Skewness of Geometric Distribution/Formulation 2
Jump to navigation
Jump to search
Theorem
Let $X$ be a discrete random variable with the geometric distribution with parameter $p$ for some $0 < p < 1$.
- $\map X \Omega = \set {0, 1, 2, \ldots} = \N$
- $\map \Pr {X = k} = p \paren {1 - p}^k$
Then the skewness of $X$ is given by:
- $\gamma_1 = \dfrac {2 - p} {\sqrt {1 - p} }$
Proof
From the definition of skewness, we have:
- $\gamma_1 = \expect {\paren {\dfrac {X - \mu} \sigma}^3}$
where:
- $\mu$ is the expectation of $X$.
- $\sigma$ is the standard deviation of $X$.
By Expectation of Geometric Distribution: Formulation 2, we have:
- $\mu = \dfrac {1 - p} p$
By Variance of Geometric Distribution: Formulation 2, we have:
- $\sigma = \dfrac {\sqrt {1 - p} } p$
So:
\(\ds \gamma_1\) | \(=\) | \(\ds \frac {\expect {X^3 - 3 X^2 \mu + 3 X \mu^2 - \mu^3} } {\sigma^3}\) | Cube of Difference | |||||||||||
\(\ds \) | \(=\) | \(\ds \frac {\expect {X^3} - 3 \mu \expect {X^2} + 3 \mu^2 \expect {X} - \mu^3} {\sigma^3}\) | Expectation is Linear | |||||||||||
\(\ds \) | \(=\) | \(\ds \frac {\expect {X^3} - 3 \paren {\dfrac {1 - p} p } \expect {X^2} + 2 \paren {\dfrac {\paren {1 - p} \paren {1 - p}^2 } {p^3} } } {\paren {\dfrac {\paren {1 - p} \sqrt {1 - p} } {p^3} } }\) |
To calculate $\gamma_1$, we must calculate both $\expect {X^2}$ and $\expect {X^3}$.
From Moment in terms of Moment Generating Function:
- $\expect {X^n} = \map { {M_X}^{\paren n} } 0$
where $M_X$ is the moment generating function of $X$.
From Moment Generating Function of Geometric Distribution: Second Moment:
- $\map { {M_X}} t = p \paren {1 - p} e^t \paren {\dfrac {1 + \paren {1 - p} e^t } {\paren {1 - \paren {1 - p} e^t}^3} }$
From Moment Generating Function of Geometric Distribution: Third Moment:
- $\map { {M_X}} t = p \paren {1 - p} e^t \paren {\dfrac {1 + 4 \paren {1 - p} e^t + \paren {1 - p}^2 e^{2t} } {\paren {1 - \paren {1 - p} e^t}^4} }$
Setting $t = 0$ and from Exponential of Zero, we have:
- $\map {M_X} 0 = \dfrac {\paren {1 - p} \paren {2 - p} } {p^2}$
- $\map {M_X} 0 = \dfrac {\paren {1 - p} \paren {6 - 6 p + p^2} } {p^3}$
So:
\(\ds \gamma_1\) | \(=\) | \(\ds \frac {\expect {X^3} - 3 \paren {\dfrac {1 - p} p} \expect {X^2} + 2 \paren {\dfrac {\paren {1 - p} \paren {1 - p}^2 } {p^3} } } {\paren {\dfrac {\paren {1 - p} \sqrt {1 - p} } {p^3} } }\) | ||||||||||||
\(\ds \) | \(=\) | \(\ds \frac {\dfrac {\paren {1 - p} \paren {6 - 6 p + p^2} } {p^3} - 3 \paren {\dfrac {1 - p} p } \dfrac {\paren {1 - p} \paren {2 - p} } {p^2 } + 2 \paren {\dfrac {\paren {1 - p} \paren {1 - p}^2} {p^3} } } {\paren {\dfrac {\paren {1 - p} \sqrt {1 - p} } {p^3} } }\) | ||||||||||||
\(\ds \) | \(=\) | \(\ds \frac {\paren {6 - 6 p + p^2} - 3 \paren {1 - p} \paren {2 - p} + 2 \paren {1 - p}^2} {\sqrt {1 - p} }\) | $\dfrac {1 - p} {p^3}$ cancels | |||||||||||
\(\ds \) | \(=\) | \(\ds \frac {6 - 6 p + p^2 - 6 + 9 p - 3 p^2 + 2 - 4 p + 2 p^2} {\sqrt {1 - p} }\) | ||||||||||||
\(\ds \) | \(=\) | \(\ds \dfrac {2 - p} {\sqrt {1 - p} }\) |
$\blacksquare$