Statistics
Mean deviation about mean
o For ungrouped data: , where is the mean given by
Mean deviation about mean
For grouped data: , where is the mean given by
Example:Calculate mean deviation about mean for the following data:
20 –
Class 0 – 10 10 – 20 30 – 40
30
Frequency 21 19 49 11
Solution: Here, assumed mean (a) = 25 and class size (h) = 10
Mid-
Frequency
Class point fidi
(fi)
(xi)
0 – 10 21 5 –2 –42 15 315
10 – 20 19 15 –1 –19 5 95
20 – 30 49 25 0 0 5 245
30 – 40 11 35 1 11 15 165
Total 100 –50 820
Here,
Now,
Mean,
Example:
Find the mean deviation about the median for the following data:
181, 29, 150, 270, 160, 16, 27, 180, 200
Solution:
Here, the number of observations is 9 and these can be arranged in ascending order as
16, 27, 29, 150, 160, 180, 181, 200, 270
Median, M = observation or 5th observation = 160
The mean of the squares of the deviations from mean is called the variance and it is
denoted by s2.
Variance of Data:
o For ungrouped data: (In direct method)
or (In shortcut method), where is the mean.
Standard deviation is the square root of variance and it is denoted bys. This means:
Example:
The mean and standard deviations of 50 observations were calculated as 30 and 4
respectively. Later, it was found that by mistake, 13 was taken instead of 18 for one
observation during the calculation. Find the correct mean and the correct standard
deviation.
Solution:It is given that, number of observations (n) = 50
Incorrect mean,
Incorrect standard deviation (s) = 4
We know that
Incorrect sum of observations = 1500
∴Correct sum of observations = 1500 – 13 + 18 = 1505
∴ Correct mean =
Now, standard deviation,
Now, correct = Incorrect
Correct standard deviation
Variance of Data:
For discrete frequency distribution: (In direct method)
or (In shortcut method), where is the mean
and
Standard deviation is the square root of variance and it is denoted by σ.
Variance of Data:
o For continuous frequency
distribution: (Indirect
method) or (In shortcut method), where
xi = class marks of the class intervals, = mean, , h = width of the class intervals,
, where A is the assumed mean.
Standard deviation is the square root of variance and it is denoted bys. This means:
Example:Find the variance and standard deviation for the following data.
10 – 30 – 50 – 60
Class 20 – 30 40 – 50
20 40
Frequency 5 4 3 1 7
Solution: Let assumed mean, A = 35
Here, h = 10, N = 20
We obtain the following table from the given data.
Frequency Mid-
Class yi2 fiyi fiyi2
(fi) points (xi)
10 – 20 5 15 –2 4 –10 20
20 – 30 4 25 –1 1 –4 4
30 – 40 3 35 0 0 0 0
40 – 50 1 45 1 1 1 1
50 – 60 7 55 2 4 14 28
Total N = 20
The measure of variability, which is independent of units, is called the coefficient of
variation. The coefficient of variation (C.V.) is defined as
Where, σ and are standard deviation and mean of the data respectively.
For comparing the variability or dispersion of two series, we first calculate the C.Vs of each
series. The series having higher C.V. is said to be more variable than the other and the
series having lower C.V. is said to be more consistent than the other.
For two series with equal mean values, the series with greater standard deviation (or
variance) is more variable or dispersed than the other. Also, the series with lower value of
standard deviation (or variance) is said to be more consistent or less scattered than the
other.
Example:Which series, I or II, is more consistent?
Series I Series II
Mean 3100 3100
Variance 121 169
Solution: Standard deviation of series I, σ1 =
Standard deviation of series II, σ2 =
Since the mean of both the series is the same, the series with lower standard deviation will
be more consistent.
Thus, series I will be more consistent.
