Professional Documents
Culture Documents
Measures of Variability For Ungrouped Data
Measures of Variability For Ungrouped Data
UNGROUPED DATA
Measures of dispersion or variability refer to the
spread of the values about the mean.
These are important quantities used by statisticians in
evaluation. Smaller dispersion of scores arising from
the comparison often indicates more consistency and
more reliability.
The most commonly used measures of dispersion are
the range, the average deviation, the standard
deviation, and the variance.
MEASURES OF VARIABILITY (UNGROUPED DATA)
1. RANGE - the difference between the
largest value and the smallest value.
R= H-L
where R = Range,
H = Highest/Maximum value,
L = Lowest/Minimum value
Examples:
Test scores of 10, 8, 9, 7, 5, and 3
What is the range of the data?
•Data Set A: 10, 9, 7, 7, 8, 9, 6, 7, 8
Range = 10 – 6 = 4
•Data Set B: 35, 40, 55, 48, 25, 31, 52
Range = 55 – 25 = 30
2. Average Deviation. This measure tells us how far each
data is from the mean. The following example illustrates how
to compute the average deviation:
Example:
Data Set 1: 6, 8, 5, 5, 6
• First we need to calculate for the mean.
• So,
6+8+5+5+6 30
𝑥̅ = = = 6
5 5
• Next, we subtract the mean from every value in our data
set. Then take the absolute value of the results.
• 𝑥−𝑥 ̅= 6−6 = 0 → |0| = 0
• 𝑥−𝑥 ̅= 8−6 = 2 → |2| = 2
• 𝑥−𝑥 ̅= 5−6 = -1 → |-1| = 1
• 𝑥−𝑥 ̅== 45−6 = -1 → |-1| = 1
• 𝑥−𝑥 ̅= 6−6 = 0 → |0| = 0
=4
Solve for the average deviation by taking the
sum of the absolute values obtained, divided
by the total number of data
0+2+1+1+0 4
Average Deviation = = = 0.8
5 5
3. Variance
It measures how far a set of numbers is spread
out from the mean. To calculate the variance,
we use the formula:
Σ(𝑥−𝑥̅)2
• For population, 𝜎 2 =
𝑁
Σ(𝑥−𝑥̅)2
• For sample size, s =
2
𝑛 −1
Example:
• Solve for the variance of the given data set
below (assuming that the data set is the entire
population).
Data Set: 10, 15, 25, 10, 12, 18
• First, calculate the mean of the data set,
10+15+25+10+12+18 90
• 𝑥̅ = = = 15
6 6
• Next, solve for Σ(𝑥−𝑥̅)2 . To get the sum of squares,
subtract the mean from each values, square it and add
them all.
(𝑥−𝑥̅)2 = (10−15)2 = (-5)2 = 25
(𝑥−𝑥̅)2 = (15−15)2 = (0)2 = 0 Σ(𝑥−𝑥̅)2 = 168
(𝑥−𝑥̅)2 = (25−15)2 = (10)2 = 100
(𝑥−𝑥̅)2 = (10−15)2 = (-5)2 = 25
(𝑥−𝑥̅)2 = (12−15)2 = (-3)2 = 9
(𝑥−𝑥̅)2 = (18−15)2 = (3)2 = 9
σ(𝑥−𝑥̅)2 = 168
• Lastly, solve for the population variance by
using the formula,
Σ(𝑥−𝑥̅)2 168
2
𝜎 = = = 28
𝑁 6
• Conversely, if the data set is just a sample of an entire
population, then we will use the formula for the sample
variance,
Σ(𝑥−𝑥̅)2 168 168
2
s = = = = 33.6
𝑛 −1 6−1 6−1
3. Standard Deviation - is the square root of
the variance. It measures the spread around
the mean making it the most reliable
measure of variability. In symbols,
•For population, 𝜎 = 𝜎 2
•For sample size, 𝑠 = 𝜎 2
• To get the standard deviation we’ll just take the square root
of the variance.
Population Variance
Σ(𝑥−𝑥̅)2 168
2
𝜎 = = = 28 = 28 = 5.29
𝑁 6
Sample Variance
Σ(𝑥−𝑥̅)2 168 168
2
s = = = = 33.6 = 33.6 = 5.8
𝑛 −1 6−1 6−1