Moment coefficient of skewness for ungrouped data
Let $x_1, x_2,\cdots, x_n$
be $n$ observations. The mean of $X$ is denoted by $\overline{x}$ and is given by
$$ \begin{eqnarray*} \overline{x}& =\frac{1}{n}\sum_{i=1}^{n}x_i \end{eqnarray*} $$
Formula
The moment coefficient of skewness $\beta_1$ is defined as
$\beta_1=\dfrac{m_3^2}{m_2^3}$
The moment coefficient of skewness $\gamma_1$ is defined as
$\gamma_1=\sqrt{\beta_1}=\dfrac{m_3}{m_2^{3/2}}$
where
$n$
total number of observations$\overline{x}$
sample mean$m_2 =\dfrac{1}{n}\sum_{i=1}^n (x_i-\overline{x})^2$
is second sample central moment$m_3 =\dfrac{1}{n}\sum_{i=1}^n (x_i-\overline{x})^3$
is third sample central moment
Example
The hourly earning (in dollars) of sample of 7 workers are :
26, 21, 24, 22, 25, 24, 23.
Compute coefficient of skewness based on moments.
Solution
The sample mean of $X$ is
$$ \begin{aligned} \overline{x} &=\frac{1}{n}\sum_{i=1}^n x_i\\ &=\frac{175}{7}\\ &=25 \text{ dollars} \end{aligned} $$
$x$ | $(x-xb)$ | $(x-xb)^2$ | $(x-xb)^3$ | |
---|---|---|---|---|
27 | 2 | 4 | 8 | |
27 | 2 | 4 | 8 | |
24 | -1 | 1 | -1 | |
26 | 1 | 1 | 1 | |
25 | 0 | 0 | 0 | |
24 | -1 | 1 | -1 | |
22 | -3 | 9 | -27 | |
Total | 175 | 0 | 20 | -12 |
Second sample central moment
The second sample central moment is
$$ \begin{aligned} m_2 &=\frac{1}{n}\sum_{i=1}^n (x_i-\overline{x})^2\\ &=\frac{20}{7}\\ &=2.8571 \end{aligned} $$
Third sample central moment
The third sample central moment is
$$ \begin{aligned} m_3 &=\frac{1}{n}\sum_{i=1}^n (x_i-\overline{x})^3\\ &=\frac{-12}{7}\\ &=-1.7143 \end{aligned} $$
Coefficient of Skewness
The coefficient of skewness based on moments ($\beta_1$) is
$$ \begin{aligned} \beta_1 &=\frac{m_3^2}{m_2^3}\\ &=\frac{(-1.7143)^2}{(2.8571)^3}\\ &=\frac{2.9388}{23.3226}\\ &=0.126 \end{aligned} $$
The coefficient of skewness based on moments ($\gamma_1$) is
$$ \begin{aligned} \gamma_1 &=\frac{m_3}{m_2^{3/2}}\\ &=\frac{-1.7143}{(2.8571)^{3/2}}\\ &=\frac{-1.7143}{4.8293}\\ &=-0.355 \end{aligned} $$
As the value of $\gamma_1 < 0$, the data is $\text{negatively skewed}$.