Data Analysis
Data Analysis
SCATTERPLOTS
Scatter plot
A scatterplot is a graph in which points are plotted on the 𝑥𝑦-plane. Scatterplots are commonly used
to display the correlation between two variables of interest in an experiment. Unlike the graph of a
function, these points are not connected by line.
Example 1:
Have you ever wondered if height is related to arm span? Whether tall people have longer arms
than short people?
To answer these questions, we can investigate the relationship between a person’s height and
his or her arm span by collecting data on both quantities from several people, as shown in the
table below.
Height Arm Span Height Arm Span Height Arm Span
(cm) (cm) (cm) (cm) (cm) (cm)
162 156 162 161 185 173
160 157 170 162 176 173
162 159 166 165 173 177
155 160 170 170 176 177
160 161 167 170 178 178
We can then plot these data into a scatterplot to see whether there is a correlation between
them.
180
175
Arm Span (cm)
170
165
160
155
150
150 155 160 165 170 175 180 185 190
Height (cm)
One of the required skills for analyzing the scatterplots is the ability to identify the coordinates of a
given point. One the SAT, some questions will require us to interpret a situation, find a point matching
some conditions, determine the coordinates, and perform some calculation with those coordinates (e.g.,
percent increase or decrease).
1
Example 2:
40
35
20
𝐴 𝐵
15
10
5
0
0 5 10 15 20 25 30 35 40
Number of repetitions on day 1
The scatterplot above shows the number of repetitions of an exercise ten members of a gym could
complete the 1st and 20th days of an exercise program. Of the labeled points, for which is the ratio
of the number of repetitions completed on the 20th day to the number of repetitions completed on
the 1st day the greatest?
A. 𝐴
B. 𝐵
C. 𝐶
D. 𝐷
To solve this question, first we need to find the coordinate for each of the points:
Then we can calculate the ratio of the y-coordinate to the x-coordinate and find the greatest
value
15 15 23 26
𝐴: =3 𝐵: ≈ 1.67 𝐶: ≈ 1.35 𝐷: ≈ 1.18
5 9 17 22
The labeled point for which the ratio is the greatest is point 𝐴 → Option A is correct
2
Example 3:
11
10
9
Rank in Soccer 8
7
6
5
4
3
2
1
0
0 1 2 3 4 5 6 7 8 9 10 11
Rank in Tenis
The scatterplot above shows the ranking of 10 students in two sports. How many students
received the same rank in both sports?
A. 1
B. 2
C. 3
D. 4
To solve this question, first we need to find the coordinate for each of the points:
𝑆𝑡𝑢𝑑𝑒𝑛𝑡 1 (1,3) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 2 (2,2) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 3 (3,4) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 4 (4,1) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 5 (5,5)
𝑆𝑡𝑢𝑑𝑒𝑛𝑡 6 (6,7) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 7 (7,6) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 8 (8,9) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 9 (9,10) 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 10 (10,8)
From the list of students, we can see that there are two students who have the same ranking
for both sports: Student 2 rank second in both sports, and student 5 rank fifth in both sports.
→ Option B is correct
When there is a correlation between two variables in the scatterplot, we can use the line of best fit to
model this correlation. The method of accurately drawing the line is far beyond the scope of the SAT test,
so we could eyeball the line and graph it. The line may pass through some of the points, none of the
points, or all of the points.
3
We must notice that the line of best fit only models the overall trend of the data. We can use it to
estimate other missing values in the scatter plot, but we may not use it to get the exact value.
180
175
Arm Span (cm) 170
165
160
155
150
150 155 160 165 170 175 180 185 190
Height (cm)
We can see that there is a correlation between the two variables plotted here. The overall trend is
that the taller the person, most likely the longer his or her arm span is. This statement may not be true
for all of the data, since a person who is 170cm tall has a shorter arm span than a person who is 166cm
tall: 162cm compared to 165cm respectively.
We can draw the line of best fit for this scatterplot by drawing a line passing through the middle of
the cluster of points so that the number of points above and below the line is balanced
185
180
Arm Span (cm)
175
170
165
160
155
150
150 155 160 165 170 175 180 185 190
Height (cm)
By using this line of best fit, we can estimate other missing values in the table. For example: a person
who is 175cm tall may have an arm span of 173cm, or a person who is 180cm tall may have an arm span
of 176cm.
NOTE: when the questions ask us to use a value predicted by the line of best fit, use the values of the
line, not the value of points on the scatterplot closest to the line.
4
Example 4:
The first metacarpal bone is located in the wrist. The scatterplot below shows the relationship
between the length of the first metacarpal bone and height for 9 people. The line of best fit is also
shown.
