Skewness Formula: Methods to Measure Skewness, Types, and Solved Examples

Collegedunia Team logo

Collegedunia Team

Content Curator

Skewness represents deviating from a symmetrical bell curve. It shows an asymmetrical curve with a tail extending to the right (positive skew) or to the left (negative skew).

  • It also indicates that a dataset's mean, median, and mode have different values.
  • The skewness formula can be calculated using the mean of the distribution, the number of variables, and the standard deviation of the distribution.
  • It is a statistical metric that may be used to indicate a probability distribution's asymmetry.
  • Skewness is used to identify outliers in a dataset. It also indicates where the data set is trending.
  • This knowledge is essential in finance since it allows investors to minimize the risks related to their investments.

Key Terms: Symmetry, Asymmetry, Variables, Probability, Skewness, Standard derivation, Mean, Distribution, Mode, Median, Skewness formula, Co-efficient of Skewness


Mean, Median, and Mode

[Click Here for Sample Questions]

To know about the skewness formula, we have to first learn the Mean, Median, and Mode.

Mean

The average of the numbers in the data distribution is called the mean. It is determined by adding all of the values in the dataset and dividing the sum by the number of values in the dataset.

Mean = Sum of all values in Dataset / Total number of values

Example: Find the mean of a dataset of exam scores: 60, 70, 75, 80, and 85.

Ans. Mean = (60 + 70 + 75 + 80 + 85) / 5 = 74

So the mean of this dataset is 74.

Median

The median is the middle value of a dataset when the values are ordered from least to greatest.

Example: Find the median of a dataset of exam scores: 75, 65, 80, 70, 90

Ans. We have to first arrange the given dataset from least to greatest value

65, 70, 75, 80, 90

Therefore, the middle value is 75. so, the median is 75.

Mode

The most frequently used number in data is known as the mode of the data.

Example: Find the mode of the given dataset: 1, 3, 0, 3, 1, 4, 3, 2, 0, 5.

Ans. The most frequently used number in the given dataset is 3. Therefore, the mode of the dataset is 3.

Also Read:


Skewness Formula

[Click Here for Sample Questions]

The skewness formula is named so because the plotted graph appears skewed. Skewness is a statistical measure that shows an asymmetric probability distribution.

The formula of Skewness is given by

\(Skewness = \frac {3(Mean - Median)}{Standard\:Deviation\:(SD)}\)

The standard deviation used in the above formula is given by

\(Standard \: Deviation = \sqrt {\frac{\sum |x - \bar x|^2}{n}}\)

Where

  • x is the random variable
  • \(\bar x\) is the mean of the data
  • n is the total number of data

Methods to Measure Skewness

[Click Here for Sample Questions]

Skewness can be calculated using Karl Pearson's Coefficient of Skewness.

Karl Pearson’s Co-efficient of Skewness 

The formula to calculate skewness using Karl Pearson's coefficient is given below.

  • Using Mode

\(sk_1 = \frac {x\: - \:Mode}{Standard \: Deviation}\)

  • Using Median

\(sk_2 = \frac {3(x\: - \:Median)}{Standard \: Deviation}\)

Conditions:

  • The coefficient of skewness is zero for symmetrical distribution, if Mean = Mode = Median.
  • The coefficient of skewness will be positive if Mean > Mode.
  • Then the coefficient of skewness will be negative if Mean < Mode.

The sign of the Karl person`s coefficient of skewness is positive for positively skewed and negative for negatively skewed.


Types of Skewness

[Click Here for Sample Questions]

There are 3 types of Skewness:

  • Positive Skewness
  • Negative Skewness
  • Zero Skewness

Positive Skewness

Positive skewness indicates that the tail on the right side of the distribution is longer. The mean and median will be larger than the mode.

The condition for positive skewness is

Mean > Median > Mode

Negative Skewness

Negative skewness occurs when the tail on the left side of the distribution is longer than the tail on the right. The mean and median will be smaller than the mode.

The condition for negative skewness is

Mode > Median > Mean

Zero Skewness

Zero skewness is also referred to as a "symmetric distribution". It indicates that data is distributed uniformly around the mean, with no lengthy tails on either end of the distribution.

