Describing Group Performances

Measures of Centrality
Measures of Variability
 MEASURES OF CENTRALITY
• Definition:
Central Location is the tendency of the observations to
converge at a point or at the center of a frequency
distribution.
 The Mean

 The Median

 The Mode
 MEASURES OF CENTRALITY
UNGROUPED DATA
 The Mean 𝑥→ x-bar
-the average score of the distribution.
𝑥= .
sum of x – values .

𝑥= 𝑛
Σ𝑥
number of items or cases
 Ex: 1.The total scores of 12 students in classroom activities
are as follows.
152,144,156,166,172,150,153,160,154,168,165, and 170.
Find the mean total score of the students.

𝑥 = 152+144+156+166+172+150+153+160+154+168+165+170
12
𝑥 = 159
 MEASURES OF CENTRALITY
UNGROUPED DATA
 The Median

X → x-curl
-is the midpoint of an array of numbers or observations

X= (n + 1)th item
2
Find the median score of sophomore students in a Chemistry quiz
10,12,14,16,23,24,25,33,34,35,41,45,50
1 2 3 4 5 6 7
X = 13 + 1
2
X= 7th item

X= 25
 MEASURES OF CENTRALITY
UNGROUPED DATA

 The Median X → x-curl
 (n + 1)th
X= item
2
The ages of the patients at the pediatric ward of Hospital Z are
10,2,5,6,5,8,9,10,4,12,4,12,9,5.
2,4,4,5,5,5,6,8,9,9,10,10,12,12
1 23 4 5 6 78
 7th item -6  6+ 8
X= 14 + 1 = 7.5 X= 2
2 8th item -8

X= 7
 MEASURES OF CENTRALITY
UNGROUPED DATA
 The Mode X → x-caret
-the most frequent score that occurs in the distribution.
What is the mode of the students’ scores in a Statistics test.
The scores are as follows:
12,13,12,11,10,20,24,25,10,22,20,13,16,18,20,20,20,20.
Score Frequency Score Frequency
10 2 18 1
11 1 20 6 
X= 20 uni- modal
12 2 22 1
13 2 24 1
16 1 25 1
MEASURES OF CENTRALITY
GROUPED DATA

• The Mean 𝑥 → x-bar

Σ𝑓𝑥
𝑥= 𝑛

where:
f = frequency
x = class mark
n = no. of cases
 TABLE 1

CLASS FREQ CM
INTERVALS f x fx Σ𝑓𝑥
93
𝑥=
91 - 95 14 1302 𝑛
86 - 90 12 88 1056
81 - 85 18 83
𝑥 = 9445
1494 120
76 - 80 35 78 2730
71 - 75 23 𝑥 = 78.71
73 1679
66 - 70 10 68 680
61 - 65 8 63 504
n = 120 fx=9445
MEASURES OF CENTRALITY
GROUPED DATA

X → x-curl
• The Median

X= LBMd +
n/
2 – <cf
i
fMd
where:
LBMd = Lower Boundary of the median class
<cf = cumulative frequency before the median class
n = no. of cases
fMd = frequency of the median class
i = class size/class width
 TABLE 1

C.I. FREQ CM <cf

LL - UL f x
n/ – <cf
 2
i
91 - 95 14 93 120 X = LBMd +
fMd
86 - 90 12 88 106
120
81 - 85 18 83 94 n/2 = 2 =60th score
76 - 80 35 fMd 78 76 LBMd =75.5
71 - 75 23 73 41 <cf
<cf = 41
fMd =35
66 - 70 10 68 18
i=5
61 - 65 8 63 8
i=5 n=120
X = 78.21
MEASURES OF CENTRALITY
GROUPED DATA

• The Mode X → x-caret
 A
X= LBMo + i
A + B
where:
LBMo = Lower Boundary of the modal class
A= difference between the frequency of the modal class and the
frequency after it
B= difference between the frequency of the modal class and the
frequency before it
i = class size/class width
 TABLE 1  A
X= LBMo + i
C.I. FREQ CM <cf A+ B
LL - UL f x
LBMo =75.5
91 - 95 14 93 120 A= 35 – 18
86 - 90 12 88 106 A= 17
81 - 85 18 fA 83 94 B= 35 – 23
76 - 80 35 fMo 78
B= 12
76
i=5
71 - 75 23 fB 73 41  17
X= 75.5 + 5
66 - 70 10 68 18 17 + 12
61 - 65 8 63 8 
X = 78.43
i=5 n = 120
 TABLE 1
CLASS FREQ CLASS <cf CLASS fx