185
180
175
Height (cm)
170
165
160
155
4 4.5 5
Length of first metacarpal bone (cm)
How many of the nine people have an actual height that differs by more than 3 centimeters from
the height predicted by the line of best fit?
A. 2
B. 4
C. 6
D. 9
→ There are 4 people – with metacarpal bone of length 4.0, 4.3, 4.8, and 4.9cm who have
actual height that are 3cm different from the height predicted by the line of best fit
→ Option B is correct
5
Practice
1. 2.
6
3. 4.
A. 130,000
B. 580,000
C. 1,725,000
D. 58,000,000
7
5.
A. 1994
B. 1996
C. 2000
D. 2006
8
II. STATISTICS
Mean
The mean of a list of numbers is found by dividing the sum of the numbers in the list by the amount
of numbers in the group
NOTE: The SAT test uses the terms “mean,” “average,” and “arithmetic mean” interchangeably.
Example 5:
What is the average test score for the class of five students if the scores they received are
92. 81, 45, 95, and 68 ?
Sometimes, the questions will give us the average and ask for the value of one of the numbers. We
can solve these questions by, first, multiplying the average and the number of members to get the sum
and, then, subtract the given values from the sum.
Example 6:
The average of seven numbers is 39. If six of the numbers are 18, 49, 25, 19, 38, and 39, what is
the seventh number?
9
Median
The median of a list of numbers is the value directly in the middle of the list when the numbers are
arranged in either increasing or decreasing order.
If the list of numbers has an even number of members, the median is the average of the 2 terms in
the middle. If the list of numbers has an odd number of members, the median is the number exactly in
the middle.
Example 7:
What is the median value of the set of numbers {4, 12, 15, 3, 7, 10}
There is an even number of members, six, so the median is the average of the two terms in the
middle
7 + 10
→ = 8.5
2
Example 8:
There is an odd number of members, seven, so the median is the value in the middle of the list
→8
10
Example 9:
There is an even number of members, six, so the median is the average of the two terms in the
middle
3+3
→ =3
2
Mode
The mode of a list of numbers is the numbers that repeat the most frequently in the list. We don’t
have to rearrange the numbers in the list to find the mode. We simply have to count the number of times
each value appears in the list and choose the ones that are most frequent.
Example 10:
The values 5, 6, and 7 appear once each while 2 appears three times
Example 11:
What is the mode of the set of numbers {108, 43, 108, 45, 61, 47, 43, 46, 46, 50, 49}
The values 45, 61, 47, 50, and 49 appear once each while 108, 43, and 46 appear twice each
11
Example 12:
What is the mode of the set of numbers {13, 20, 14, 27, 20, 13, 27, 14}
→ There is no mode
Range
The range of a list of numbers is the difference between the highest value in the list and the lowest
value in the list.
Example 13:
→ The range is 28
Practice
Question 1 and 2 1.
What is the average price of the cell phones?
The table below shows the prices of the six
different cell phones that a store carries. A. $69.99
B. $79.99
Phone Price C. $89.99
SJ-119 $49.99 D. $99.99
SJ-220 $69.99
RV-375 $79.99 2.
RV-400 $99.99 What is the median price of the cell phones?
12
3. 5.
A linguistics library contains several archives of The price of a ticket to a concert varies
language samples. The table above shows the depending on the day of the week, as shown in
number of distinct languages referenced in each the table above. How much greater is the mean
archive. What is the range of numbers of distinct ticket price than the median ticket price in
languages referenced? dollars, to the nearest cent?
4. 6.
13
III. PROBABILITY
Probability is how likely something will happen. The value of probability ranges from 0 to 1.
0≤𝑝≤1
If something has a probability of 0, it will never happen while if something has a probability of 1, it
will certainly happen.
On the SAT, questions regarding probability involve only the most basic calculation of probability.
Example 14:
In a class, there are 10 boys and 15 girls. If a student is chosen at random, what is the probability
that the student is a boy?
Example 15:
Peter is at a car dealership. He is going to randomly select a vehicle to test drive. There are 11
trucks, 9 vans, and 5 compact cars. What is the probability that he picks the compact car?
Probability questions on the SAT test usually involve tables of data, so finding the probability of an
event may be more complicated than what is shown in Example 14 and 15. Aside from knowing the basic
rule to calculate probability, we also have to know how to identify the proper numbers, the number of
possible outcomes and the total number of outcome, to use.
14
NOTE: Sometimes the total number of outcomes is not the total sum in the table of data – the largest
value. We must assess the questions carefully in order to determine what to use for the total number of
outcomes.
