Seventh Grade
Data Analysis and
Probability
Standard 7-6: Through the process standards students will demonstrate an
understanding of relationships between two populations or samples through data
analysis and probability.
The indicators for this standard
are grouped by the following major concepts:
The
indicators that support each of those major concepts and an explanation of the
essential learning for each major concept follows.
Collection and
Representation
Indicator
7-6.2 Organize data in box plots or circle graphs as appropriate.
Since
kindergarten, students have been collecting and representing data. The representations used include:
Kindergarten; drawings and pictures
First
Grade; picture, object, bar
graphs and tables
Second
Grade; charts, pictographs, and
tables
Third
Grade; tables, bar graphs,
and dot plots
Fourth
Grade; tables, line graphs, bar
graphs, and double
bar
graphs (scale increments greater than or
equal
to one)
Sixth
grade; frequency tables,
histograms, and stem-and-
leaf
plots
In seventh grade, students should
learn to use box-and-whisker plots as well as circle graphs to organize
data. Box-and-whisker plots are
sometimes called a box plot for
short. A box plot is a visual way to
easily see the median and range of a data set and can be drawn vertically or
horizontally.
A box-and-whisker plot displays the
median, the quartiles, and outliers of a set of data, but does not display any
other specific values. There are five
key parts. The easiest way to construct
a box-and-whisker plot is to write the data in order from least to greatest,
draw a number line to show the data in equal intervals, mark the median, mark
the medians of the upper and lower half and then mark the upper and lower
extremes. Be certain to stress that the
quartile refers to one-fourth of the number of items, not one-fourth of the
range.
In circle graphs, students organize
data by using knowledge of fractions, percents, and degrees of a circle. Students can relate data as fractional parts
of a circle, percentage of degrees or compare to a clock (1 minute =
of the clock face = 6°/360°).
Circle graphs are used to compare parts of a whole and show
relationships at a glance. The graph
makes it easy to see the relationship of the categories to each other, as well
as, the relationship of each category to the whole.
Students
should have practice using a protractor and compass to create circles and measure
angles. The knowledge of equivalent
ratios is crucial for this activity. For
example, 6 students out of 20 students is
, which is equivalent to
. This ratio is then
converted to degrees,
= 108°/360°, therefore the measure of the
central angle of the circle graph corresponding to these 6 students is 108°. It
should also be noted that
= 30% so this section
of the graph is 30% of the whole.
Students should realize that the sum of the percents for each category
is 100%.
Students
should be engaged in a discussion about the steps needed to convert tabular
data into a circle graph. Methods that might be suggested:
Have students develop the steps in
constructing a circle graph as well as carrying out the steps. Students should
be able to describe the purposes for using circle graphs or dot plots and
discuss comparisons that can be made with each.
Connections
to:
Other Seventh
Grade Indicators
7-2.9
Apply
an algorithm to multiply and divide fractions and decimals.
7-3.6 Represent proportional relationships with graphs, tables, and
equations.
Teacher Notes: Box-and-whisker plots (or just box plots) are an easy way
to display information about the ranges and distributions of a data set. Box plots can provide effective comparisons
between two data sets because they make descriptive characteristics such as
median and interquartile range readily apparent. (Principles and Standards,
NCTM)
Students apply percentages to make and
interpret circle graphs.
Data Analysis
Indicators
7-6.1 Predict the characteristics of two populations based on the
analysis of sample data.
7-6.3 Apply procedures to calculate the interquartile range.
7-6.4 Interpret the interquartile range for data.
Third
grade students were asked to find the range of a data set as well as analyze
dot plots and bar graphs to make predictions about populations. Fourth grade
students interpreted data in tables, line graphs, bar graphs, and double bar
graphs with scale increments greater than or equal to 1. Fifth grade students
applied procedures to calculate to calculate the measures of central tendency
as well as interpreted the meaning and applications of the measures. Sixth
grade students predicted the characteristics of one population based on the
analysis of sample data and analyzed which measure of central tendency (mean,
median, or mode) was the most appropriate for a given purpose.