The condition for zero skewness is

Mean = Mode = Median

Types of Skewness
Types of Skewness

Solved Examples

[Click Here for Sample Questions]

Ques. Find the skewness for the given Data (3, 4, 5, 5).

Ans. The given data is (3, 4, 5, 5)

Number of terms (n) = 4 (Here n is even)

Mean of Data = (3 + 4 + 5 + 5) / 4

⇒ Mean of Data = 17 / 4 = 4.25

Median of Data = {[n / 2]th term + [n / 2 + 1]th term} / 2

⇒ Median of Data = [(4 /2)th term + (4/2 +1)th term] / 2

⇒ Median of Data = [2nd term + 3rd term] / 2

⇒ Median of Data = [4 + 5] / 2 = 9/2 = 4.5

Standard deviation, S.D. = √[(3 – 4.5)2 + (4 – 4.5)2 + (5 – 4.5)2 + (5 – 4.5)2 / 4]

⇒ S.D = √[(2.25 + 0.25 + 0.25 + 0.25) / 4]

⇒ S.D = √(0.75) = 0.87

The formula of Skewness is given by

Skewness = 3(Mean – Median)/S.D.

On substituting the values, we get

Skewness = 3(4.25 – 4.5) / 0.87

⇒ Skewness = 3(-0.25)/ 0.87

⇒ Skewness = – 0.86

Therefore, the skewness of these data is negative.

Ques. Find the skewness for the given Data (2, 3, 4, 9).

Ans. The given data is (2, 3, 4, 9)

Number of terms (n) = 4 (Here n is even)

Mean of Data = (2 + 3 + 4 + 9) / 4

⇒ Mean of Data = 18 / 4 = 4.5

Median of Data = {[n / 2]th term + [n / 2 + 1]th term} / 2

⇒ Median of Data = [(4/2)th term + (4/2 +1)th term] / 2

⇒ Median of Data = [2nd term + 3rd term] / 2

⇒ Median of Data = [3 + 4] / 2 = 7/2 = 3.5

Standard deviation, S.D. = √[(2 – 3.5)2 + (3 – 3.5)2 + (4 – 3.5)2 + (9 – 3.5)2 / 4]

⇒ S.D = √[(2.25 + 0.25 + 0.25 + 30.25) / 4]

⇒ S.D = √(8.25) = 2.87

The formula of Skewness is given by

Skewness = 3(Mean – Median)/S.D.

On substituting the values, we get

Skewness = 3(4.5 – 3.5) / 2.87

⇒ Skewness = 3(1)/ 2.87

⇒ Skewness = 1.04

Therefore, the skewness of these data is positive.


Things to Remember

  • Skewness refers to the degree of asymmetry in a probability distribution.
  • The Skewness formula is given by \(Skewness = \frac {3(Mean - Median)}{Standard\:Deviation\:(SD)}.\)
  • Standard deviation is given by the formula \(Standard \: Deviation = \sqrt {\frac{\sum |x - \bar x|^2}{n}}.\)
  • There are three types of skewness i.e. positive, negative, and zero.
  • The coefficient of skewness is zero for symmetrical distribution, if Mean = Mode = Median.

Also Read:


Sample Questions

Ques. Find the skewness in the following data. (4 Marks)
Find the skewness in the following data

Ans. We must compute the skewness to determine how skewed these data are in comparison to other data sets.

The sample size and sample mean must be determined.

N = 5 +18 + 42 + 27 + 8 = 100

\(\bar{x}\) = (61*5) + (64*18) + (67*42) + (70*27) + (73*8) / 100

\(\bar{x}\) = 6745/100

\(\bar{x}\) = 67.45

Now with the mean, we can compute the skewness.

Now, the skewness is: 

The skewness
The skewness

Ques. What would be the position of the mean or median if the distribution is negatively skewed? (4 Marks)

Ans. The Mean would be less than the mode. For the positively skewed distribution, the frequency curve has a longer tail towards the right. Karl Pearson's measure of skewness is based on the divergence of the mean from the mode in a skewed distribution

⇒ Sk = (Mean – Mode)/Standard deviation

The sign Sk gives the direction and its magnitude gives the extent of skewness.

