Measures of Variability

Measures of Dispersion/variability;
Dispersion/variability can be defined as the
degree of dispersion (spread) of data points in
a distribution.
There are main measures of dispersion which
are:
 Range
The range is the difference between the highest
.and lowest score in a distribution
.The formula is : R = L (x max) – S (x min)
Examples
1. Calculate the range of the following data:
a) 1,1,1,2,2,2,3,3,4,4,4,4,5,6
Solution
R = L (x max) – S (x min) = 6 – 1 = 5
b) 2, 4, 5, 2, 8, 7
Solution
R = L (x max) – S (x min) = 8 – 2 = 6
Coefficient of Range:
Coefficient of Range = L – S / L + S
Examples
Calculate the Coefficient of range for the previous
examples:
Solution
a)The Coefficient of range =6-1/6+1 = 5/7=0.7143
b)The Coefficient of range =8-2/8+2 = 6/10 = .6
 The Variance
The variance of a set of data is defined as the
.square of the standard deviation
Population variance is 2
Sample variance is S2
: Variance for Raw Data )1
Examples
[Link] the Population variance of the following
data.
1, 0, 6, 1
 (X   ) 2
Population variance 2 = N

Step3 Step 2 Step 1 X

d2 D d =X-
1 -1 1–2 1
4 -2 0–2 0
16 +4 6–2 6
1 -1 1–2 1
22 0 Total

Step 1: Find the mean (2)

Step 2 : Find the difference between
each value and the mean
Step 3: d2 = (1 + 4 + 16 + 1) = 22
Step 4: 22 / 4 = 5.5
2 = 5.5
Computing the variance using definitional
formula
Student Test Score X (
Eliot 3 3 – 5 = -2 4
Don 2 2 – 5= -3 9
Janice 5 5 – 5= 0 0
Amanda 9 9 – 5 = +4 16
Duane 1 1 – 5 = -4 16
Chris 8 8 – 5 = +3 9
Stephanie 8 8 – 5 = +3 9
Denise 4 4 – 5 = -1 1

x = 40
 = 64

(X  X) 2 64
S2 9.14 =
n 1 8 1
:Exercise
Calculate the population variance for these data
.2,4,5,8,11
 The shortcut method
Calculate the variance of the sample data below
by using the shortcut method. 5 7 1 2 4
 Solution

X
5 25
7 49
1 1
2 4
4 16
19= 95=

From we get ,

= 5.7
 Exercise
Calculate the population variance for these data 2,4,5,8,11.
( use the shortcut method.)
Solution
X
2 4
4 16
5 25
8 64
11 121
=30 =230

10 =
e for Grouped Data )2

Examples

Find the sample variance for the following data.

X 0 1 2 3
F 4 5 2 4
Solution X F fx
0 4 0 0 0
1 5 1 5 5
2 2 4 8 4
3 4 9 36 12
Ʃ 15 14 49 21

1.4 =
Exercise
Find the sample variance of the following accidents data .

Number of Frequency
accidents,( x) )F(
0 55
1 14
2 5
3 2
4 0
5 2
6 1
7 0
8 1
 Number of Frequency fx
accidents,( x) )F(
0 55 0 0 0
1 14 14 1 14
2 5 10 4 20
3 2 6 9 18
4 0 0 16 0
5 2 10 25 50
6 1 6 36 36
7 0 0 49 0
8 1 8 64 64
TOTAL 80 54 202

2.1 =
 Standard Deviation -2
The standard deviation is defined as the positive
square root of the variance. Thus, the
standard deviation is a measure of variability
expressed in the same units as the data. The
standard deviation is very much like a mean or
an "average" of these deviations
• To distinguish between the standard deviation
for the sample and the standard deviation for
the population, we will use the symbol S for a
sample standard deviation and the symbol δ
for the standard deviation of a population. For
calculating the standard deviation, we can use
the formula:
• Population standard deviation:
• Sample Standard deviation:
Computing s2 and s using definitional
formula
Student Test Score X (X- ) (X- )2
Eliot 3 3 – 5 = -2 4
Don 2 2 – 5= -3 9
Janice 5 5 – 5= 0 0
Amanda 9 9 – 5 = +4 16
Duane 1 1 – 5 = -4 16
Chris 8 8 – 5 = +3 9
Stephanie 8 8 – 5 = +3 9
Denise 4 4 – 5 = -1 1

x = 40
(X- µ )2 = 64
(X  X) 2
n 1

64
9.14 =
8 1

standard deviation  s=

9.14

= 3.02
Standard Deviation for Grouped Data
 Importance of Variance & Standard
Deviation in Inferential Statistics
.Variance & standard deviation estimate the spread of the scores-
If scores are closely packed to the mean, the variance & standard deviation-
.is small
If scores are very far away from the mean, the variance & standard deviation-
.is large
In general, variance & standard deviation can be conceived of as “error-
.”variance
-.The amount to which there is random fluctuations b/n scores
-.If there is a great deal of error, patterns in data are hard to detect
.If there is a small amount of error, patterns are easier to see-
Inferential stats are a way to determine how well a sample set of data allows-
.us to see patterns & infer that those patterns exist in some population
Thus, Variance & standard deviation will play big roles in inferential statistics
 Detecting Outliers Based on Z-Score
Detecting outliers data is a sample value that is much
larger or smaller than the rest. If the value of z-score is
far away from zero, the observation may be
characterized as an outlier . In general,
When we consider the empirical rule an observation with a

z-score < -2.00 or z-score > 2.00

might be characterized as a mild outlier.
Any observation with a
z-score < - 3.00 or z-score > 3.00
might be characterized as an extreme outlier.
Examples;
1) Consider this sample of n = 10measurements:
1, 1, 0, 15, 2, 3, 4, 0, 1, 3
The measurement x = 15 appears to be
unusually large . Calculate the z-score for this
observation and state your conclusion.
Solution;
z 
x  


Hence, the observation x = 15 lies 2.71 standard

deviation above the sample mean (3). Although
the z-score does not exceed 3, it is close enough
so that you might suspect that x = 15 is an
outlier.
Is there any outlier observation for the following
data.
46, 54, 42, 46, 32
Solution
Solution
Here,

= 44 and

X X- z
=8
32 -12 -1.5
42 -2 -0.25
46 2 0.25
46 2 0.25
54 10 1.25

We note here that all the values of z- score

are >- 3.00 and < 3.00.
Therefore, there is no outlier observation
 Finding Measures of Central Tendency by
using SPSS
Analyze Choose Descriptive Statistics
Frequencies Move the
variable name into “ variable” box and click
on “statistics” Click on “Mean” ,
“Median” , “Mode” from the central Tendency
. Click OK
Finding Measures of Variation Using SPSS

Analyze Choose Descriptive Statistics

Frequencies
Move the variable name into “
variable” Box and click on “statistics”
Click on “the Std. deviation” , “variance” ,
“Range”, Quartiles, Percentiles. Click
OK.