Standard Deviation (Ungrouped Data)
Standard Deviation (Ungrouped Data)
John 40 38 49 43 40
Peter 41 41 44 42 42
Mile 42 42 42 42 42
Using the mean as our average, you will notice that three students have the same mean. Their scores
have an average of x=42. In other words, if we use mean, the scores of the three students have the same
center. However, it is obvious that the set of scores are NOT the same. At on glance, you will notice that a set
is more scattered than the others.
To be particular, notice that Mike’s set of scores is the most consistent. Moreover, he consistently
scored 42 in all five quizzes. Thus, we can say that Mike score has the least degree of variability among the
three sets of scores. In other words, his scores are the least scattered ones.
On the other hand, it is very easy to spot that between Peter and John. Peter’s scores are less
scattered than John’s. In other words, Peter’s scores have lesser degree of variability than John’s. Putting of
these together, we can say that John’s score are most scattered ones.
Therefore, while the three students have the same average, they have different degree of variability.
John has the greatest degree of variability: it is followed by Peter: and then followed by Mike.
NOTE: LESSER VARIABILITY means MORE CONSISTENT (and vice versa)
o Greater degree of variability means that the scores are more scattered.
o On the other hand, if a set of data has lesser degree of variability, the scores are less scattered. That
is, the score are more consistent.
Let us now formally determine the degree of variability of a set of data by computing the important stepping
stone:
DEFINITION: VARIANCE
The variance of a distribution denoted by s2, can be calculated using the formula:
s2=∑ ¿ ¿¿
Where:
x is the mean of the distribution
x represents the individual scores of the distribution
n number of data values in the distribution
Comments:
You will notice that there is a need to know the mean of the distribution. In computing for the variance,
the first thing to do is to compute the mean.
Do NOT be confused with the meaning of x in the formula. In the context of ungrouped data, x means
individual scores. On the other hand, in the context of grouped data, x means midpoints.
In organizing the data for the computation of the variance, the first column is labelled x . All individual
scores of the distribution are contained in this column.
EXAMPLE 1
Ten students took a special examination (with 30 items) in Mathematics. Their scores are the following.
22 24 12 30 29 21 17 30 10 25
Solution:
As noted earlier, the first thing to do is to compute first the mean of the distribution. I will let the students
to fill in the gap of the solution and verify that the mean is 22. Thus, x́=22.
The next thing to do is to construct a column labelled as x . All the individual scores are contained in this
column.
x
22
24 This is the column labelled as x
12
30
29
21
17
30
10
25
After that, let us construct another column. Let us label that as x−x . This column contains the
difference between individual scores and the mean.
With x́=22.
x x−x
22 0
24 2 For example, 24 – 22 = 2
12 -10
30 8 For example, 12 – 22 = -10
29 7
21 -1
17 -5
30 8 For example, 25 – 22 = 3
10 -12
25 3
After that, construct another column labelled as ( x−x )2. This column contains the squares of all the
entries of the column (x−x ).
x x−x (x−x )
2
22 0 0
24 2 4 For example, 22=4
12 -10 100
30 8 64
29 7 49
21 -1 1
17 -5 25 For example, (−5)2=25
30 8 64
10 -12 144
25 3 9
∑ (x−x )2 =460
It is the sum of all the entries of
the columns (x−x )2
To get the value of the numerator of the formula, which is ∑ ( x−x ) , all we need to do is add all the
2
entries of the column (x−x )2. As you can see, we have ∑ (x−x ) =460 . Since there are 10 data values, we
2
s =∑ ¿ ¿¿
2
460
s2= =51.11
10−1
So, the variance of the scores of the ten students is 51.11.
Now that we already covered the computation of variance, which I noted to be an important stepping
stone, we are now ready to tackle the standard deviation.
DEFINITION: STANDARD DEVIATION
The standard deviation of a distribution, denoted by s, is simply the square of the variance. That is,
s= √ s
2
Comments:
Procedurally, we need to know the variance first before computing the standard deviation.
The greater the standard deviation is, the greater the degree of variability of the scores in a distribution.
EXAMPLE 2 (follow up problem)
Ten students took a special examination (with 30 items) in Mathematics. Their scores are the following.
22 24 12 30 29 21 17 30 10 25
Solution:
From example 1, we already found out that the variance is 51.11. Hence, the standard deviation of the
scores is:
s= √ s
2
s= √ 51.11=7.15
Thus, the standard deviation of the scores is 7.15.
EXAMPLE 3
Fifteen students measured their heights (in cm) and recorded as follows:
137 132 145 131 162 177 173 180 144 123
147 151 130 130 129
Calculate the variance and standard deviation of the height of the students.
Solution:
Again, I will let the students to fill in the gap to the solution and verify that the mean of the distribution is
146.07. So x́=146.07 . Now, let us create a column labelled as x . Following that column is the column (x−x ).
With x́=146.07
x (x−x )
137 137 – 146.07 -9.07
132 132 – 146.07 -14.07
145 145 – 146.07 -1.07
131 131 – 146.07 -15.07
162 162 – 146.07 15.93
177 177 – 146.07 30.93
173 173 – 146.07 26.93
180 180 – 146.07 33.93
144 144 – 146.07 -2.07
123 123 – 146.07 -23.07
147 147 – 146.07 0.93
151 151 – 146.07 4.93
130 130 – 146.07 -16.07
130 130 – 146.07 -16.07
129 129 – 146.07 -17.07
Now, let us construct the column (x−x )2. This column contains all the squares of the entries of the
column (x−x ).
x (x−x ) (x−x )2
137 -9.07 (−9.07)2 82.26
132 -14.07 (−14.07) 2 197.96
145 -1.07 (−1.07)
2 1.14
131 -15.07 (−15.07)
2
227.10
162 15.93 (15.93) 2 253.76
177 30.93 (30.93)
2 956.66
173 26.93 (26.93)2 725.22
180 33.93 (33.93)
2
1151.24
144 -2.07 (−2.07)
2 4.28
123 -23.07 (−23.07) 2 532.22
147 0.93 (0.93)2 0.86
151 4.93 (4.93)2 24.30
130 -16.07 (−16.07) 2 258.24
130 -16.07 (−16.07) 2 258.24
129 -17.07 (−17.07)
2 291.38
Taking the sum of all the entries of the column (x−x )2.
(x−x )2
82.26
197.96
1.14
227.10
253.76
956.66
725.22
1151.24
4.28
532.22
0.86
24.30
258.24
258.24
291.38
∑ (x−x )2 =4964.86
Since there are 15 data values in the distribution, we have n=15. Hence, the variance is:
s =∑ ¿ ¿¿
2
2 4964.86
s= =354.63
15−1
So, the variance of the scores of the ten students is 354.63 .
s= √ s
2
s= √354.63=18.83
Thus, the standard deviation of the scores is 18.83.
Republic of the Philippines
SOUTHERN LUZON STATE UNIVERSITY
LABORATORY SCHOOL
Lucban, Quezon
DO IT YOURSELF
Compute for the standard deviation of the following set of data. Show your solution.
1. Scores of 20 students in a 50 – item quiz in science.
29 46 41 50 27 35 50 31 40 40
23 23 37 26 42 26 20 23 28 24
33 30 33 31 35 33 27 32
21 32 27 22 24 20 24