why?
Solution:
The mean is the best measure of center. In this scenario, the mean shows the variation between the
travel times better than the median. Since the medians are the same, the median can be deceiving in
thinking that the travel times are equivalent for each state.
Here are the travel times from home to work in minutes for 15 workers in North Carolina, chosen at
random by the Census Bureau:
5 10 10 10 10 12 15 20 20 25 30 30 40 40 60
Here are the travel times in minutes of 19 randomly chosen New York workers:
5 10 15 15 15 15 20 20 20 20 30 30 40 40 45 60 60 65 85
3. Compare the two means. Which state has a longer travel time when comparing the means?
4. Find the median of the North Carolina and New York travel times.
5. Compare the medians. Which state has a longer travel time when comparing the medians?
6. Looking at the New York travel times, which number(s) affect the mean, but not the median?
Find the Interquartile Range (IQR) of the North Carolina and New York travel times. What does the
IQR tell you about each set of data?
North Carolina:
a) Find the distance that upper quartile is away from the lower quartile.
New York:
a) Find the distance that upper quartile is away from the lower quartile.
8. Overall, which measure of center best describes travel time to work, the mean or the median?
Why?
MGSE7.SP.4. Use measures of center and measures of variability for numerical data from random
samples to draw informal comparative inferences about two populations. For example, decide whether
the words in a chapter of a seventh-grade science book are generally longer than the words in a chapter
of a fourth-grade science book.
ESSENTIAL QUESTIONS
• What are ways to summarize numerical data sets?
MATERIALS REQUIRED
Thumbs on Fire article http://www.cnn.com/2014/05/15/tech/mobile/guiness-record-fastest-text/
Teacher Notes
This task is designed around a specific context (the world record for texting) while allowing teachers the
flexibility of developing the procedures. In the task description below, one way of implementing this
task is described although there are many different ways in which this context could be used in a Math 7
class.
Task Description
Thumbs on Fire (Part 2)
Students may need to revisit the video clips from the Unit 3 task, Thumbs on Fire,
https://gfletchy.com/thumbs-on-fire/.
Have the students read the following article as an introduction to Part 2: Thumbs on Fire taken from
http://www.cnn.com/2014/05/15/tech/mobile/guiness-record-fastest-text/
It is clear from the article that companies are working to make smartphone keyboards faster, but which
one is fastest and how much faster is one than another? One possible option for this task is for students
to investigate two different types of phones and the speed in which a text message can be typed on each
phone. For instance, a class may want to compare the length of time it takes a given message to be typed
by Apple iPhone users to the length of time it takes Android users to type the same message. (The
message in the article is used by Guinness World Records but a different message could be used for this
task.)
Once the main question has been determined, the class will decide on appropriate ways to collect the
data.
• Should data be collected only on students in our school or should iPhone and Android users
outside our school be included?
• What is an appropriate sample size?
Regardless of the methods used to collect data, the class should engage in a conversation about the
validity of the samples taken recalling that conclusions can be drawn about a population only if the
sample represents that population.
After the data is collected, students should calculate appropriate measures of center and measures of
variability for the samples. Students should compare the two samples and be able to make inferences
about the two populations.
This task provides an excellent opportunity for students to utilize mathematical practice 3: Construct
viable arguments and critique the reasoning of others by writing about their conclusions and providing a
critique of their classmates’ conclusions.
This task requires that students calculate measures of center and variability to draw conclusions
about the effectiveness of two ambulance companies.
MGSE7.SP.1. Understand that statistics can be used to gain information about a population by
examining a sample of the population; generalizations about a population from a sample are
valid only if the sample is representative of that population. Understand that random sampling
tends to produce representative samples and support valid inferences.
MGSE7.SP.2. Use data from a random sample to draw inferences about a population with an
unknown characteristic of interest. Generate multiple samples (or simulated samples) of the same
size to gauge the variation in estimates or predictions. For example, estimate the mean word
length in a book by randomly sampling words from the book; predict the winner of a school
election based on randomly sampled survey data. Gauge how far off the estimate or prediction
might be.
