Topic 1 Numerical Measure
Topic 1 Numerical Measure
1. Mean, ̅
The mean is the average or the most common value in a collection of numbers. In statistics, it
is a measure of central tendency of a probability distribution along median and mode. It is
also referred to as an expected value. Mean can be significantly impacted by extreme value.
The higher the mean score the higher the expectation and vice versa. This depends on what
is studied. E.g. If mean score for male students in a Mathematics test is less than the females,
it can be interpreted that female students perform better than the male students in the test
2. Median,
The median is the point on the scale that divides the distribution of scores in half (half of the
scores fall above the median and half fall below). Median is the middle value of an ascending
or descending ordered dataset.
3. Mode,
The mode is simply the score that occurs most frequently. Data may have no mode or more
than one mode.
Measures of Variability
We need the measures of variability to measure the degree of variation in the data set.
1. Range
Useful to evaluate the whole of a data set and for comparing the spread between similar
datasets.
=
−
2. Standard deviation
A number used to tell how measurements for a group are spread out from the average. A low
standard deviation means that most of the numbers are very close to the average.
1 ∑
= −
Standard deviation
−1
1
3. Coefficient of Variation
Comparison between two different data sets which are measured in different units. Small CV
indicates that the data set is more consistent and reliable.
= × 100%
̅
Measures of Skewness
Skewness is a measure of the asymmetry of the distribution of the measurements of a variable
relative to its mean. As the data becomes skewed from a normal distribution, the mean loses its
ability to provide the best measure of central tendency. As the data becomes skewed from a normal
distribution, the mean loses its ability to provide the best measure of central tendency. To measure
a skewness, we can use Pearson coefficient of skewness:
Every dataset can have some gradient of three skew states: Negatively Skew, No Skew and Positively
Skew.
If the skewness is between -0.5 & 0.5, the data are nearly symmetrical.
If the skewness is between -1 & -0.5 (negative skewed) or between 0.5 & 1(positive skewed),
the data are slightly skewed.
If the skewness is lower than -1 (negative skewed) or greater than 1 (positive skewed), the
data are extremely skewed.
2
Example 1
Solution
∑ 9 + 6 + 11 + 10 + 13 + 7 56
̅ = = = = 9.33
6 6
Mean
9 + 10
, = = 9.5
2
Median
Mode Above data has no mode because there is no repeated number(s) in the
dataset
+ 1 9: 6+1
First quartile
6+1
4; = 3 6 8 = 5.259: = 11 + 0.2513 − 11 = 11.5
+ 1 9: 4
Third quartile
4; = 3 6 8
4
Range − = 13 − 6 = 7
∑ = 9 + 6 + 11 + 10 + 13 + 7 = 56
∑ = 9 + 6 + 11 + 10 + 13 + 7 = 556
Standard
deviation
1 ∑ 1 56
= − = 556 − = √6.67 = 2.58
−1 6−1 6
2.58
= × 100 = × 100 = 27.65%
̅ 9.33
Coefficient of
variation
3
Example 2
Solution
Attend Lecture
Mean
Median
Mode
+ 1 9:
First quartile
45 = 6 8
4
+ 1 9:
Third quartile
4; = 3 6 8
4
Range
Standard
deviation
Coefficient of
variation
Pearson
coefficient of
skewness
4
Example 3
Solution
Attend Lecture
Mean
Median
Mode
+ 1 9:
First quartile
45 = 6 8
4
+ 1 9:
Third quartile
4; = 3 6 8
4
Range
Standard
deviation
Coefficient of
variation
Pearson
coefficient of
skewness
5
Grouped Data (Frequency Table)
∑ D
C=
>?@A,
∑D
∑D + J
− LH
= GH + I K
>?EF@A, M×N
D
OP = Q+R) S+T &)U +V W&' XQ
YP = XTWTQ('* V)ZT XU SV+) W&'
V = V)ZT XU +V W&'
X = XQR'&(ℎ +V W&' XQ
∆J
>\E?,
= GH + ] _×N
∆J + ∆K
OP = Q+R) S+T &)U +V W+& XQ
∆5 = V)ZT XU +V W+& − V)ZT XU SV+) W+&
∆ = V)ZT XU +V W+& − V)ZT XU V() W+&
X = XQR'&(ℎ +V W+& XQ
∑D + J
− LH
G\`?a bc@adFe?, fJ = GH + I g M×N
D
OP = Q+R) S+T &)U +V Q+R) ZT)('Q XQ
YP = XTWTQ('* V)ZT XU SV+) Q+R) ZT)('Q
V = V)ZT XU +V Q+R) ZT)('Q
X = XQR'&(ℎ +V Q+R) ZT)('Q XQ
∑D + J
j 6 g 8 − LH
hii?a bc@adFe?, fj = GH + k l×N
D
J ∑ DK
nd@AE@aE E?oF@dF\A, p = DK −
∑D − J ∑D
6
Example 1
Calculate the mean, median, mode, lower quartile, upper quartile and standard deviation.
Solution
V
marks students midpoint boundaries
∑ V 685
Mean
̅ = = = 22.83
∑V 30
∑ tuv
xyz
, = OP + × X = 17.5 + { }× 25.5 − 17.5 = 24.17
w 5|.|x5;
q ;
3.
Mode
v r∆w
2.
7
Lower quartile position = = = 7.759:
∑ qr5 ;sr5
Lower quartile
1.
2. Class boundaries of median = 9.5 – 17.5
∑ tuv
xyz
45 = OP + × X = 9.5 + { }× 17.5 − 9.5 = 10.5
.|x
q
3.
∑ tuv
;
xyz
3. 4; = OP + × X = 33.5 + { }× 41.5 − 33.5 = 36.39
;.|xs
q
nd@AE@aE E?oF@dF\A
V = 685
V = 20900
1 ∑ V 1 685
= V − = 20900 − = 13.47
∑V − 1 ∑V 30 − 1 30
8
Example 2
Calculate the mean, median, mode, lower quartile, upper quartile and standard deviation of weekly
wages. [Answer: 66.05, 65.5, 65.71, 47.12, 81.5, 24.82]
Solution
Attend lecture
Wages V Class V V CF
boundaries
20 – 39 14
40 – 59 21
60 – 79 30
80 – 99 10
100 – 119 12
Total 87 5746.5 432531.75
9
10
Example 3
Table below represent distribution of body mass for 100 patients in a private hospital.
a) Find the mean, median, mode, first quartile and third quartile.
b) Find the standard deviation and coefficient of variation.
c) Determine the skewness of the distribution.
Solution
Attend lecture
11