Advertisements
Advertisements
Question
The mean and standard deviation of a set of n1 observations are `barx_1` and s1, respectively while the mean and standard deviation of another set of n2 observations are `barx_2` and s2, respectively. Show that the standard deviation of the combined set of (n1 + n2) observations is given by
S.D. = `sqrt((n_1(s_1)^2 + n_2(s_2)^2)/(n_1 + n_2) + (n_1n_2 (barx_1 - barx_2)^2)/(n_1 + n_2)^2)`
Solution
Let xi' = 1, 2, 3, 4, ..., n1
And yj' = 1, 2, 3, 4, ..., n2
∴ `barx_1 = 1/n_1 sum_(i = 1)^n x_i`
And `barx_2 = 1/n_2 sum_(j = 1)^n y_j`
⇒ `sigma_1^2 = 1/n_1 sum_(i = 1)^(n_1) (x_i - barx_1)^2`
And `sigma_2^2 = 1/n_2 sum_(j = 1)^(n_2) (y_i - barx_2)^2`
Now mean of the combined series is given by
`barx = 1/(n_1 + n_2) [sum_(i = 1)^(n_1) + sum_(j = 1)^(n_2) y_j]`
= `(n_1 barx_1 + n_2 x_2)/(n_1 + n_2)`
Therefore, `sigma^2` of the combined series is
`sigma^2 = 1/(n_1 + n_2) [sum_(i = 1)^(n_1) (x_i - barx)^2 + sum_(j = 1)^(n_2) (y_j - barx)^2]`
Now, `sum_(i = 1)^(n_1) (x_i - barx)^2 = sum_(i = 1)^(n_1) (x_i - barx_j + bar_j - barx)^2`
= `sum_(i = 1)^(n_1) (x_i - x_j)^2 + n_1 (barx_j - barx)^2 + 2(barx_j - barx) sum_(i = 1)^(n_1) (x_i - barx_j)^2`
But `sum_(i = 1)^n (x_i - barx_i)` = 0
∵ The algebraic sum of the deviation of values of first series from their mean is zero
Also `sum_(i = 1)^(n_1) (x_i - barx)^2 = n_1s_1^2 + n_1(barx_1 - barx)^2`
= `n_1s_1^2 + n_1d_1^2`
Where `d_1 = (barx_1 - barx)`
Similarly, we have
`sum_(j = 1)^(n_2) (y_j - barx)^2 = sum_(j = 1)^(n_2) (y_j - barx_i + barx_i - barx)^2`
= `n_2s_2^2 + n_2d_2^2`
Where `d_2 = (barx_2 - barx)`
Now combined Standard Deviation (S.D.)
`sigma = sqrt((n_1(s_1^2 + d_1^2) + n_2(s_2^2 + d_2^2))/(n_1 + n_2))`
Where `d_1 = barx_1 - barx`
= `barx_1 - ((n_1barx_1 + n_2 barx_2)/(n_1 + n_2))`
= `(n_2(barx_1 - barx_2))/(n_1 + n_2)`
And `d_2 = barx_2 - barx`
= `barx_2 - ((n_1barx_1 + b_2barx_2)/(n_1 + n_2))`
= `(n_1(barx_2 - barx_1))/(n_1 + n_2)`
∴ `sigma^2 = 1/(n_1 + n_2)[n_1s_1^2 + n_2s_2^2 + (n_1n_2^2(barx_1 - barx_2)^2)/(n_1 + n_2)^2 + (n_2n_1^2(barx_2 - barx_1)^2)/(n_1 + n_2)^2]`
So, `sigma = sqrt((n_1s_1^2 + n_2s_2^2)/(n_1 + n_2) + (n_1n_2(barx_1 - barx_2)^2)/(n_1 + n_2)^2`
Hence proved.
APPEARS IN
RELATED QUESTIONS
Find the mean and variance for the first n natural numbers.
The sum and sum of squares corresponding to length x (in cm) and weight y (in gm) of 50 plant products are given below:
`sum_(i-1)^50 x_i = 212, sum_(i=1)^50 x_i^2 = 902.8, sum_(i=1)^50 y_i = 261, sum_(i = 1)^50 y_i^2 = 1457.6`
Which is more varying, the length or weight?
