Scribd
Upload
257 views23 pages

Skewness, Moments and Kurtosis

Karl Pearson's coefficient of skewness is used to quantify the degree of skewness of a distribution. It is calculated as the ratio of the difference between the mean and median to the standard deviation. A skewness value between -0.5 and 0.5 indicates an approximately symmetric distribution, between -1 and -0.5 or 0.5 and 1 indicates a moderately skewed distribution, and less than -1 or greater than 1 indicates a highly skewed distribution. The document provides examples of calculating skewness for different distributions.

Uploaded by

Meet Patel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
257 views23 pages

Skewness, Moments and Kurtosis

Karl Pearson's coefficient of skewness is used to quantify the degree of skewness of a distribution. It is calculated as the ratio of the difference between the mean and median to the standard deviation. A skewness value between -0.5 and 0.5 indicates an approximately symmetric distribution, between -1 and -0.5 or 0.5 and 1 indicates a moderately skewed distribution, and less than -1 or greater than 1 indicates a highly skewed distribution. The document provides examples of calculating skewness for different distributions.

Uploaded by

Meet Patel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 23

Skewness

Karl Pearson’s coefficient of skewness


Mean  Mode
Sk 
SD
Sk = 3(Mean – Median)/SD
 If skewness is less than -1 or greater than 1, the distribution is highly skewed.
 If skewness is between -1 and -0.5 or between 0.5 and 1, the distribution is
moderately skewed.
 If skewness is between -0.5 and 0.5, the distribution is approximately symmetric.

Skewness is zero if mean=median=mode, for a symmetrical distribution – mean,


median and mode coincide.

For a positively skewed distribution, the value of Mean is the greatest of the three
measures and the value of Mode is the least of the three measures.

For a negatively skewed distribution, the value of Mode is the greatest of the three
measures and the value of Mean is the least of the three measures.

Range = Xmax - Xmin

Xmax = mean + ½(range)

Xmin = mean – ½(range)

Xmax + Xmin = 2Mean

1. Calculate the Karl Pearson’s coefficient of skewness:

Size (x) Frequency (f) fx X2 Fx2


1 10 10 1 10
2 18 36 4 72
3 30 90 9 270
4 25 100 16 400
5 12 60 25 300
6 3 18 36 108
7 2 14 49 98
Total N=100 ∑fx=32 ∑fx2 = 1258
8

Mean = ∑fx /N = 3.28


Mode = 3
SD = underroot (∑fx2/N)-(Mean)2 = underroot((1258/100) – 3.282 = 1.35
Sk = (Mean-Mode)/sd = (3.28 – 3)/1.35 = 0.2075
Distribution is positively skewed.

2. Calculate the Karl Pearson’s coefficient of skewness:

Hourly No. of Workers Mid point (x) fx Less than cf


Wages (Rs) (f)
40-50 5 45 5
50-60 6 55 11
60-70 8 65 19
70-80 10 75 29
80-90 25 85 54
90-100 30 95 84
100-110 36 105 120
110-120 50 115 170 – median class
120-130 60 125 230
130-140 70 135 300
Total 300

Mean = 110.93
Since the maximum frequency 70 occurs towards the end of the frequency
distribution, mode is not defined properly. Hence, use the formula with
median.
Median = 116
SD = 22.3043
Sk = 3(Mean-Median)/SD = -0.6819
Distribution is negatively skewed

3. Find Karl Pearson’s coefficient of skewness.

Wages more than (Rs) Number of earners


5 100
15 80
25 75
35 60
45 55
55 20
65 0

Wages f Mid fx cf x- (x-xbar)2 f(x-xbar)2


(Rs) point x xbar
5-15 20 10 200 20 -29 841 16820
15-25 5 20 100 25 -19 361 1805
25-35 15 30 450 40 -9 81 1215
35-45 5 40 200 45 1 1 5
45-55 35 50 1750 80 – 11 121 4235
median
class
55-65 20 60 1200 100 21 441 8820
N=100 3900 1846 32900

Mean = 3900/100 = 39
N/2 = 50
Median = 45 + (50 – 45)/35 *10 = 46.42
SD = underroot (32900/100) = 18.13
Sk = 3(mean – median)/sd = 3(39-46.42)/18.13 = -1.22
Distribution is negatively skewed
4. Consider the following distributions:

Distribution A Distribution B
Mean 100 90
Median 90 80
SD 10 10

a. Distribution A has the same degree of the variation as distribution B


b. Both distributions have same degree of skewness. True/False.

CV for distribution A = 100* SD/Mean = 100*10/100 = 10%

CV for distribution B = 100*10/90 = 11.11%

CV for distribution B has more variation than CV for distribution A.

Statement (a) is wrong.

(b) Sk = 3(mean-median)/sd = 3(100-90)/10 = 3

Sk (B) = 3(90-80)10 = 3

True statement

5. Pearson’s coefficient of skewness for a distribution is 0.4 and its coefficient


of variation is 30%. Its mode is 88, find mean and median.

Given: Sk = 0.4; CV = 30%; mode = 88


Find: mean and median

Sk = (Mean – Mode)/sd
0.4 = (mean-88)/sd ---- A

CV = sd/mean *100
30 = 100sd/mean
Sd = 30mean/100 --- B

Substituting B in A
0.4 = (mean – 88)/ 30mean/100
0.4 = 100(mean – 88)/ 30mean) = (100mean – 8800)/30mean
0.4 *30mean = 100mean – 8800
12mean = 100mean-8800
8800 = 88mean
Mean = 100

Substituting mean in B, we get SD = 30

Sk = 3(mean-median)/sd
0.4 = (3*100 – 3median)/30
Median = 96

6. Scores of 100 students in an aptitude test are given below: calculate Karl
Pearson’s coefficient of skewness.

Scores No of students Mid point (x) fx (x- (x- f(x-


(f) xbar) xbar)2 xbar)2
0-10 10 5 50 -26.4 696.96 6969.6
10-20 15 15 225 -16.4 268.96 4034.4
20-30 24 25 600 -6.4 40.96 983.04
30-40 25 – modal class 35 875 3.6 12.96 324
40-50 10 45 450 13.6 184.96 1849.6
50-60 10 55 550 23.6 556.96 5569.6
60-70 6 65 390 33.6 1128.9 6773.76
6
N=100 Total 3140 26504

Mean = ∑fx/N = 3140/100 = 31.4

Mode = L+ h*(f1-f0)/(2f1-f0-f2)
= 30 + 10(25-24)/(2*25-24-10) = 30.63

Sd = underroot(∑f(x-xbar)2/N) = underroot(26504/100) = 16.28

Sk = (mean – mode)/sd = (31.4 – 30.63)/16.28 =0.04

Distribution is low degree of positively skewed


 If skewness is less than -1 or greater than 1, the distribution is highly skewed.
 If skewness is between -1 and -0.5 or between 0.5 and 1, the distribution is
moderately skewed.
 If skewness is between -0.5 and 0.5, the distribution is approximately symmetric.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy