FREQUENCY DISTRIBUTION

(Calmorin, 2004)
Grouped Data:

105 93 118 90 117 94 107 105 99 107

98 111 105 106 104 110 120 98 109 103
96 103 107 102 100 112 102 106 110 101
113 107 115 116 107 11 108 104 97 108

Step 1: Find the absolute range

RS = HS - LS
R = 120 - 11
R = 109

Step 2: Find the class interval

109 ÷ 10 = 109
109 ÷ 20 = 5.45
Class interval = 9
Class limit = 13

Step 3: Set up the classes

HS + C/2
120 + 4.5 = 124.5
Upper Class Limit = 124.5
Lower Class Limit = 115.5
C/2 - LS
120 - 4.5 = 115.5
Real Limit = 115.5 - 124.5
Integral Limit = 116 - 124

Table 1.1 FREQUENCY DISTRIBUTION

Real Limit Integral Limit Tally Frequency
115.5-124.5 116-124 IIII 4
106.5-115.5 107-115 IIIII-IIIII-IIII 14
97.5-106.5 98-106 IIIII-IIIII-IIII-I 16
88.5-97.5 89-97 IIIII 5
79.5-88.5 80-88 0 0
70.5-79.5 71-79 0 0
61.5-70.5 62-70 0 0
52.5-61.5 53-61 0 0
43.5-52.5 44-52 0 0
34.5-43.5 35-43 0 0
25.5-34.5 26-34 0 0
16.5-25.5 17-25 0 0
7.5-16.5 8-16 I 1
Total Σf = 40
 Table 1.2 CUMULATIVE FREQUENCIES DISTRIBUTION
Class Limits Fre que ncy (f) Cumulative Fre que ncy C f
< >
116-124 4 40 4
107-115 14 36 18
98-106 16 22 34
89-97 5 6 39
80-88 0 1 39
71-79 0 1 39
62-70 0 1 39
53-61 0 1 39
44-52 0 1 39
35-43 0 1 39
26-34 0 1 39
17-25 0 1 39
8-16 1 1 40

Table 1.3 CUMULATIVE PERCENTAGE FREQUENCY DISTRIBUTION

Cumulative Frequency C f Cumulative Percentage Frequency
Class Limits f < > <(%) >(%)
116-124 4 40 4 100 10
107-115 14 36 18 90 45
98-106 16 22 34 55 85
89-97 5 6 39 15 97.5
80-88 0 1 39 2.5 97.5
71-79 0 1 39 2.5 97.5
62-70 0 1 39 2.5 97.5
53-61 0 1 39 2.5 97.5
44-52 0 1 39 2.5 97.5
35-43 0 1 39 2.5 97.5
26-34 0 1 39 2.5 97.5
17-25 0 1 39 2.5 97.5
8-16 1 1 40 2.5 100
Total 40

Table 1.4 FREQUENCY DISTRIBUTION AND MIDPOINTS

Cumulative Frequency
Class Limits Midpoints Frequency < >
116-124 120 4 40 4
107-115 111 14 36 18
98-106 102 16 22 34
89-97 93 5 6 39
80-88 84 0 1 39
71-79 75 0 1 39
62-70 66 0 1 39
53-61 57 0 1 39
44-52 48 0 1 39
35-43 39 0 11 39
26-34 30 0 1 39
17-25 21 0 1 39
8-16 12 1 1 40
40
 MEASURES OF CENTRAL TENDENCY
(Calmorin, 2004)
The arithmetic mean from grouped data
Grouped Data:

105 93 118 90 117 94 107 105 99 107

98 111 105 106 104 110 120 98 109 103
96 103 107 102 100 112 102 106 110 101
113 107 115 116 107 11 108 104 97 108

Weighted Arithmetic Method

ΣfM
Formula: x̄ = Σf
Where: x̄ = arithmetic mean
ΣfM = sum of the products of midpoints times frequency
N = total number of frequency

Step 1. Compute the midpoints of all the class limits which is given the symbol M.
Step 2. Multiply each midpoint by the corresponding frequency.
Step 3. Sum of the products of midpoints times frequencies.
Step 4. Divide this sum by the total number of cases (N) to obtain the mean.

