91影视

Independent Random variables$=X_1,X_2$

$Var\left(X_1\right)={蟽}_1^2$

$Var\left(X_2\right)={蟽}_2^2$

$渭=?$

$位X_1+(1-位)X_2$ will be used as an estimate of$渭.$

Suppose that $X_1$and $X_2$are independent random variables having a common mean $渭$.

Let $位X_1+(1-位)X_2$will be used as an estimate of $渭$for some appropriate value of $位$. It is known that $Var\left(X_1\right)={蟽}_1^2$and $Var\left(X_2\right)={蟽}_2^2$

Find the variance of $位X_1+(1-位)X_2,$

$\begin{array}{r}\mathrm{Var}\left(位X_1+(1鈭�位)X_2\right)=\mathrm{Var}\left(位X_1\right)+\mathrm{Var}\left[(1鈭�位)X_2\right]\end{array}$

role="math" $={位}^2\mathrm{Var}\left(X_1\right)+(1鈭�位{)}^2\mathrm{Var}\left[X_2\right]$

$={位}^2{蟽}_1^2+(1鈭�位{)}^2{蟽}_2^2$

Find the value of $位$yields the estimate having the lowest possible variance:

Differentiate with respect to $位$and then equating to $0.$

$\begin{array}{r}\frac{d}{d位}\left[\mathrm{Var}\left(位X_1+(1鈭�位)X_2\right)\right]=0\end{array}$

$\begin{array}{r}\frac{d}{d位}\left[{位}^2{蟽}_1^2+(1鈭�位{)}^2{蟽}_2^2\right]=0\end{array}$

role="math" $2位{蟽}_1^2鈭�2(1鈭�位){蟽}_2^2=0$

$位=\frac{{蟽}_2^2}{{蟽}_1^2+{蟽}_2^2}$

The reason for it is desirable to use this value of$位,$

As $Var\left[位X_1+(1-位)X_2\right]=E\left[{\left(位X_1+(1-位)X_2\right)}^2\right]$then $位$is to be small.