In grade 7, students extend their
predictions of characteristics of one population to two populations. Emphasis should be placed on linearity and
proportionality.
Students should plan and design
experiments to collect and compare relevant two population data. Students should be expected to gather
reliable information with well-written questions. Experiments should be used to make inferences
and predictions. For example, based on
data regarding sneaker prices at three different stores, “What would you expect
to pay for a pair of sneakers?” Box
plots are useful when making comparisons between populations.
Students should describe observed
relationships mathematically and discuss whether the conjectures that they drew
from the sample data might apply to a larger population. In deciding whether two data sets are similar
or different consists essentially in deciding whether the distributions of the
data sets are similar or different.
Students need to understand that differences in the variability, or
spread, in two data sets are an important part of deciding whether the data
sets are similar or different. Students
should describe the variability by characterizing the shape(s) of the
distributions: bell curve, u-shape distribution, rectangle-shaped (flat or
uniform), and J-shaped or backward J-shaped.
In the middle grades, not only is the
range a measure of the spread in a data set, but the use of quartile is another
measure. Quartiles are the three values
that divide an ordered set of data into four equal-sized subsets. Of the data, 25% fall between two successive
quartiles. The number of data elements
between successive quartiles depends on the size of the data set, but the
percent of the data between the successive quartiles is always 25%.
Comparing
quartiles involves comparing concentrations of data in two data sets. This comparison is an example of
multiplicative reasoning (i.e., ratios of numbers of elements).
To find the interquartile range,
students need to find the difference between the upper and lower quartiles
(third and first or Q3 – Q1). Half of the data is in that range. The “box” of the box plot denotes the middle
50% of the data and the difference between the two ends of the box is the
interquartile range.
Students need to understand that data
analysis is a sophisticated process.
Connections
to:
Other
Seventh Grade Indicators
7-3.2
Analyze
tables and graphs to describe the rate of change between and among quantities.
7-3.6 Represent proportional relationships with graphs, tables, and
equations.
Teacher Notes: Students use proportions to make
estimates relating to a population on the basis of a sample.
Students need an understanding of
percents (percent as a rate) to use multiplicative reasoning effectively.
Probability
Indicators
7-6.5 Apply procedures to calculate the probability of mutually exclusive simple or compound events.
7-6.6 Interpret the probability of mutually
exclusive simple or compound events.
7-6.7 Differentiate between experimental and theoretical probability of
the same event.
7-6.8
Use
the fundamental counting principle to determine the number of possible outcomes
for a multistage event.
Beginning with grade two, students
were asked to predict on the basis of data whether events are more likely or
less likely to occur
In grades 3-5, students learned how to
quantify the likelihood of single-stage events as likely, unlikely, certain,
impossible, or equally likely. Third
grade students understood when the probability of an event would be 0 or
1. Fourth grade students analyzed
possible outcomes for a simple event.
Sixth grade students used theoretical
probability to determine the sample space and probability for one- and
two-stage events such as tree diagrams, models, lists, charts, and pictures and
applied procedures to calculate the probability of complementary events.
Since sixth students calculated the
probability of complementary events, they were introduced to events that were
mutually exclusive. In seventh grade
students will use prior knowledge to calculate the probability of mutually
exclusive simple or compound events.
Mutually exclusive events can not happen at the same time (the events
have no common elements in the sample space). For example, when rolling 2 dice, getting an
even sum and getting an odd sum are mutually exclusive. When two outcomes are mutually exclusive,
student can use this formula to find the probability; Probability (A or B) = Probability
(A) + Probability (B). Students should
be given ample opportunities to calculate and interpret the probability of
mutually exclusive simple or compound (combination of at least two simple
events) events. Students should be able
to decide whether or not given events are mutually exclusive and describe how
they know.
