Lecture 8

Coefficient of Skewness
3 (𝑚𝑒𝑎𝑛−𝑚𝑒𝑑𝑖𝑎𝑛)
SK1 =
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
𝑚𝑒𝑎𝑛−𝑚𝑜𝑑𝑒
SK2 =
𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
➢ -3 > Sk1& SK2 < 3

➢ =0 is symmetric distribution
➢ =+ is positive Skewness
➢ =- is negative Skewness
When the value close to zero, the distribution is almost
symmetric. (low skewness)
Example:
For a symmetric distribution if:
mean = 50 first quartile (Q1) = 30
Find the semi- interquartile range?
Solution:
since this dist. is symmetric
then mean = median = mode
median = 50
also
𝑄 1+ 𝑄3
Median =
2
30+𝑄3
50 =
2
100 = 30 +Q3
Q3 = 70
Semi-interquartile range
𝑄 3− 𝑄1 70− 30
= = = 20
2 2
1
Box Plot
Box plot is a graphical summary of data that is based on a
five-number summary, that helps us to picture a set of
data. To construct a box plot, we need only five
statistics: the minimum value, Q 1 first quartile), the
median, Q3 (the third quartile), and the maximum
value.
In a five-number summary, five numbers are used to summarize
the data:
1- Smallest value
2- First quartile
3- Median
4- Third quartile
5- Largest value
2
The box plot reveals the distribution of the data:
The first chart (from left) is positively skewed

The second chart (from left) is symmetric.
The third chart (from left) is negatively skewed.
Example:
Construct a box plot for the following data:
89, 47, 164, 296, 30, 215, 138, 78, 48, 39
What conclusions can you make about this data?
Solution:
89, 47, 164, 296, 30, 215, 138, 78, 48, 39
Sort in ascending order.
30, 39, 47, 48, 78, 89, 138, 164, 215, 296
Five-Number Summary: 30-47-83.5-164-296
3
The box plot:
The box plot also reveals that the distribution of the data is
positively skewed.
General Example
If you have the following frequency table
classes frequencies
10- 3
20- 5
30- 8
40- 3
50-60 1
total 20
1) Find the mean and the mode

2) Find the median
3) Find the range
4) Find the variance and the standard deviation
5) Find the coefficient of variation
6) Find the skewness coefficients
Solution
1)
The mean
classes frequencies x xf
10- 3 15 45
20- 5 25 125
30- 8 35 280
40- 3 45 135
4
50-60 1 55 55
total 20 640
∑ 𝑥𝑓 640
𝑥̅ = = = 32
∑𝑓 20
The mode
To obtain the value of mode we have 4 methods
- the modal class center
30 + 40
𝑚𝑜𝑑𝑒 = = 35
2
- using the graph
- leverage method
𝑓2
𝑚𝑜𝑑𝑒 = 𝐴 + 𝐿
𝑓1 + 𝑓2
𝐴 = 30 𝑓1 = 5 𝑓2 = 3 𝐿 = 10
3
𝑚𝑜𝑑𝑒 = 30 + (10) = 33.75
5+3
- pearson`s difference method
𝑑1
𝑚𝑜𝑑𝑒 = 𝐴 + 𝐿
𝑑1 + 𝑑2
𝐴 = 30 𝑑1 = 8 − 5 = 3 𝑑2 = 8 − 3 = 5 𝐿 = 10
3
𝑚𝑜𝑑𝑒 = 30 + (10) = 33.75
5+3
2) the median
Cumulative table
5
Less than Cum freq.
Less than 10 0
Less than 20 3
Less than 30 8
Less than 40 16
Less than 50 19
Less than 60 20
the rank of median

𝑛 20
𝑟𝑎𝑛𝑘 = = = 10
2 2
The value of median
𝑛
2 − 𝑓1
𝑚𝑒𝑑𝑖𝑎𝑛 = 𝐴 + 𝐿
𝑓2 − 𝑓1
𝑛
𝐴 = 30 = 10 𝑓1 = 8 𝑓2 = 16
2
10 − 8
𝑚𝑒𝑑𝑖𝑎𝑛 = 30 + (10) = 32.5
16 − 8
The range = higher category center – the lower category center

higher category center= 55
the lower category center=15
𝑅 = 55 − 15 = 40
The variance
classes freq x (𝑋 − 𝑋̅) (𝑋 − 𝑋̅)2 (𝑋 − 𝑋̅)2 𝐹

10- 3 15 -17 289 867
20- 5 25 -7 49 245
30- 8 35 3 9 72
40- 3 45 13 169 507
50-60 1 55 23 529 529
total 20 640 172 2220
The variance
∑(𝑋 − 𝑋̅)2 𝐹 2220
𝑉( 𝑋) = = = 116.84
𝑛−1 19
The standard deviation
6
∑(𝑋 − 𝑋̅)2 𝐹 2220
𝑆. 𝐷 = √ =√ = 10.8
𝑛−1 19
The coefficient of variation

𝑆 10.8
× 100 = × 100 = 33.75%
𝑋̅ 32
- the first skewness coefficient

- the first pearson skewness coefficient
3(𝑥̅ − 𝑄2 ) 3(32 − 32.5)
𝑠𝑘1 = = = −0.13
𝑠 10.8
- the second pearson skewness coefficient
(𝑥̅ − 𝑚𝑜𝑑𝑒) (32 − 34)
𝑠𝑘2 = = = −0.185
𝑠 10.8
Negative skewed

Lecture 8

Uploaded by

Copyright:

Available Formats

Lecture 8

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lecture 8

Uploaded by

Copyright:

Available Formats

Coefficient of Skewness

➢ -3 > Sk1& SK2 < 3

The first chart (from left) is positively skewed

Five-Number Summary: 30-47-83.5-164-296

1) Find the mean and the mode

the rank of median

The range = higher category center – the lower category center

classes freq x (𝑋 − 𝑋̅) (𝑋 − 𝑋̅)2 (𝑋 − 𝑋̅)2 𝐹

The coefficient of variation

- the first skewness coefficient

You might also like