INTERVALS MARK BOUNDARIES

62 - 68 10 65 10 61.5 - 68.5 650

69 - 75 5 72 15 68.5 - 75.5 360
76 - 82 9 79 24 75.5 - 82.5 711
83 - 89 11 86 35 82.5 - 89.5 946
90 - 96 14 93 49 89.5 - 96.5 1302
97 - 103 11 100 60 96.5 - 103.5 1100
104 - 110 5 107 65 103.5 - 110.5 535
111 - 117 5 114 70 110.5 - 117.5 570
i=7 n=70 fx = 6174
 TABLE 1

CLASS FREQ CLASS <cf C.B. fx

INTERVALS MARK LB UB
n/2 =
62 - 68 10 65 10 61.5 - 68.5 650 35th
69 - 75 5 72 15 68.5 - 75.5 360 score
76 - 82 9 79 24 75.5 - 82.5 711
<cf
83 - 89 11 fMd 86 35 82.5 LB - 89.5 946
Md

90 - 96 14 93 49 89.5 - 96.5 1302

97 - 103 11 100 60 96.5 - 103.5 1100
104 - 110 5 107 65 103.5 - 110.5 535
111 - 117 5 114 70 110.5 - 117.5 570
 TABLE 1

CLASS FREQ CLASS <cf C.B. fx

INTERVALS MARK LB UB

62 - 68 10 65 10 61.5 - 68.5 650

69 - 75 5 72 15 68.5 - 75.5 360
76 - 82 9 79 24 75.5 - 82.5 711
83 - 89 11 fb 86 35 82.5 - 89.5 946
90 - 96 14 93 49 89.5 - 96.5 1302
LBMo
97 - 103 11 fa 100 60 96.5 - 103.5 1100
104 - 110 5 107 65 103.5 - 110.5 535
111 - 117 5 114 70 110.5 - 117.5 570
i=7 n=70
6174
MEASURES OF VARIABILITY
• It describes how the data are scattered or how much
they are bunched.
• Range (R)
• Mean Absolute Deviation (MAD)
• Inter-Quartile Range or Quartile Deviation (IQR or QD)
• Variance (sd2)
• Standard Deviation (sd)
RANGE

 Ungrouped Data
 Range
 R=Highest Observed Value – Lowest Observed Value
INTERPRETATION OF RANGE

The larger the value of the range the more dispersed the
distribution is. Therefore the distribution is heterogenous.
Otherwise, homogenous.
 MEAN ABSOLUTE DEVIATION
• Measures the average deviation of the values from the
arithmetic mean. It gives equal weight to the deviation of
every score in the distribution.

where
fx – x  MAD =mean absolute deviation
MAD = f = frequency
n
x = class mark
x = mean score
n = number of cases
 Example:
• Compute the range and the MAD of the ages of the ff.
teachers.
34,35,45,56,32,25, and 40.
Range = HS - LS
Range = 56 - 25
Range = 31
Mean Age (x) = 34+ 35+45+56+32+25+40
7
Mean Age (x) = 38.14
Mean Age (x) = 38.14
x x-x x – x 
34 –4.14 4.14
35 –3.14 3.14 MAD = 53.14
7
45 6.86 6.86
56 17.86 17.86 MAD = 7.59
32 –6.14 6.14
25 –13.14 13.14
40 1.86 1.86
Total 53.14
QUARTILE DEVIATION
where QD= Quartile Deviation
Q3 – Q1
QD = 2
Q3 = 3rd Quartile
Q1 = 1st Quartile
 Compute the QD of the ff:
34,35,45,56,32,25, and 40. QD = 40 – 32
2
 25,32,34,35,40,45,56 QD = 4

Q3 = 3N Q3 = 3(7) Q3 = 5.25 th item

4 4
Q3 = 40
Q1 = 1.75 th item
Q1 = N Q1 = 7
4 4 Q1 = 32
INTERPRETATION OF IQR/QD

The larger the value of IQR or QD, the more dispersed the
scores at the middle 50% of the distribution.
VARIANCE & STANDARD DEVIATION
• The deviation of each observation from the mean.

s2 = (x – x) 2
s= (x – x) 2
n–1  n–1

where s2 =sample variance

s =standard deviation
x = raw score
x = mean score
n = number of cases
Mean Age (x) = 38.14 (x – x) 2
s2 =
n–1
x x – x  (x – x)2
34 4.14 17.14
35 3.14 9.86 s2 = 606.86
7–1
45 6.86 47.06 s2 = 101.14
56 17.86 318.98
32 6.14 37.70 s = 101.14
25 13.14 172.66 s = 10.06
40 1.86 3.46
Total 53.14 606.86
INTERPRETATION OF SD

