📂Mathematical Statistics

Properties of Mean and Variance

Theorem

The mean $E ( X ) = \mu_{X}$ and variance $\Var (X) = E [ ( X - \mu_{X} )^2 ]$ have the following properties:

• [1]: $E(X + Y) = E(X) + E(Y)$
• [2]: $E(aX + b) = a E(X) + b$
• [3]: $\Var (X) \ge 0$
• [4]: $\Var ( X ) = E(X^2) - \mu_{X}^2$
• [5]: $\Var (aX + b) = a^2 \Var (X)$

Explanation

As they relate to mean and variance, these are very important properties. Specifically, [1] and [2] are properties known as Linearity, which make handling equations very convenient.

Proof

[1]

For discrete cases $$\begin{align*} E ( X + Y ) =& \sum (xp(x) + yp(y) ) \\ =& \sum xp(x) + \sum yp(y) \\ =& E(X) + E(Y) \end{align*}$$ For continuous cases $$\begin{align*} E ( X + Y ) =& \int_{-\infty}^{\infty} \int_{-\infty}^{\infty} (x + y) f(x,y) dx dy \\ =& \int_{-\infty}^{\infty} \int_{-\infty}^{\infty} x f(x,y) dx dy + \int_{-\infty}^{\infty} \int_{-\infty}^{\infty} y f(x,y) dx dy \\ =& E(X) + E(Y) \end{align*}$$

■

[2]

For discrete cases $$\begin{align*} E ( aX + b ) =& \sum \left( a x p(x) + b p(x) \right) \\ =& a \sum x p(x) + b \sum p(y) \\ =& a E(X) + b \end{align*}$$ For continuous cases $$\begin{align*} E ( aX + b ) =& \int_{-\infty}^{\infty} (ax+b) f(x) dx \\ =& \int_{-\infty}^{\infty} a xf(x) dx + \int_{-\infty}^{\infty} b f(x) dx \\ =& a \int_{-\infty}^{\infty} xf(x) dx + b \int_{-\infty}^{\infty} f(x) dx \\ =& a E(X) + b \end{align*}$$

■

[3]

Since $( X - \mu_{X} )^2 \ge 0$, then $\Var (X) = E [ ( X - \mu_{X} )^2 ] \ge 0$

■

[4]

$$\begin{align*} \Var (X) =& E [ ( X - \mu_{X} )^2 ] \\ =& E (X^2 - 2 \mu_{X} X + \mu_{X}^2 ) \\ =& E (X^2) - 2 \mu_{X} E(X) + \mu_{X}^2 \\ =& E(X^2) - \mu_{X}^2 \end{align*}$$

■

[5]

According to theorem [2], if $Y = a X + b$ then $\mu_{Y} = a \mu_{X} + b$ and $$\begin{align*} \Var (Y) =& E [ ( Y - \mu_{Y} )^2 ] \\ =& E [ ( aX + b - a \mu_{X} - b )^2 ] \\ =& E [ a^2 ( X - \mu_{X} )^2 ] \\ =& a^2 \Var (X) \end{align*}$$

■