MGSE7.SP.4. Use measures of center and measures of variability for numerical data from
random samples to draw informal comparative inferences about two populations. For example,
decide whether the words in a chapter of a seventh-grade science book are generally longer than
the words in a chapter of a fourth-grade science book.
ESSENTIAL QUESTION
• How is statistical data used in the real-world?
• How do I use data to make decisions or show evidence of an event occurring or not
occurring?
MATERIALS
• Student Task Sheet
• Graphing calculator or TI-30 XII (random number generator is needed)
TASK COMMENTS
Prior to completing the task, the teacher may want to do a mini-lesson with the graphing
calculator or TI-30 XII to teach students how to use the random integer function. Options to
replace using a calculator include using the computer (random integer site:
http://www.random.org/integers/) or put numbers in a container and draw numbers, replacing the
number after each draw.
Used with permission from Balanced Assessment: Middle Grades Package 1, Dale Seymour Publications
TASK DESCRIPTION
Last week there was an accident at the Waterfront Amusement Park in Bay City. A seat on one
of the rides broke loose, resulting in the deaths of two teenagers. The owners of the amusement
park have charged that if ambulances had responded more quickly, the two teens would have
survived. They have threatened to sue the Bay City 911 emergency service for failing to dispatch
ambulances efficiently.
The Bay City Council has hired your firm to conduct an independent investigation of the city’s
911-response to emergencies. The 911 operators dispatch from two companies: Arrow
Ambulance and Metro Ambulances.
The 911 operators aren’t always sure which company to send when an emergency call is
received.
Data on the response times for the two companies for an area of a one-mile radius of the
Amusement Park show that responses can take as little as 6 minutes or as long as 19 minutes.
You need to continue your investigation by analyzing the response time data on the next page.
Based on the information above and your analysis of the data, you conclude that the Bay City
Council needs to establish a policy about which service to call.
Using the steps below, you will discover which Ambulance Service would best serve the
Amusement Park.
• To find five random responses, you can use the Random Integer function on the
calculator (TI-30X II: press PRB, then RANDI (1, 16), press enter, one incident
number will appear) or put the numbers (1-16) in a container, draw a number, put
number back in container and repeat.
• Look up the corresponding incident number and record the response time below.
• Continue until you have found five response times for Arrow Ambulances.
Teacher Commentary: If you do not have access to enough calculators, you have options. You
can use 1 calculator and choose samples for everyone to use in class. This may make grading
the task easier if all students use the same values. Or, you can also put numbers in a bucket
and draw values from the bucket. Replace numbers once you have a group completed.
Sample Solution:
Random integers 10 1 5 11 7
Corresponding Time
17 11 16 7 17
minutes
1. Find 5 more random incidents and response times for Arrow Ambulances. Use the
procedure above, or continue to press enter to get 5 more random incidents for the groups
below. It is okay if an incident number repeats in one group.
Response times for 5 random Arrow incidents:
Randomized Group 2
Random integers
Corresponding Time
Sample Solution:
Random integers 10 8 1 6 13
Corresponding Time
17 6 11 8 17
minutes
Sample Solution:
Random integers 4 3 16 7 8
Corresponding Time
7 19 9 17 6
minutes
Sample Solution:
Random integers 15 6 4 1 5
Corresponding Time
8 8 7 11 16
minutes
Sample Solution:
Random integers 12 16 8 9 15
Corresponding Time
8 9 6 16 8
minutes
Group Mean
1
2
3
4
5
Total Mean of Groups 1-5
“the mean of the means”
Sample Solution:
Group Mean
1 68/5=13.6
2 59/5=11.8
3 58/5=11.6
4 50/5=10
5 47/5=9.4
Total Mean of Groups 1-5 𝟏𝟑. 𝟔 + 𝟏𝟏. 𝟖 + 𝟏𝟏. 𝟔 + 𝟏𝟎 + 𝟗. 𝟒 𝟓𝟔. 𝟒
= = 𝟏𝟏. 𝟐𝟖 𝒎𝒊𝒏𝒖𝒕𝒆𝒔
𝟓 𝟓
“the mean of the means”
3. Find the mean response time of all 16 Arrow Ambulances. Compare that to the “mean of
the means” from question 3. Are they similar or different? Why do you think that is?