The mean and variance of 7 observations are 8 and 16, respectively. If five of the observations are 2, 4, 10, 12 and 14. Find the remaining two observations.
The mean and standard deviation of marks obtained by 50 students of a class in three subjects, Mathematics, Physics and Chemistry are given below:
|
Subject |
Mathematics |
Physics |
Chemistry |
|
Mean |
42 |
32 |
40.9 |
|
Standard deviation |
12 |
15 |
20 |
Which of the three subjects shows the highest variability in marks and which shows the lowest?
Find the mean, variance and standard deviation for the data:
2, 4, 5, 6, 8, 17.
The mean and standard deviation of 6 observations are 8 and 4 respectively. If each observation is multiplied by 3, find the new mean and new standard deviation of the resulting observations.
For a group of 200 candidates, the mean and standard deviations of scores were found to be 40 and 15 respectively. Later on it was discovered that the scores of 43 and 35 were misread as 34 and 53 respectively. Find the correct mean and standard deviation.
Calculate the A.M. and S.D. for the following distribution:
| Class: | 0-10 | 10-20 | 20-30 | 30-40 | 40-50 | 50-60 | 60-70 | 70-80 |
| Frequency: | 18 | 16 | 15 | 12 | 10 | 5 | 2 | 1 |
A student obtained the mean and standard deviation of 100 observations as 40 and 5.1 respectively. It was later found that one observation was wrongly copied as 50, the correct figure being 40. Find the correct mean and S.D.
Find the mean and variance of frequency distribution given below:
| xi: | 1 ≤ x < 3 | 3 ≤ x < 5 | 5 ≤ x < 7 | 7 ≤ x < 10 |
| fi: | 6 | 4 | 5 | 1 |
Coefficient of variation of two distributions are 60% and 70% and their standard deviations are 21 and 16 respectively. What are their arithmetic means?
From the data given below state which group is more variable, G1 or G2?
| Marks | 10-20 | 20-30 | 30-40 | 40-50 | 50-60 | 60-70 | 70-80 |
| Group G1 | 9 | 17 | 32 | 33 | 40 | 10 | 9 |
| Group G2 | 10 | 20 | 30 | 25 | 43 | 15 | 7 |
Find the coefficient of variation for the following data:
| Size (in cms): | 10-15 | 15-20 | 20-25 | 25-30 | 30-35 | 35-40 |
| No. of items: | 2 | 8 | 20 | 35 | 20 | 15 |
If the sum of the squares of deviations for 10 observations taken from their mean is 2.5, then write the value of standard deviation.
If X and Y are two variates connected by the relation
In a series of 20 observations, 10 observations are each equal to k and each of the remaining half is equal to − k. If the standard deviation of the observations is 2, then write the value of k.
If v is the variance and σ is the standard deviation, then
The standard deviation of first 10 natural numbers is
Let x1, x2, ..., xn be n observations. Let \[y_i = a x_i + b\] for i = 1, 2, 3, ..., n, where a and b are constants. If the mean of \[x_i 's\] is 48 and their standard deviation is 12, the mean of \[y_i 's\] is 55 and standard deviation of \[y_i 's\] is 15, the values of a and b are
The standard deviation of the observations 6, 5, 9, 13, 12, 8, 10 is
If for distribution `sum(x - 5)` = 3, `sum(x - 5)^2` = 43 and total number of items is 18. Find the mean and standard deviation.
Let x1, x2, ..., xn be n observations and `barx` be their arithmetic mean. The formula for the standard deviation is given by ______.
Let x1, x2, x3, x4, x5 be the observations with mean m and standard deviation s. The standard deviation of the observations kx1, kx2, kx3, kx4, kx5 is ______.
Standard deviations for first 10 natural numbers is ______.
The mean and standard deviation of six observations are 8 and 4, respectively. If each observation is multiplied by 3, find the new mean and new standard deviation of the resulting observations.