The larger the value of the standard deviation the more

dispersed the distribution is. Therefore, the distribution is
heterogenous. Otherwise, homogenous.
MEASURES OF VARIABILITY
• It describes how the data are scattered or how much
they are bunched.
 Grouped Data
 Range
 R=Highest Upper Boundary – Lowest Lower Boundary
 Range=HUB – LLB
VARIANCE & STANDARD DEVIATION
Grouped Data

• The deviation of each observation from the mean.

s2 = f(x – 𝑥) 2
s= f(x – 𝑥) 2

n–1  n–1
where s2=sample variance
s =standard deviation
x = class mark
x = mean score
f = frequency
n = number of cases
Example:
 Compute the Range, MAD,QD, Variance, and Standard
Deviation of the given data.
Table 1
IQ Scores of Education Students
IQ Scores f
 Range=HUB – LLB
75-79 10
80-84 12  Range=104.5 – 74.5
85-89 25
 Range=30
90-94 34
95-99 19
100-104 15
i=5 n=115
 Example:
 Compute the Range, MAD,QD, Variance, and Standard
Deviation of the given data.
Table 1
IQ Scores of Education Students
IQ Scores f x fx x – x  fx – x  fx – x 
75-79 10
MAD =
77 770 13.7 137 n
80-84 12 82 984 8.7 104.4 MAD = 667.3
85-89 25 87 2175 3.7 92.5 115
90-94 34 MAD =5.80
92 3128 1.3 44.2
95-99 19 97 1843 6.3 119.7 X= fx
n
100-104 15 102 1530 11.3 169.5
X= 10430 X= 90.7
i=5 n=115 fx= 10430 667.3 115
QUARTILE DEVIATION QD =
Q 3 – Q1
Table 1 2
IQ Scores of Education Students
IQ Scores f x <cf
3n/ –<cf
Q3= LB + 4 i
75-79 10 77 10 Q3 fQ3
80-84 12 82 22 86.25 –81
Q3= 94.5 + 5
85-89 25 87 47 Q1 19
90-94 34 92 81 Q3=95.88
n/
– <cf i
95-99 19 97 100 Q3 + 4
Q1= LBQ1 fQ1
100-104 15 102 115
28.75 – 22 5
i=5 n=115 Q1= 84.5 + 25
3n 3(115) Q3=86.25th score Q =85.85 95.88 – 85.85
Q3 = 4 4 1
QD =
n (115) Q1=28.75thscore 2
Q1 = 4 4 QD =5.015
 s2 f(x – x) 2
VARIANCE & SD =
n-1
`
IQ Scores f x x – x  fx – x  (x – x)2 f(x – x)2
75-79 10 77 13.7 137 187.69 1876.90
80-84 12 82 8.7 104.4 75.69 908.28
85-89 25 87 3.7 92.5 13.69 342.25
90-94 34 92 1.3 44.2 1.69 57.46
95-99 19 97 6.3 119.7 39.69 754.11
100-104 15 102 11.3 169.5 127.69 1915.35
i=5 n=115 667.3 5854.35
2
s = f(x – x) 2
s2 = 5854.35
n-1 114 s = 51.35
s2 = 51.35 s =7.166
COEFFICIENT OF VARIATION
• Shows variation relative to the mean. It is used to
compare two or more groups of distribution of scores.
• The smaller the value of the CV the more homogenous
the scores in that particular group.
𝑠
𝐶𝑉 = 𝑥100
𝑥
where:
s = standard deviation
𝑥=mean
MEASURES OF SHAPE
 Convey all the information ordinarily needed to
understand and interpret the distribution. They furnish
additional information to supplement that obtained
from the measures of central tendency and variability.

• Skewness
 The degree of its departure from symmetry.

 SK= 3(Mean – Median)

SD
 Skewness
 Normal Distribution
 Symmetrical

 Mean = Median = Mode

 Skewness
 Positively Skewed Distribution
 Skewed to the Right

Mo Md Mean
 Mean > Median
 Skewness
 Negatively Skewed Distribution
 Skewed to the Left

Mean Md Mo
 Mean < Median
 SKEWNESS
• SK= 3(mean – median)
sd
Mean = 88.6
Median = 89.2
Mode = 91.8
Standard Deviation = 14.3584
 SK= 3(88.6 – 89.2)  SK= -0.12536
14.3584 or 12.536%
negatively skewed distribution
A. Given the data showing the scores of two group of students
who took an entrance examination. Compute for the
measures of central tendency, variability, coefficient of
variation and skewness. Compare and interpret the results.
Which group is more heterogenous?

• Group A: 58,67,70,72,75,78,83,88,90,92
• Group B: 45,46,48,50,55,58,60,63,66,68
B. Compute for the mean, median, mode and standard
deviation.

Section A
Scores FREQ
170-179 3
160-169 12
150-159 20
140-149 28
130-139 15
120-129 2