Solution: The mean of all 16 Arrow incidents is 11.5 minutes. The mean of all 16 ambulance
incidents is very similar to the “mean of the means” of 11.28. Since they use the same values
and they are both means, they will be similar.
Now, you will complete the same procedure with Metro Ambulances.
Teacher Commentary: If you do not have access to enough calculators, you have options. You
can use 1 calculator and choose samples for everyone to use in class. This may make grading
the task easier if all students use the same values. Or, you can also put numbers in a bucket
and draw values from the bucket. Replace numbers once you have a group completed.
Sample Solution:
Random integers 9 2 6 12 10
Corresponding Time
16 8 11 15 11
minutes
5. Find 5 more random incidents and response times for Metro Ambulances. Use the
procedure above, or continue to press enter to get 5 more random incidents for the groups
below. It is okay if an incident number repeats in one group.
Sample Solution:
Random integers 14 16 1 11 2
Corresponding Time
8 8 11 12 8
minutes
Sample Solution:
Random integers 6 13 12 5 3
Corresponding Time
11 14 15 11 16
minutes
Sample Solution:
Random integers 2 19 11 6 17
Corresponding Time
8 10 12 11 19
minutes
Sample Solution:
Random integers 3 19 15 5 7
Corresponding Time
16 10 10 11 12
minutes
Group Mean
1
2
3
4
5
Total Mean of Groups 1-5
“the mean of the means”
Sample Solution:
Group Mean
1 61/5=12.2
2 47/5=9.4
3 67/5=13.4
4 60/5=12
5 59/5=11.8
Total Mean of Groups 1-5 𝟏𝟐. 𝟐 + 𝟗. 𝟒 + 𝟏𝟑. 𝟒 + 𝟏𝟐 + 𝟏𝟏. 𝟖 𝟓𝟖. 𝟖
= = 𝟏𝟏. 𝟕𝟔
“the mean of the means” 𝟓 𝟓
7. Find the mean response time of all 20 Metro Ambulances. Compare that to the “mean of
the means” from question 7. Are they similar or different? Why do you think that is?
Solution:
Mean of all 20 ambulance incidents is 10.9 minutes. Compared to the “mean of the means” in
question 7, the mean of all incidents is almost a full minute different. 1 minute could mean a
huge difference in emergency situations, so 10.9 and 11.76 are quite different.
8. Did either ambulance company have outliers, numbers that stood out to be extremely
high or extremely low? How do outliers affect the mean response time?
Solution:
No outliers were apparent in any incident from Arrow or Metro. Outliers can pull the mean
response time higher or lower. No outliers appeared to affect the means for Arrow or Metro.
Comments:
Some students may want for “19” to be an outlier in Arrow or Metro. But since both
ambulance companies have other incidents within 2-3 minutes of 19, it is not a “strong”
outlier.
9. The Bay City Council wants your recommendation of which company to use. Prepare a
statistical chart below (dot plot, histogram, box plot, bar graph, etc) to support your
recommendation. Then be sure to give clear, statistical reasons for the ambulance
company you are recommending.
Solution:
Metro Ambulances should be chosen based on the lower mean of 10.9 minutes as compared to
Arrow’s 11.9 minute mean.
The box plots show Arrow at the top, and Metro under it. The overall “box” of the box plots
shows Metro as having a trend for lower response times.
Last week there was an accident at the Waterfront Amusement Park in Bay City. A seat on one
of the rides broke loose, resulting in the deaths of two teenagers. The owners of the amusement
park have charged that if ambulances had responded more quickly, the two teens would have
survived. They have threatened to sue the Bay City 911 emergency service for failing to dispatch
ambulances efficiently.
The Bay City Council has hired your firm to conduct an independent investigation of the city’s
911 response. The 911 operators dispatch from two companies: Arrow Ambulance and Metro
Ambulances.