Example 15:
Beef Chicken
First Class 15 20
Coach 50 115
The table above summarizes the meat preferences of passengers on a particular flight. Calculate
the following probabilities.
i. If a passenger is chosen at random from this flight, what is the probability that the passenger
is in first class and prefers beef?
ii. If a first class passenger is chosen at random from this flight, what is the probability that the
passenger chosen prefers beef?
iii. If a passenger who prefers beef is chosen at random from this flight, what is the probability
that the passenger is in first class?
i. If a passenger is chosen at random from this flight, what is the probability that the passenger
is in first class and prefers beef?
The question says “if a passenger is chosen at random from this flight”
→ we are choosing from the whole flight
→ the total number of outcomes: 15 + 50 + 20 + 115 = 200
The question asks for the probability that the passenger is in first class and has a preference
for beef
→ the number of possible outcomes: 15
15
ii. If a first class passenger is chosen at random from this flight, what is the probability that the
passenger chosen prefers beef?
The question says “if a first class passenger is chosen at random from this flight”
→ we are choosing from the first class section only
→ the total number of outcomes: 15 + 20 = 35
The question asks for the probability that the passenger prefers beef
→ among the 35 first class passengers, only 15 prefer beef
→ the number of possible outcomes: 15
iii. If a passenger who prefers beef is chosen at random from this flight, what is the probability
that the passenger is in first class?
The question says “if a passenger who prefers beef is chosen at random from this flight”
→ we are choosing from those who prefer beef only
→ 15 + 50 = 65
The question asks for the probability that the passenger is in first class
→ among the 65 passengers who prefer beef, only 15 are in first class
16
Practice
1. 16
A.
47
Results of College Applications 31
Attended Attended B.
47
private school public school
Offered 16
37 144 C.
Admission 100
Not offered 31
51 168
Admission D.
100
The table above summarizes the results of 400
applications handled by a team of admissions
3.
officers at a particular college. If one of the
students who were offered admission is chosen
Drive to Walk to
at random, what is the probability that the Total
school school
students attended private school? Junior 3 25 28
144 Senior 15 7 22
A.
181 Total 18 32 50
37
B. The table above shows the distribution of age
181 and year in school for 50 students who
144 answered a survey in the school newspaper
C.
400 asking about the most frequent way students
37 get to school. If one of the survey respondents is
D. chosen at random, what is the probability that
400
the person chosen is either a junior who drives
2. to school or a senior who walks to school?
4
Reading preferences A.
50
Novels Non-fiction 10
Male 16 34 B.
50
Female 31 19 21
C.
The table above summarizes the results of a
50
survey of 100 adults about their preferences for 28
D.
leisure reading. If one of the adults who prefer 50
reading novels is chosen at random, what is the
probability that the person is male?
17
IV. HOMEWORK
1. 3.
18
5. 6.
19
8. 10.
20
12. graph, which model achieves the greatest
number of miles per gallon of gasoline?
Time in minutes Number of runners
18 1 A. A
19 2 B. B
20 3 C. C
21 6 D. D
22 𝑟
23 1
24 2 14.
13.
500
The scatterplot above shows the distribution of
D seats for the restaurants in 7 different mall food
400
B courts. The line of best fit is also shown.
Number of Miles
100 A. 200
B. 240
0 C. 320
0 6 12 18 24 D. 560
Tank Size (gallon)
21
15. 17.
A. $29
B. $99
C. $128
D. The mean and the median are equal
16.
18.
Month Civil aircraft produced
A Per pupil
400 Year
expenditure
B ?
2008 $11,223
C 286
D 350 2009 $11,665
E 290 2010 $11,825
2011 $11,864
The table above partially reports the
2012 $11,735
numbers of civil aircraft produced in the
United States during the course The table above shows the annual average per
of 5 months. If there was a mean of 325 civil pupil educational expenditures in the United
aircraft produced during that time, how States from 2008 through 2012. What is the
many were produced in month B? range of the per pupil expenditures?
22
19. cat under 1 year old or a dog 1 year old or
older?
2
A.
53
12
B.
53
27
C.
53
32
D.
53
12
10
A. 1 8
B. 2 6
C. 3 4
D. 4 2
0
0 1 2 3 4
Depth in meters
20.
Bally tracked the number of living organisms she
Pet Adoptions found at different depths in a pond near her
Cats Dogs Total home, as shown in the histogram to the left.
Under 1 year old 4 23 27 What is the range of depths at which Bally found
living organisms?
1 year old or older 18 8 26
Total 22 31 53 A. 1
B. 4
The table above shows the distribution of animal C. 5
type and age for all of the pets adopted at an D. 10
animal shelter during a particular month. If one
of the adopted animals is chosen at random,
what is the probability that the animal is either a
23
22. A. Both the median and the mean will increase.
7 B. Both the median and the mean will
6
decrease.
5
C. The median will decrease by the mean will
4
3
increase.
2 D. The median will increase, but the mean will
1 decrease
0
50 60 70 80 90 100
24