If Sk > 0 the distribution is positively skewed.

If Sk < 0 the distribution is negatively skewed.

⇒ To obtain the Sk < 0 we have one condition.

∴ Mean will be less than the mode.

Ques. For the distribution of students’ height, the quartiles are 60.125, 61.345, and 62.688. What would be the absolute measure of skewness? (4 Marks)

Ans. Given:

  • μ1 = 60.125
  • μ2 = 61.345
  • μ3 = 62.688

The skewness coefficient is denoted by β1

⇒ β1 = (μ3)2/(μ2)2

⇒ (62.688)2/(61.345)3 

⇒β1 = 0.0170

Absolute skewness measurement = γ1

⇒ γ1 = √(β1)

⇒ √(0.0170)

∴ The absolute skewness measurement is 0.123

Ques. The first four raw moments of distribution are 2, 136, 320, and 40,000. What would be the coefficient of skewness? (4 Marks)

Ans. Given μ'1, μ2, μ'3, μ'4 are row moments

μ’1 = 2

μ’2 = 136

μ’3 = 320

μ’4 = 40,000

We have to find first our central moments:

μ1 = μ’1 = 2

μ2 = μ’2 – (μ’1)2

⇒ 136 – (2)2

⇒ 136 – 4

⇒ 132

μ3 = μ’3 – 3 × μ’2μ’1 + 2 × (μ’1)3

⇒ 320 – 3 × 136 × 2 + 2 × (2)3

⇒ 320 – 816 + 16

⇒ - 480

μ4 = μ’4 – 4 × μ’1 × μ’3 + 6 × μ’2 × (μ’1)2 – 3 × (μ’1)4

⇒ 40000 – 4 × 2 × 320 + 6 × 136 × 22 – 3 × 24

⇒ 40000 – 2560 + 3264 – 48

⇒ 40656

The coefficient of skewness denoted by β1

⇒ β1 = μ2332

⇒ (-480)2/(132)3

∴ The coefficient of skewness is (-480)2/(132)3

Ques. If Bowley’s coefficient of skewness is less than zero, then what type of distribution would be? (2 Marks)

Ans. Bowley’s coefficient of skewness is based on the quartile. The formula for calculating the coefficient of skewness is given by

⇒ Sk = [(Q3 – Q2) – (Q2 – Q1)]/(Q3 – Q1)

⇒ (Q3 – 2Q­2 + Q1)/(Q3 – Q­1)

The value of Sk would be zero if it is asymmetrical distribution

If the value is less than zero, then it is a negatively skewed distribution

It will take a value between + 1 and - 1

Ques. If μ4, = 199, μ3 = 50, and μ2 = 8, then what is the value of excess kurtosis? (3 Marks)

Ans. μ4 = 199

μ3 = 50

μ2 = 8

Kurtosis a4= μ4/(μ2)2

Excess kurtosis = a4 – 3

a4 = 199/(8)2

⇒ 199/64

⇒ 3.109

⇒ Excess kurtosis is denoted by g2

⇒ g2 = a4 – 3

⇒ 3.109 – 3

∴ Excess kurtosis is 0.109

Ques. For a distribution, the percentile partition values are P10 = 58.983, P50 = 61.345 and P90 = 63.831. Then what is Kelly's coefficient of skewness? (3 Marks)

Ans. Kelly’s skewness denoted by Sk

Sk = P90 + P10 – 2P50

P90, P10, P50 are percentile partition

Sk = 63.831 + 58.983 + 2 × 61.345

⇒ 122.814 – 122.69

⇒ 0.124

Kelly’s coefficient of skewness denoted by Sp

SP = (P90 + P10 – 2P50)/P90 – P10

⇒ 0.124/4.848

∴ Kelly’s coefficient of skewness is 0.026

Ques. For distribution with mean, median, mode, and standard deviation 25, 24, 26, and 5 respectively. Find Karl Pearson's coefficient of skewness. (2 Marks)