Table 1.1
Class Limits Midpoints Frequency Frequency x Midpoint (f x M)
116-124 120 4 480
107-115 111 14 1,554
98-106 102 16 1,632
89-97 93 5 465
80-88 84 0 0
71-79 75 0 0
62-70 66 0 0
53-61 57 0 0
44-52 48 0 0
35-43 39 0 0
26-34 30 0 0
17-25 21 0 0
8-16 12 1 12
Total 40 4,143
 ΣfM
x̄ = Σf

12,040
= 70

x̄ = 172
Class Deviation Method:

The formula in computing class deviation method is as follows:

Σfd
x̄ = M˳+ C ( N )
Where: M˳= midpoint value of origin
Σfd = sum of the product of the frequency times the deviation
N = total number of cases
C = class interval

Using the frequency distribution for grouped data, the steps are as follows:
Step 1. Choose a temporary arbitrary origin from any of the class limits either at the center,
bottom or at the top.
Step 2. Assign to the class limits coded values, starting with zero at the origin with positive
values above the zero deviation and negative values below.
Step 3. Multiply the d by the corresponding class frequency f to get the fd.
Step 4. Sum the fd product algebraically. The symbol is ∑fd.
Step 5. Compute the mean by using the foregoing formula. The table represents the
computation of the mean by class deviation method to the same frequency distribution in the
table.

Class Limits Midpoints Frequency Deviation Frequency x Deviation (f x d)

116-124 120 4 6 24
107-115 111 14 5 70
98-106 102 16 4 64
89-97 93 5 3 15
80-88 84 0 2 0
71-79 75 0 1 0
62-70 66 0 0 0
53-61 57 0 -1 0
44-52 48 0 -2 0
35-43 39 0 -3 0
26-34 30 0 -4 0
17-25 21 0 -5 0
8-16 12 1 -6 -6
Total N = 40 Σfd = 167
 Σfd
x̄ = M˳+ C ( N )
167
= 162 + 7 ( N )
1503
= 162 + ( 4 0 )
= 66 + 37.575
x̄ = 103.58

COMPUTATION OF THE MEDIAN FROM BELOW: GROUPED DATA

(Calmorin, 2004)
Step 1. Estimate the cumulative frequencies as presented in the table.
Step 2. Find N/2, or one-half of the number of cases in the distribution.
Step 3. Determine the class limit in which the 20 th case falls. The 20th case falls within the
class limit.
Step 4. Compute the median from below by using the formula;

Where:
x͂ = the median
L = the lower real limit of the median class
N = the total number of cases
∑Cf< = the sum of the cumulative frequencies “lesser than” up to but below Median class
fc = the frequency of the median class
C = the class interval
N
( ¿
x͂ = L + C 2 −Σcf < fc ¿ )
20−6
= 97.5 + 9 ( ) 16
14
( )
= 97.5 + 9 16
= 97.5 + 9 (0.875)
= 97.5 + (7.875)
x͂ = 105.38

Integral Limit Frequency Cumulative Frequency

< >
116-124 4 40 4
107-115 14 36 18
98-106 16 22 34
 89-97 5 6 39
80-88 0 1 39
71-79 0 1 39
62-70 0 1 39
53-61 0 1 39
44-52 0 1 39
35-43 0 1 39
26-34 0 1 39
17-25 0 1 39
8-16 1 1 40
Total 40 (N)

COMPUTATION OF THE MEDIAN FROM ABOVE

Step 1. Estimate the cumulative frequencies as presented in the table.
Step 2. Find N/2, or one-half of the number of cases in the distribution.
Step 3. Determine the class limit in which the 20 th case falls. The 20th case falls within the
class limit.
Step 4. Compute the median from above by using the formula;

N
x͂ =U-C ( 2 −Σcf > fc¿ ¿)
Where:
x͂ = the median
U = the upper real limit of the median class
N = the total number of cases
∑Cf> = the sum of the cumulative frequencies “greater than” up to but below the Median
class
fc = the frequency of the median class
C = the class interval

Integral Limit Frequency Cumulative Frequency

< >
116-124 4 40 4
107-115 14 36 18
98-106 16 22 34
89-97 5 6 39
80-88 0 1 39
71-79 0 1 39
62-70 0 1 39
53-61 0 1 39
44-52 0 1 39
 35-43 0 1 39
26-34 0 1 39
17-25 0 1 39
8-16 1 1 40
Total 40 (N)
N
x͂ =U-C ( 2 −Σcf < fc¿ ¿)
20−18
= 106.5 - 9 ( 16 )
2
= 106.5 - 9 ( 16 )
= 106.5 - 9 (0.125)
= 106.5 - 1.125
x͂ = 105.38
 UNGROUPED DATA

(Calmorin, 2004)

34, 30, 26, 19, 22, 21, 35, 38, 50 44, 95, 52, 63, 52, 63, 52, 72, 81, 61, 72, 72, 93, 33
HS-95
LS-19

95
93
81
72
72
72
63
61
52
52
50 - median
44
38
35
34
33
30
27
26
22
19
Σx = 1,071

Where:
x = arithmetic mean
Σx = sum of all the scores
N = number of scores/cases

Mean:
Σx
x=
N

1,071
=
21

x = 51

Median:
x͂ = 50
 2ND QUARTILE (GROUPED DATA)

(Calmorin, 2004)

Integral Limit Frequency Cumulative Frequency

(cf<)
116-124 4 40
107-115 14 36
98-106 16 22
89-97 5 6
80-88 0 1
71-79 0 1
62-70 0 1
53-61 0 1
44-52 0 1
35-43 0 1
26-34 0 1
17-25 0 1
8-16 1 1

Step 1: Estimate the cumulative frequency

Step 2: Find 2N/4 of the number of cases in the distribution
Step 3: Determine the class limit in which the 2N/4 case falls
Step 4: Compute Q2 by using this formula:

(
Q2 = L + C 2 N / 4−∑ Cf < ❑ ¿
¿
)
COMPUTATION:

Q2 = L + C ( 2 N /4−∑ Cf < fc¿ ¿ )

2(40)/4−6
= 97.5 + 9 ( 16 )
20−6
= 97.5 + 9 ( 16 )

= 97.5 + 9 (0.875)
= 97.5 + 7.875

Q2 = 105.38

Where:
Q2 = second quartile
N = number of cases
L = lower real limit of the second quartile class
C = class interval
∑ Cf <¿ = sum of the cumulative frequencies “lesser than” up to but below the second quartile
class.
fc = frequency of the second quartile class

5th DECILE (GROUPED DATA)

(Calmorin, 2004)
Integral Limit Frequency Cumulative Frequency
(cf<)
116-124 4 40
107-115 14 36
98-106 16 22
89-97 5 6
80-88 0 1
71-79 0 1
62-70 0 1
53-61 0 1
44-52 0 1
35-43 0 1
26-34 0 1
17-25 0 1
8-16 1 1

Step 1: Estimate the cumulative frequency “lesser than”

Step 2: Find 5N/10 of the number of cases (N) in the distribution
Step 3: Find the closer limit in which 5N/10 case falls
Step 4: Compute D5 by using formula:
5 N /10−∑ Cf < ¿ ¿
D5 = L + C ( fc )
COMPUTATION:
5 N /10−∑ Cf < ¿ ¿
D5 = L + C ( fc )
5(40)/10−6
= 97.5 + 9 ( 16 )
20−6
= 97.5 + 9 (16 )
= 97.5 + 9 (0.875)
= 97.5 + 7.875

D5 = 105.38

Where:
D5 = fifth decile
N = number of cases
L = lower real limit of the second quartile class
C = class interval
∑ Cf <¿ = sum of the cumulative frequencies “lesser than” up to but below the second quartile
class.
fc = frequency of the second quartile class

50th PERCENTILE (GROUPED DATA)

(Calmorin, 2004)

Integral Limit Frequency Cumulative Frequency

(cf<)
116-124 4 40
107-115 14 36
98-106 16 22
89-97 5 6
80-88 0 1
71-79 0 1
62-70 0 1
53-61 0 1
44-52 0 1
35-43 0 1
26-34 0 1
17-25 0 1
8-16 1 1

Step 1: Estimate the cumulative frequency “lesser than”

Step 2: Look for 50N/100 value under the cumulative frequency “lesser than” (cf<)
Step 3: Find the class limit where 50N/100 case falls
Step 4: Compute P50 by using the formula:

(
P50 = L + C 5 0 N /10 0−∑
fc
Cf < ¿ ¿
❑ )
COMPUTATION:
5 N /10−∑ Cf < ¿ ¿
P50 = L + C ( fc )
5(40)/10−6
= 97.5 + 9 ( 16 )
20−6
= 97.5 + 9 ( 16 )
= 97.5 + 9 (0.875)
= 97.5 + 7.875

P50 = 105.38

Where:
P50 = fiftieth percentile
N = number of cases
L = lower real limit of the second quartile class
C = class interval
∑Cf< = sum of the cumulative frequencies “lesser than” up to but below the second quartile
class.
fc = frequency of the second quartile class
 2ND QUARTILE (UNGROUPED DATA)
x Below Above
95 21 1
93 20 2
81 19 3
72 18 4
72 17 5
72 16 6
63 15 7
61 14 8
52 13 9
52 12 10
50 11 11
44 10 12
38 9 13
35 8 14
34 7 15
33 6 16
30 5 17
27 4 18
26 3 19
22 2 20
19 1 21

(Calmorin, 2004)

Step 1: Arrange the scores from highest to lowest

Step 2: Mark 1 from the lowest score; 2 second lowest score
Step 3: Mark 1 from the highest; 2 from the second highest score; 3 from the third highest
score and so on.
Step 4: Find 2N/4 from below and get the score falls within the value
Step 5: Find a 2N/4 from above and the score falls within the value
Step 6: If the number of cases is even, add the scores pf steps 4 and 5 divided by 2 equals the
second quartile value. If the number of cases is odd, get the score falls within 2N/4 below and
above the distribution

COMPUTATION:

Q2 = 2N/4
= 2 (21)/4
= 42/4
= 10.5 or 11
Q2 = 50 (below)

Q2 = 2N/4
= 2 (21)/4
= 42/4
= 10.5 or 11
Q2 = 50 (above)
 50+50
Q2 =
2
Q2 = 50

5th DECILE (UNGROUPED DATA)

(Calmorin, 2004)
x Below Above
95 21 1
93 20 2
81 19 3
72 18 4
72 17 5
72 16 6
63 15 7
61 14 8
52 13 9
52 12 10
50 11 11
44 10 12
38 9 13
35 8 14
34 7 15
33 6 16
30 5 17
27 4 18
26 3 19
22 2 20
19 1 21

Step 1: Arrange the scores from highest to lowest

Step 2: Mark 1 from the lowest score; 2 second lowest score
Step 3: Mark 1 from the highest; 2 from the second highest score; 3 from the third highest
score and so on.
Step 4: Find 5N/10 from below and get the score falls within the value
Step 5: Find a 5N/10 from above and the score falls within the value.
Step 6: If the number of cases (N) is even, add the scores below and above divided by 2
equals the fifth decile value. If the number of cases is odd, get the middlemost score between
and above the distribution.

COMPUTATION:

D5 = 5N/10
= 3 (21)/10
= 105/10
= 10.5 or 11
D5 = 50 (below)
D5 = 5N/10
= 5 (21)/10
= 105/10
= 10.5 or 11
D5 = 50 (above)

50+50
D5 =
2

D5 = 50

50th PERCENTILE (UNGROUPED DATA)

(Calmorin, 2004)
x Below Above
95 21 1
93 20 2
81 19 3
72 18 4
72 17 5
72 16 6
63 15 7
61 14 8
52 13 9
52 12 10
50 11 11
44 10 12
38 9 13
35 8 14
34 7 15
33 6 16
30 5 17
27 4 18
26 3 19
22 2 20
19 1 21

Step 1: Arrange the scores from highest to lowest

Step 2: Mark 1 from the lowest score; 2 second lowest score
Step 3: Mark 1 from the highest; 2 from the second highest score; 3 from the third highest
score and so on.
Step 4: Find 50N/100 from below and get the score falls within the value
Step 5: Find a 50N/100 from above and the score falls within the value.
Step 6: If the number of cases (N) is even, add the scores below and above divided by 2
equals the fifth decile value. If the number of cases is odd, get the middlemost score between
and above the distribution.
COMPUTATION:

P50 = 50N/100
= 50 (21)/100
= 1050/100
= 10.5 or 11
P50 = 50 (below)

P50 = 50N/100
= 50 (21)/100
= 1050/100
= 10.5 or 11
P50 = 50 (above)

50+50
P50 =
2

P50 = 50
QUARTILE DEVIATION (Grouped Data)
(Calmorin, 2004)
Step 1: Estimate the cumulative frequency “lesser than”
Step 2: Find the third and first quartile
Step 3: Compute the quartile deviation by using the formula

Q3−¿Q
QD = 1
¿
2

Where:
QD = quartile deviation
Q3= third quartile
Q1= first quartile

Class Limit Frequency Cumulative Frequency <

116-124 4 40
Q3107-115 14 36
98-106 16 Σcf< = 22
Q1 89-97 5 6
80-88 0 Σcf< = 1
71-79 0 1
62-70 0 1
53-61 0 1
44-52 0 1
35-43 0 1
26-34 0 1
17-25 0 1
8-16 1 1
Total N = 40

Q3 = L + C 3 N /4−∑
fc
(Cf < ¿ ¿
❑ )
= 106.5 + 9 ( )
3(40)/ 4−22
Q3 ❑
fc
3 0−22
= 106.5 + 9 ( 1 4 )
= 106.5 + 9 (0.571428571)
= 106.5 + 5.14

Q3 = 111.64
Q1 = L + C ( N / 4−∑
fc
Cf < ¿ ¿ )
❑
10−1
Q1 = 88.5 + 9 ( 5 )
= 88.5 + 9 (1.8)
= 88.5 + 16.2
Q1 = 104.7

Q3−¿Q
QD = 1
¿
2

111.64−¿ 104.7
¿ ¿
2
6.94
¿
2

QD = 3.47
 STANDARD DEVIATION FROM GROUPED DATA: MIDPOINT METHOD
Step 1: Multiply the frequency (f) times the midpoint (m) to get Fm and add all the Fm values
to get the sum of Fm or ΣFm.
Step 2: Multiply the Fm times m to get the Fm2 or ΣFm2
Step 3: Compute the standard deviation (SD) from grouped data

Class Limits Midpoints Frequency Fm Fm2

116-124 120 4 480 57, 600
107-115 111 14 1,554 172,494
98-106 102 16 1,632 166,464
89-97 93 5 465 43,245
80-88 84 0 0 0
71-79 75 0 0 0
62-70 66 0 0 0
53-61 57 0 0 0
44-52 48 0 0 0
35-43 39 0 0 0
26-34 30 0 0 0
17-25 21 0 0 0
8-16 12 1 12 144
Total N = 40 ΣFm = 4,143 ΣFm2=439,947

SD = √ NΣF m2−¿ ¿ ¿
=√ 40 (439,947)−¿ ¿ ¿

¿
√ 17,597,880−17,164,449
1600−40

¿
√ 433,431
1,560
¿ √ 277.8403846
SD = 16.67

STANDARD DEVIATION FROM GROUPED DATA: CLASS DEVIATION METHOD

Step 1: Choose a temporary arbitrary origin. You can choose from any of the class limits, either at the
center, bottom, or top.
Step 2: Assign coded values to the class limits, starting with zero at the origin and with positive
values above the zero deviation and negative values below if its class limits are arranged from
highest to the lowest.
Step 3: Multiply the d by the corresponding class frequencies to get fd
Step 4: Sum of fd products algebraically the symbol is ΣFd
Step 5: Take the product of fd and d to get fd 2
Step 6: Take the sum of the products, fd 2. This sum is Σ fd 2
Step 7: Compute the standard deviation

Class Limits Frequency d Fd Fd 2

116-124 4 6 24 144
107-115 14 5 70 350
98-106 16 4 64 256
89-97 5 3 15 45
80-88 0 2 0 0
71-79 0 1 0 0
62-70 0 0 0 0
53-61 0 -1 0 0
44-52 0 -2 0 0
35-43 0 -3 0 0
26-34 0 -4 0 0
17-25 0 -5 0 0
8-16 1 -6 -6 36
Total N = 40 ΣFd = 167 ΣFd 2=831

SD =
√ ΣF d 2
N −1
−¿ ¿