PNG University of Technology Mathematics & Computer Science Department
PNG University of Technology Mathematics & Computer Science Department
MA 339
LECTURE 3
Graphical Representation
1
The most commonly used graph for
displaying a summary of quantitative
data is the histogram. A histogram is
the graph of the frequency distribution
made by constructing a series of
continuous rectangles (ie, without gaps
in between), whose areas are
proportional to the frequencies to each
class.
2
Example 3.
Refer to the marks obtained by 50
students in a test which is marked out
of 50 in example 1 of lecture 2 and
draw a histogram to represent this
information. To construct histogram of
ungrouped frequency data, we need a
frequency distribution in Table 1 of
lecture 2 (see below).
3
Marks obtained by 50 students in a test which is marked
out of 10.
14
12
10
Frequency
8
6
4
2
0
1 2 3 4 5 6 7 8
Marks
4
Example 4.
Refer to the swimming pool data used in example
2 on lecture 2. Mark the class boundaries on a
horizontal axis, and let the vertical axis show
frequency. Draw rectangles above each class
intervals, with areas in proportion to the given
frequencies. Therefore, to construct, histogram of
any grouped frequency, we need to modify the
frequency distribution in Table 2 of lecture 2. We
need class boundary (obtained from class interval)
and frequency columns.
5
Histogram of swimming pool data
16
14
12
Number of Children
10
0
30-34 35-39 40-44 45-49 50-54
Time taken in Seconds
6
Example 5.
The frequency polygon formed
from the histogram in example 4
(above) is shown below. We need
class interval (from this we find
class midpoints), class boundary
and frequency to draw the
frequency polygon.
7
Swimming pool data
16
14
12
Number of Children
10
0
32 37 42 47 52
Time taken in Seconds
8
Example 6.
Refer to table 2.2 in lecture 2; the
cumulative frequencies can be
plotted, giving a cumulative
frequency polygon. We need
class boundary (obtained from
class interval) and cumulative
frequency columns.
9
Cummulative Frequency Polygon of Swimming
Pool
45
40
Cummulative Frequency
35
30
25
20
15
10
5
0
29.5 34.5 39.5 44.5 49.5 54.5
Time in seconds
10
Collected data can be considered as forming a
sample taken from a very large population.
Many observations can be taken on a large
population, and hence for continuous data,
very small class interval could be chosen, still
with a reasonable number of observations
falling into each class. The rectangles in the
histogram would then become very small in
width, and the frequency polygon (joining up
a large number of points) would closely
resemble a curve.
11
Thus a continuous curve can be drawn in
place of a frequency polygon in some
instances. Such a curve is called a
frequency curve. If cumulative frequencies
of a cumulative frequency distribution are
plotted together against the corresponding
upper class boundaries, the curve obtaining
by joining the plotted points is called the
ogive or a cumulative frequency curve.
12
Example 7
The ogive of the above data is given below.
Note that the main purpose of an ogive is the
read off the percentage [we will discuss
percentile in calculations of spread of data in
the next topic] of a population below a
certain observed value – hence its vertical
axis usually represents percentages. We need
class boundary (obtained from class interval)
and percentage cumulative frequency
columns.
13
Class Class Freq Cum Percentage
Interval Boundary Freq Cum. Frequency
30 – 34 29.5 – 34.5 4 4
14
Cummulative Frequency Curve or Ogive
120
Percentage Cum. Frequency
100
80
60
40
20
0
29.5 34.5 39.5 44.5 49.5 54.5
Time in Seconds
15