Ans. Mean = xÌÂ = 25

Median = Md = 26

Standard deviation = σ = 5

Karl Pearson coefficient of skewness = SKp = (Mean – Mode)/Standard deviation

SKP = (25 – 26)/5

⇒ -1/5 = -0.2

∴ The Karl Pearson coefficient of skewness is -0.2

Ques. The following measures were computed for a moderately symmetrical frequency distribution: mean = 50, coefficient of variation = 35%, and Karl Pearson's Coefficient of Skewness = - 0.25. Find the value of the median of the distribution. (4 Marks)

Ans. Mean = XÌÂ = 50

Coefficient of variation = CV = 35%

Coefficient of skewness = SKp = -0.25

CV = (σ/XÌÂ) × 100

SKp = (Mean – Mode)/σ

Mode = 3 × Median – 2 × Mean

σ = Standard deviation

CV = (σ/xÌÂ) × 100

⇒ 35 = (σ/50) × 100

∴ σ = 35/2 = 17.5

Coefficient of skewness = (Mean – Mode)/σ

⇒ - 0.25 = (50 – Mode)/17.5

⇒ (50 – Mode) = 0.25 × 17.5

∴ Mode = 50 + 4.375 = 54.375

Mode = 3 × Median – 2 × Mean

⇒ 54.375 = 3 × Median – 2 × 50

⇒ 3 × Median = 100 + 54.375

⇒ Median = 154.375/3 = 51.458

∴ The value of the median is 51458/1000 = 1235/24

Ques. The first four moments about the mean of distribution are 0, μ2, 0.7, and 18.75. If the distribution is mesokurtic, find the value of μ2. (3 Marks)

Ans. μ1 = 0

μ3 = 0.7

μ4 = 18.75

β2 = 3 (distribution is mesokurtic)

β2 = (μ4)/(μ2)2

μ2 and μ4 are moments about the mean

β2 = Coefficient of kurtosis

According to the formula,

⇒ 3 = 18.75/(μ2)2

⇒ μ22 = 18.75/3

⇒ 6.25

∴ The value of μ2 = 2.5

For Latest Updates on Upcoming Board Exams, Click Here: https://t.me/class_10_12_board_updates


Check-Out: 

CBSE CLASS XII Related Questions

  • 1.
    Find:

    The shortest distance between the lines: \[ \vec{r}=(4+\lambda)\hat{i}+(2\lambda-1)\hat{j}-3\lambda\hat{k} \] and \[ \vec{r}=(1+2\mu)\hat{i}+(4\mu-1)\hat{j}+(2-5\mu)\hat{k} \]


      • 2.

        An NGO organises a charity event in which they decide to distribute woollen caps to protect children from winter. The caps to be distributed are in three separate boxes, Box I has 30 red caps, Box II has 20 red and 10 green caps, and Box III has 30 green caps. The probability that a Box i is selected and a cap picked out is i/6, where i = 1, 2, 3.  
        Based on the above information, answer the following questions :


          • 3.
            Which of the following equations is NOT a Linear Differential Equation?

              • \((1 + x^2) \, dy + 2xy \, dx = \cot x \, dx\)
              • \(y + \frac{d}{dx}(xy) = x(\sin x + \log x)\)
              • \(x(1 + y^2) \, dx - y(1 + x^2) \, dy = 0\)
              • \(y \, dx - (x + 3y^2) \, dy = 0\)

            • 4.
              Find:

              If the function \[ f(x)= \begin{cases} \frac{\sin x}{x}+\cos x, & x\neq0\\ k, & x=0 \end{cases} \] is continuous at \(x=0\), then find the value of \(k\).

                • \(0\)
                • \(-2\)
                • \(-1\)
                • \(2\)

              • 5.

                At a birthday party, children are being served orange juice in conical cups, as shown in the figure. 


                Each cup is 15 cm deep and has a radius 5 cm. The juice is being poured into this cup at a rate of 0·1 cm3/s.
                On the basis of the above information, answer the following questions :


                  • 6.
                    Differentiate \( \tan^{-1}\left( \frac{\sqrt{1 + x^2} + \sqrt{1 - x^2}}{\sqrt{1 + x^2} - \sqrt{1 - x^2}} \right) \) with respect to \( \cos^{-1}(x^2) \).

                      CBSE CLASS XII Previous Year Papers

                      Comments


                      No Comments To Show