MEASURES OF CENTRAL TENDENCY

The measure of central tendency is the point about which the scores tend to cluster or
the value to be expected of a typical or middle data point. This measure of position is a single
figure which represents the general level of magnitudes or values of the items in a given set of
data. If the data are arranged according to magnitude, it tends to lie centrally within the set.

The most commonly used measures of central tendency are the mean, median, mode,
and quantiles.

A. MEAN. The mean or arithmetic mean is the arithmetic average of a set of observations.

∑X
1. Ungrouped Data: M = where ∑ = summation notation
N
X = scores
N = total number of scores

Example I : The daily income of a vendor in 7 days are P520, P450, P300, P600,
P430, P380, and P320. Find the average income of the man in one
week.

520+450+300+ 600+430+380+320
Solution: M=
7

M = P 428.57

Example 2 : The grades of a student on 12 examinations were 90, 78, 85, 88,
75, 92, 86, 85, 94, 84, 91, 83. Find the mean (or average).

90+78+85+ 88+75+92+86+ 85+94 +84+ 91+ 83

Solution: M=
12

M = 85.92

2. Grouped Data:
∑ fX
Method I. Long Method M=
N

where f = class frequency

X = class midpoint
N = sum of frequencies

Method II. Short Method M = AM + ( ∑Nfd ) i

where AM = assumed mean (this is the midpoint where
the highest frequency is)
 f = class frequency (this is the frequency of
each class)
d = class deviation from the AM (write 0 where
the AM is located then count
positive above the AM and
negative below AM)
N = sum of frequencies
i = interval or class size

EXAMPLE 1:

1 2 3 4 5 6

Class Limits Midpoint Frequency

/Intervals (X) (f) fX d fd
125 - 129 127 1 127 5 5
120 - 124 122 2 244 4 8
115 - 119 117 3 351 3 9
110 - 114 112 6 672 2 12
105 - 109 107 8 856 1 8
100 - 104 102 10 1020 0 0
95 - 99 97 6 582 -1 -6
90 - 94 92 4 368 -2 -8
85 - 89 87 4 348 -3 -12
80 - 84 82 2 164 -4 -8
75 - 79 77 3 231 -5 -15
70 - 74 72 1 72 -6 -6
N = 50 ∑X = 5035 ∑fd= -13

Solution:

Method I :
5035
M= = 100.70
50

Method II :

M = AM + ( ∑Nfd ) i
M = 102 + ( −13
50 )
5
M = 100.70
 EXAMPLE 2:

Class Limits Midpoint Frequency

/Intervals (X) (f) fX d fd
Above 100   14   4 56
95.1 - 100.0   19   3 57
90.1 - 95.0   21   2 42
85.1 - 90.0   27   1 27
80.1 - 85.0 82.55 63   0 0 ← Assumed Mean (AM)
75.1 - 80.0   58   -1 -58
70.1 - 75.0   51   -2 -102
65.1 - 70.0   45   -3 -135
60.1 - 65.0   39   -4 -156
55.1 - 60.0   38   -5 -190
50.1 - 55.0   21   -6 -126
50 and below   15   -7 -105
N = 411 ∑fd= - 690

Solution: Use Method 2 (Short Method) since Method I is not applicable

M = AM + ( ∑Nfd ) i Recall: To get the midpoint (this is the AM) =

(80.1+85) / 2 = 82.55

i =5

M = 82.55 + ( −690
411 )
5
M= 74.16
3. Mean of the Combination of Groups or Weighted Mean

N 1 M 1 + N 2 M 2 +…+ N n M n
M c=
N 1 + N 2 +…+ N n

where N = frequencies of the distributions

M = mean of the distribution

EXAMPLE I :

Consider the mean of exams of the 3 sections:

Section Mean N
I 86 32
II 84 45
III 88 40

Solution:
32 ( 86 )+ 45 ( 84 )+ 40(88)
Mc = = 85.91
32+ 45+40

EXAMPLE 2:

Find the General Weighted Average (GWA) of Paula’s grade last semester.

