How much will the variance vary?

Suppose there exists a set of obsevation whose variance is 11. If each term of this set is multiplied by 3, then find the new variance of this set.


The answer is 99.

This section requires Javascript.
You are seeing this because something didn't load right. We suggest you, (a) try refreshing the page, (b) enabling javascript if it is disabled on your browser and, finally, (c) loading the non-javascript version of this page . We're sorry about the hassle.

2 solutions

Ashish Menon
Jun 18, 2016

So, lets derive a general formula:-
Let x i = x 1 , x 2 , x 3 , x_i = x_1, x_2, x_3, \cdots be n n values of variable X X .
Let k i = k 1 , k 2 , k 3 , k_i = k_1, k_2, k_3, \cdots be n n values of variable K K such that k i = y x i k_i = yx_i where y y is any non-zero real number.
If K \overline{K} be the mean of the obversations of k i k_i and X \overline{X} be the mean of the observations of x i x_i .


K = 1 n i = 1 n k i = 1 n i = 1 n y x i = 1 n × i = 1 n x i × n y = y ( i = 1 n x i ) K = y X k i K = y x i y X ( because k i = y x i ) k i K = y ( x i x ) ( k i K ) 2 = y 2 ( x i X ) 2 ( Squaring on both sides ) i = 1 n ( k i K ) 2 = y 2 i = 1 n ( x i X ) 2 1 n i = 1 n ( k i K ) 2 = 1 n y 2 i = 1 n ( x i X ) 2 1 n i = 1 n ( k i K ) 2 = y 2 ( 1 n i = 1 n ( x i X ) 2 ) Var(K) = y 2 Var(X) \begin{aligned} \overline{K} & = \dfrac{1}{n} \displaystyle \sum_{i = 1}^{n} k_i\\ \\ & = \dfrac{1}{n} \displaystyle \sum_{i = 1}^{n} yx_i\\ \\ & = \dfrac{1}{n} × \displaystyle \sum_{i = 1}^{n} x_i × ny\\ \\ & = y\left(\displaystyle \sum_{i = 1}^{n} x_i\right)\\ \\ \overline{K} & = y\overline{X}\\ \\ k_i - \overline{K} & = yx_i - y\overline{X} \color{#EC7300}{\left(\text{because} \, k_i = yx_i\right)}\\ \\ k_i - \overline{K} & = y\left(x_i - x\right)\\ \\ {\left(k_i - \overline{K}\right)}^2 & = y^2{\left(x_i - \overline{X}\right)}^2 \color{#EC7300}{\left(\text{Squaring on both sides}\right)}\\ \\ \displaystyle \sum_{i = 1}^n {\left(k_i - \overline{K}\right)}^2 & = y^2 \displaystyle \sum_{i= 1}^{n} {\left(x_i - \overline{X}\right)}^2\\ \\ \dfrac{1}{n} \displaystyle \sum_{i = 1}^n {\left(k_i - \overline{K}\right)}^2 & = \dfrac{1}{n} y^2 \displaystyle \sum_{i = 1}^{n} {\left(x_i - \overline{X}\right)}^2\\ \\ \dfrac{1}{n} \displaystyle \sum_{i = 1}^n {\left(k_i - \overline{K}\right)}^2 & = y^2 \left(\dfrac{1}{n} \displaystyle \sum_{i = 1}^{n} {\left(x_i - \overline{X}\right)}^2\right)\\ \color{#20A900}{\text{Var(K)}} & = \color{#20A900}{y^2 \text{Var(X)}} \end{aligned}

So, this means if we multiply any set of observations by any non-zero real number y y , the variance increases y 2 y^2 times.


So, in the given question observations are multiplied by 3 3 .
So, new variance will be:-
11 × 3 2 = 11 × 9 = 99 \begin{aligned} 11 × 3^2 & = 11 × 9\\ & = \color{#3D99F6}{\boxed{99}} \end{aligned}

Kexin Zheng
Jun 19, 2016

We know that because variance = (standard deviation)^2, the old SD = sqrt(11). When each element of the old set is multiplied by 3, the SD of the resulting set is also multiplied by 3, giving the new SD to be 3sqrt(11). Thus, the new variance is (3sqrt(11))^2 = 99.

0 pending reports

×

Problem Loading...

Note Loading...

Set Loading...