The 911 operators aren’t always sure which company to send when an emergency call is
received.
Data on the response times for the two companies for an area of a one-mile radius of the
Amusement Park show that responses can take as little as 6 minutes or as long as 19 minutes.
You need to continue your investigation by analyzing the response time data on the next page.
Based on the information above and your analysis of the data, you conclude that the Bay City
Council needs to establish a policy about which service to call.
Using the steps below, you will discover which Ambulance Service would best serve the
Amusement Park.
2. Find 5 more random incidents and response time for Arrow Ambulances. Use the
procedure above, or continue to press enter to get 5 more random incidents for the groups
below. It is okay if an incident number repeats in one group.
Randomized Group 2
Random integers
Corresponding Time
Group Mean
1
2
3
4
5
Total Mean of Groups 1-5
“the mean of the means”
4. Find the mean response time of all 16 Arrow Ambulances. Compare that to the “mean of
the means” from question 3. Are they similar or different? Why do you think that is?
Now, you will complete the same procedure with Metro Ambulances.
6. Find 5 more random incidents and response time for Metro Ambulances. Use the
procedure above, or continue to press enter to get 5 more random incidents for the groups
below. It is okay if an incident number repeats in one group.
Group Mean
1
2
3
4
5
Total Mean of Groups 1-5
“the mean of the means”
8. Find the mean response time of all 20 Metro Ambulances. Compare that to the “mean of
the means” from question 7. Are they similar or different? Why do you think that is?
9. Did either ambulance company have outliers, numbers that stood out to be extremely
high or extremely low? How do outliers affect the mean response time?
10. The Bay City Council wants your recommendation of which company to use. Prepare a
statistical chart below (dot plot, histogram, box plot, bar graph, etc) to support your
recommendation. Then be sure to give clear, statistical reasons for the ambulance
company you are recommending.
MGSE7.SP.2 Use data from a random sample to draw inferences about a population
with an unknown characteristic of interest. Generate multiple samples
(or simulated samples) of the same size to gauge the variation in
estimates or predictions. For example, estimate the mean word length
in a book by randomly sampling words from the book; predict the
winner of a school election based on randomly sampled survey data.
Gauge how far off the estimate or prediction might be.
http://nzmaths.co.nz/resource/planning-statistics-investigation-l3
http://nzmaths.co.nz/resource/channel-surfing
http://nzmaths.co.nz/resource/stork-delivery
http://illuminations.nctm.org/Activity.aspx?id=3580
MGSE7.SP.3 Informally assess the degree of visual overlap of two numerical data
distributions with similar variabilities, measuring the difference between the medians by
expressing it as a multiple of the interquartile range.
https://www.illustrativemathematics.org/content-standards/7/SP/B/3/tasks
https://www.illustrativemathematics.org/content-standards/7/SP/B/4/tasks
http://nzmaths.co.nz/resource/number-statistics
http://nzmaths.co.nz/resource/sports-statistics
http://nzmaths.co.nz/illustrating-mathematics-standards-60
http://illuminations.nctm.org/Activity.aspx?id=3576
http://illuminations.nctm.org/Activity.aspx?id=3580
http://illuminations.nctm.org/Lesson.aspx?id=2643
http://illuminations.nctm.org/Activity.aspx?id=3580
MGSE7.SP.4 Use measures of center and measures of variability for numerical data
from random samples to draw informal comparative inferences about two populations.
For example, decide whether the words in a chapter of a seventh‐grade science book are
generally longer than the words in a chapter of a fourth‐grade science book.
https://www.illustrativemathematics.org/content-standards/7/SP/B/3/tasks
https://www.illustrativemathematics.org/content-standards/7/SP/B/4/tasks
http://nzmaths.co.nz/resource/number-statistics
http://nzmaths.co.nz/resource/sports-statistics
http://nzmaths.co.nz/illustrating-mathematics-standards-60
http://illuminations.nctm.org/Activity.aspx?id=3576
http://illuminations.nctm.org/Lesson.aspx?id=2643
http://illuminations.nctm.org/Activity.aspx?id=3580