Subject Grade Units Weight

English 1.5 3 4.5

Math 2.0 3 6.0
Filipino 1.25 3 3.75
Science 2.0 3 6.0
History 1.75 3 5.25
Soc. Sci. 1.5 3__ 4.5____
Total Units: 18 Total Weight = 30

Solution:

Total weight 30
GWA = = = 1.67
Total Units 18
When to Use the Mean:

1. When we want to use a measure of central tendency with the greatest stability.

2. When we want a balance point in the given data.

3. When the scores are distributed symmetrically around a central point.

4. When other statistical methods like standard deviation and coefficient of correlation are to
be computed. These statistics are based upon the mean.

Advantages of the Mean:

1. The concept of the mean is familiar to most people and intuitively clear.

2. Every set of data has a mean. It can easily calculated and unique, since every data set has
one and only mean.

3. The mean is useful in computing other statistics such as comparing the means from several
data sets.

Disadvantages of the Mean:

1. The mean is affected by extreme scores or values that are not representative of the rest of
the data.

2. It is tedious to compute the mean since we include every data point in the calculation.

3. The mean cannot be computed for a data set that has open-ended classes at either the high
or low end of the distribution.
B. MEDIAN. The median is a single value from the data set that measures the central item in
the data. This single value is the middlemost or most central item in the set of
scores. Half of the scores lie above this point and the other half lie below it.

1. Ungrouped Data. To find the median of a data set, first arrange the data in either
ascending or descending order. If the data has odd numbered
items, the median is middle item of the array. However, if it has
even number of items, the median is the average of the two
middle items.

Median = the ( n+12 ) th items in a data array

Example 1: Given the ages of 7 girls: 15, 19, 14, 13, 18, 19, 16. Find the
median of their ages.

Solution:

Arrange the ages from lowest to highest.

Girls 1 2 3 4 5 6 7
Ages in data array 13 14 15 16 18 19 19

Median = the ( n+12 ) th items in a data array

7+1
= (
2 )
th
th = the 4 item
Median = 16 years old

Example 2: Patients treated in OPD of a hospital on 8 consecutive days

In data array 1 2 3 4 5 6 7 8
No. of patients 56 47 33 30 27 25 21 18

Median = the ( n+12 ) th items in a data array

8+1
= (
2 )
th = the 4.5th item

Median = 28.5 or 28 patients

 2. Grouped Data

Median = l + ¿ i where l = exact lower limit of the median

class (this is where the highest
frequency of the class is found)

N = total number of scores (or

frequency)

cf< = cumulative frequency of the

class immediately preceding
the median class

fm = frequency of the median class

i = class size or interval

Example 1:

Class Limits Midpoint Frequency

/Intervals Exact limits (X) (f) cf<
125 - 129 124.5 - 129.5 127 1 50
120 - 124 119.5 - 124.5 122 2 49
115 - 119 114.5 - 119. 5 117 3 47
110 - 114 109.5 - 114.5 112 6 44
105 - 109 104.5 - 109.5 107 8 38

100 - 104 99.5 - 104.5 102 10 30 ← Median Class

95 - 99 94.5 - 99.5 97 6 20
90 - 94 89.5 - 94.5 92 4 14
85 - 89 84.5 - 89.5 87 4 10
80 - 84 79.5 - 84.5 82 2 6
75 - 79 74.5 - 79.5 77 3 4
70 - 74 69.5 - 74..5 72 1 1
N = 50

Solution:
 l = 99.5 cf< = 20 fm = 10 i=5
Median = l + ¿ i = 99.5 + ( 25−20
10 )
5

Median = 102

Example 2:

Class Limits Midpoint Frequency

Exact Limits cf<
/Intervals (X) (f)
Above 100     14 411

95.1 - 100.0 97.55  19 397

90.1 - 95.0  92.55 21 378

85.1 - 90.0  87.55 27 357

80.1 - 85.0 80.05 -85.05 82.55 63 330 ← Median Class
75.1 - 80.0  77.55 58 267

70.1 - 75.0  72.55 51 209

65.1 - 70.0  67.55 45 158

60.1 - 65.0  62.55 39 113

55.1 - 60.0  57.55 38 74

50.1 - 55.0  52.55 21 36

50 and below     15 15

N = 411

Solution: Using this formula:

Median = l + ¿ i In the table, l = 80.05 , N = 411 ,

cf< = 267 , fm = 63 , i = 5

411
Median = 80.05 +

Median = 75.17
( 2
−267
63 )
(5)

Advantages of the Median:

1. Extreme values do not affect the median.

2. The median is easy to understand and can be calculated from any kind of data, even for
grouped data with open-ended classes, unless the median falls into an open-ended class.
3. Even qualitative data like sharpness, sound, or color have median.

