Professional Documents
Culture Documents
(FORM 4)
Presented by
Nur Shakirin Sabri
Nur Ayuni Daud
Nornaimah Rodzi
Ungrouped and Grouped
Data
Ungrouped data is where the values are
handled individually.
e.g. 1, 3, 6, 6, 6, 6, 7, 7, 12, 12, 17
Grouped data is where the values are
grouped into classes because
sometimes we may collect a large
number of data with varying values. e.g.
data.
1, 3, 6, 6, 6, 6, 7, 7, 12, 12, 17
= 1 + 3 + 6 + 6 + 6 + 6 + 7 + 7 + 12 + 12 + 17 =
7.546
Mean of grouped data.
For grouped data, we take the midpoint of
the class, known as the class mark, to
represent the class.
Let f be the frequency of for each class
2
If n is an even number, the median is the
mean of
n th value and n + 1 th value.
2
Example: 1, 3, 6, 6, 6, 7, 8, 8, 12, 12, 17
2 2
Mode
Mode is the value that occurs the most
Mode
Steps to find mode from
histogram.
1.Determine the
modal class in
the histogram.
Modal class
2.Join the top vertices
of the modal
class to the
vertices of the
adjacent.
3.Determine the value
of the horizontal
axis at the Mode
intersection of
the two lines.
This value
obtained
Median from cumulative
frequency distribution table
The median of grouped set of data can be
calculated from cumulative frequency
distribution table using the following formula:
Median:
Where
L = lower boundaries where the median lies
f
m= frequency of the class where the median
Circumference (cm) 1 - 2 3-4 5- 6 7-8
No. of branches, f 2 10 14 8
Cumulative 2 12 26 34
frequency, F
Calculate the median.
The median lies between 17th and 18th
5-6, F=12
Lower boundary, L=4.5
fm= 14
Estimating the median of
grouped data from an ogive.
We can use ogive to estimate the median
of grouped data.
Median
Effects of uniform changes in
data on mean, median and
mode
Activity: To find the effects on the measures of
central tendency if every value of the data is
changed uniformly
Given 4, 12, 5, 7, 9, 6, 10, 6, 13
Answer:
Example:
Find the range of data.
Answer: Range = 24 – 2 = 22
Interquartile range of
ungrouped data
Quartiles are three values in a set of data
Example:
Interquartile range = Q3 – Q1 = 20 – 6 = 14
Range of grouped data
Range of grouped data
= largest class mark – smallest class
Number 0 – 4 5–9 10 – 14 15 – 19 20 – 24 25 mark
- 29
of goals 12
Number 9 4 3 1 1
of
players
first.
Number 20-29 30-39 40-49 50-59 60-69 70-79
of
Frequenc 2 5 11 16 10 4
durians
yCumulati 2 7 18 34 44 48
ve
frequenc
y
Q1
Q3
Cumulati 220-29
Number
Frequenc 7530-39 40-49
11
18 50-59
16
34 60-69
10
44 470-79
48
yof
ve
durians
frequenc
y
Q1 =
= 10th value
= 24.5 mm
Q3 =
= 30th value
= 31.5 mm
24.5 Hence, the
31.5
interquartile range
= 31.5-24.5
= 7.0 mm
Variance
Variance of ungrouped data
or where
Mean;
Varianc
e;
s.d.;
Effects on measures of
dispersion when:
If every value of the data is changed
uniformly, i.e. when every value n a
set of data is multiplied by a constant
quantity k, then we have
new range = k x original range
new interquartile range= k x ori.
interquartile range
new s.d. = k x ori. standard
deviation
new variance = k2 x original
variance
Effects on measures of
dispersion when:
If there are extreme values in the
set of data, this will significantly
increase the range of the set of data but
have little or no effect on the interquartile
range.
Extreme values also significantly increase
the value of standard deviation and
variance but s.d. Is affected to a smaller
degree as compared to variance.
Hence, interquartile range will eliminates the
effect of extreme values.
Other measures of dispersion are affected at
different degree by extreme values.
Effects on measures of
dispersion when:
If certain values are added or removed
from a set of data, the effect on the
measures of dispersion is uncertain.
In general, the range and the interquartile
range are less affected as compared to
the variance and the standard deviation.
Variance and standard deviation are more
significantly affected when the added or
removed value has a greater difference
from the mean
Comparing the measures of
central tendency and
dispersion
There are many situations where we need
to compare two or more sets of data
and subsequently make a conclusion.
The measure of central tendency may not
provide us with enough information for
comparison.
We need to determine the measures of
dispersion of a set of data to provide us
with a better picture of the
characteristics of the set of data and
eventually help us arrive at a more
meaningful and acceptable conclusion.
A teacher would like to select one of
Team Marks these teams to represent the school
P 60, 65, 85, 76, 64, 88 in a Mathematics quiz. The teacher is
more concerned about a steady
Q 68, 62, 76, 80, 81, 71 performance of the team in the quiz.
Which team would the teacher select?
Team P Team Q
= =
= 10.74 = 6.73
Both teams have the same mean, meaning that they are
considered equally good statistically. However, team Q
has a lower s . d . , implying a small difference in the
performances between the members of the team. Hence, they
are expected to have a more consistent performance
in the quiz as compared to team P. Therefore, the teacher
would select team Q.
THE END
Thank you for your patience and
attention.