Math 1342 One Quantitative Variable: Shape and Center 2.
The table below records the amount in dollars spent by a young couple on fast food each week for 44
weeks.
32 22 19 18 45 42 40 43 18 21 55
31 26 22 25 47 40 26 32 22 34 34
28 35 47 26 35 38 35 28 19 38 35
38 36 25 22 45 48 27 34 41 40 24
One way to analyze the properties of quantitative data is to graph it on a dotplot .
Definition. We create a dot plot by using an axis with a scale appropriate for the numbers
in the dataset and placing a dot over the axis for each case in the dataset. If there are multiple values that
are the same, we stack the dots vertically.
Definition. An outlier is an observed value that is notably distinct from the other values
in a dataset. Usually, an outlier is much larger or much smaller than the rest of the data values.
Are there any outliers in the data on fast food spending?
$95
1
Another type of graph for displaying a distribution of data is a histogram.
Cost of Fast Food Meals
15
little
22 29 36 43 50 57
¥ Dollars
Data points
between 15122
Now consider the table below, which contains values for midterm grades.
85 89 79 78 77 98 86 96 72 80
87 69 98 60 72 95 86 73 79 82
Construct a histogram for the midterm grades data.
7
Shapes of Histograms
A
symmetric B
Bell-shaped
I skewed left
1
b i D
Skewed right 1 symmetric
bimodal
1
1
'
→ lots of alata
E F
skewed left
Bimodal symmetric
uniform
The shape of the histogram is the distribution .
Common Shapes for Histograms
• A distribution is
of one another.
symmetric if the right side and left side are approximately mirror images
• A distribution is skewed right if if the data is piled up on the left and the tail extends
relatively far out to the right.
• A distribution is skewed left if if the data is piled up on the right and the tail extends
relatively far out to the left.
• A distribution is bell-shaped if is the data are symmetric and also shaped like a bell.
• A distribution is bimodal if the data has two humps.
• A distribution is uniformed if the bars on the histogram are all of the same height.
Example. Determine which histograms on the previous page have each shape.
• symmetric
• skewed to the right
• skewed to the left
• bell-shaped
• bi-modal
• uniform
4
Recall that when we are working with a sample, we use n to represent the size of the sample, the number
of cases in the sample. ✗ 3 ,
✗ 7
Mean
~
Definition. The of the data values for a single quantitative variable is given by ✗3 4
+ Xn
✗,+ Xztxzt . .
✗4
11
.
mean = = , xg 9
mean
where x1 , x2 , . . . , xn are the data values.
proportion :
3t1t4gt
sample :p
pop =p • The mean is the average.
• The notation for the mean of a sample is I , which is read X bar
-
• The notation for the mean of a population is the Greek letter µ .
Definition. The median of a set of data values for a single quantitative variable, denoted
m, is y median
• the middle entry if an ordered list of the data values contains an odd number of entries OR 157
• the average of the middle two values if an ordered list contains an even number of entries. 1497
4+9-2=4.9
The median splits the data in half.
Example. Return to the data on midterm grades and determine both the mean and the median.
-1981610+52+99+86=173+781%22
fÉÉ+÷É9
Mean =
= 82.05
median
8/5/86 8/78/99/5916 #
:
6/0 69/427/273/4 78/7/87980 82
80 ! 82 middle two
-
80+21=81 5
Example. Let’s instead consider the data on midterm grades with the grades of the students who dropped
the course included. Their midterm grades were 25 and 31. What are the mean and median with these
grades included?
µ 77.14
=
M -79.9
-
Definition. A statistic is resistant if it is relatively una↵ected by extreme values.
The median is resistant, but the mean is not.
How does the shape of a distribution a↵ect the mean and the median?
• If a histogram is symmetric, then the median is right in the middle and approximately equal to the
mean.
• If the data are skewed to the right, the values in the extended right tail pull the mean up but have
little e↵ect on the median. Thus the mean is greater than the median.
Em
• If the data are skewed to the left, the values in the extended left tail pull the mean down but have
little e↵ect on the median. Thus the mean is less than the median.
÷÷ 6
Recording information .
=
Math 1342 One Quantitative Variable: Shape and Center 2.2
Example. Arsenic is toxic to humans, and people can be exposed to it through contaminated drinking
water, food, dust, and soil. Scientists have devised an interesting new way to measure a person’s level of
arsenic poisoning: by examining toenail clippings. In a recent study, scientists measured the level of arsenic
(in mg/kg) in toenail clippings of eight people who lived near a former arsenic mine in Great Britain. The
grIs
following levels were recorded:
Miki
per 1.9 2.7 0.8
0
26.0 3.9 7.1 3.4 11.9
Kilogram
• Do you expect the mean or the median of these toenail arsenic levels to be larger? Why?
since 26
we expect the mean to be larger
than the other
,
⑧eems
significantly larger
values in our data
• Calculate the mean and the median.
mean :µ :7.21229
median : m -3.69
-
1
Example. The number of grams of fiber eaten in one day for a sample of ten people are
10 115 11 11 14 28 17 15 21 24
• Find the mean and the median for these data.
104115111-11111,442847119+21424-1=26.6
µ 26.6
-
-
10 11 11 14 1517 21 2428 119
mvedian :
19¥ =
16
M -16
-
• The value of 115 appears to be an obvious outlier. Compute the mean and the median for the nine
numbers with the outlier excluded.
lOt1It1H14qBtnt21t24t28_ µ= 16.77
10 11 11 14 15 17 2124 28
A- 15
• Comment on the e↵ect of the outlier on the mean and the median.
Hermits the mean by 10
And doesn't really errettthe median
2
Example. Consider a dataset giving the adult weights of species of insects. Most species of insects weigh
less than 5 grams, but there are a few species that weigh a great deal, including the largest insect known:
the rare and endangered Giant Weta from New Zealand, which can weigh as much as 71 grams. Describe
the shape of the distribution of weights of insects. Is it symmetric or skewed? If it is skewed, is it skewed to
the left or skewed to the right? Which will be larger, the mean or the median?