When finding a probability by tossing
a coin 100 times or throwing free throws on the basketball court 50 times are
examples of finding an experimental probability (simulation). It is considered experimental because the
probability is based on the results of an experiment rather than theoretical
analysis. The experimental probability
of an event is the ratio of number of observed occurrences of the event to the
total number of trials:
Experimental Probability = Number
of favorable outcomes
Number
of Trials
The more
trials the more confident one is that the experimental (simulation) probability
is close to the actual probability. There
are advantages to an experimental approach:
An
experimental (simulation) approach should be used in the classroom whenever
possible. (Elementary and middle School
Mathematics, Teaching Developmentally
3rd Edition, John A. Van de Walle, p410)
(Adapted
from Navigating Through Probability, Grades 6 – 8, NCTM, p.73 – 76)
Students need to know that a
simulation is a procedure for answering questions about a real problem by
conducting an experiment that closely resembles the real situation. As students think about and discuss the real
problem and the factors that make the real problem more complex, remind them a
simulation is an approximation of the real problem and that with a simulation
some of the factors are eliminated such as any possible danger, complexity of
the problem, or length of time necessary to solve the problem.
Have students examine when a
simulation’s results appear to be the closest to theoretical probability. (Results of a simulation are more precise
when it is run repeatedly. Remember that
probability deals more with long term trends than with outcomes of individual
events.)
When designing a simulation, students
need to keep the following 5 tasks in mind:
i.
Problem
stated clearly.
i.
Device
must be able to generate chance outcomes with probabilities that match those of
the problem.
i.
One
trial must be clearly specified. A trial
may require several flips, spins, or draws for example.
i.
There
is no magic number of trials. Rule of
thumb, 25 to 30 trials are appropriate for most of the problems for middle
school students.
i.
Data
must be summarized in some meaningful way such as computing an average, making
a graph, or noting trends in data.
A
simulation is a model of a problem that occurs in real life. The model is designed so that it reflects the
probabilities of the real situation.
Students
use simulations to conduct experiments whose results represent experimental
probability.
Discuss how results of simulations can be deceptive. (Not
enough trials, very few attempts, etc.)
Theoretical probability is the ratio
of the number of favorable outcomes to the total number of possible outcomes. Theoretical probability is based on a logical
analysis of the experiment. For example,
the theoretical probability of a coin landing on tails is ½.
P(heads) = number of sides with heads = ½
number of sides
To use theoretical probability to predict how many times a
coin would land on heads if tossed 30 times:
Multiply
its probability by the number of attempts.
P(heads)
x number of tosses
½
x 30 = 15
You would
toss heads 15 times out of 30.
Students should discuss the
differences between the probability of an event found
through experimental/simulation and the theoretical probability of that same
event
Theoretical Probability = Number
of favorable outcomes
Number of possible
outcomes
Experimental Probability = Number
of favorable outcomes
Number of Trials
Students
should understand that when all outcomes of an experiment are equally likely,
the theoretical probability of an event is the fraction of the outcomes in
which the events occurs Students should
use theoretical probability and proportions to make approximate predictions.
The Fundamental Counting Principle
states that if a first event can occur in a
ways, and a second event can occur in b ways, then the two events can occur
together in a times b ways. For example the school shirt comes in
three colors and in short or long sleeves.
How many choices of shirts are there?
So, 3 x 2 = 6 choices.
Connections
To:
Other
Seventh Grade Indicators
7-3.6
Represent
proportional relationships with graphs, tables, and
equations.
Teacher Notes: In the middle grades, the
groundwork is laid to help students know when events are or are not mutually
exclusive. This is important for the
study of more complex situations in grades 9 – 12.
When a probability experiment has very
few attempts or outcomes, the result can be deceptive. Computer simulations may
help students avoid or overcome erroneous probabilistic thinking. Simulations afford students access to
relatively large samples that can be generated quickly and modified easily.”
(NCTM 2000, p254) Using large samples,
the distribution is more likely to be close to the actual distribution. When simulations are used, you will need to
help students understand what the simulation data represent and how they relate
to the problem situation.