Disadvantages of the Mean:

1. Some statistical techniques using median are more complicated than those using the mean.

2. We have to array (arrange) the data even those with large number of items before we can
compute the median. This is time-consuming for data set with large number of items.

C. MODE. The mode is the most often repeated value or the value with the highest frequency
in the data set.

1. Ungrouped Data. The mode is easily identified by merely locating or identifying the
score or item which occurs most frequently.

A distribution with only one mode is said to be unimodal; with two modes is
called bimodal; with three modes is said to be trimodal; and so on. A distribution
with two or more modes is labelled as multimodal.

Example 1: 10, 10, 19, 17, 10, 16, 18, 15, 11, 11

Mode is 10. This is unimodal.

Example 2: 2, 3, 4, 4, 5, 7, 3, 6, 8, 9

Modes: 3 and 4. This is bimodal.

Example 3: 25, 22, 29, 28, 24, 24, 21, 25, 29, 20

Modes: 24, 25, and 29. This is trimodal.

2. Grouped Data.

d1
Mo = LMO +
( )
d 1 +d 2
i where: LMO = lower limit of the modal class

(modal class is found where the

highest frequency occurs)
 d1 = frequency of the modal class
minus the frequency of the class
directly below it.

d2 = frequency of the modal class

minus the frequency of the class
directly above it.

i = class size or class interval

Example 1:

Class Limits Midpoint Frequency

/Intervals (X) (f)
125 - 129 127 1
120 - 124 122 2
115 - 119 117 3

110 - 114 112 6

105 - 109 107 8

100 - 104 102 10 ← Modal Class

5 - 99 97 6

90 - 94 92 4
85 - 89 87 4

80 - 84 82 2
75 - 79 77 3

70 - 74 72 1
N = 50

Solution: Using the formula

d1
Mo = LMO +
( )
d 1 +d 2
i where LMO = 100

d1 = 10 – 6 = 4
d2 = 10 – 8 = 2
i = 5
= 100 + ( 4 4+2 )(5)
 Mo = 103.33

Example 2:

Class Limits Midpoint Frequency

/Intervals (X) (f)
Above 100   14

95.1 - 100.0 97.55  19

90.1 - 95.0  92.55 21

85.1 - 90.0  87.55 27

← Median
80.1 - 85.0 82.55 63
Class
75.1 - 80.0  77.55 58

70.1 - 75.0  72.55 51

65.1 - 70.0  67.55 45

60.1 - 65.0  62.55 39

55.1 - 60.0  57.55 38

50.1 - 55.0  52.55 21

50 and below   15

N = 411

Solution: Using the formula

d1
Mo = LMO + ( d 1 +d 2)i where LMO = 80.1

d1 = 63 – 58 = 5
d2 = 63 – 27 = 36
i = 5
5
= 80.1 + ( 5+36 )(5)
Mo = 80.71

Advantages of the Mode:

1. Like the median, the mode can be used as a central location for qualitative as well as
quantitative data.

2. It is also used for modal styles.

3. It is not unduly affected by extreme values. We can choose the mode no matter how large,
small or spread out the data happen to be.

4. Mode is still identified when one or more of the classes are open-ended.

Disadvantages of the Mode:

1. The mode is not often used to measure central tendency unlike the mean and median.

2. Too often, there is no modal value if data set has no repeated values. Other times, every
value is the mode because every value occurs the same number of times. Therefore, the
mode is a useless measure of central tendency.

3. It is difficult to interpret and compare data sets with two, three, or many modes.

D. QUANTILES. Values which divide a set of data into equal parts are called quantiles. The
quantile which divide the distribution into four parts are called quartiles;
those which divide the distribution into ten parts are called deciles; and
those which divide the distribution into one hundred parts are called
percentiles.

The median is the same as the second quartile or 50th percentile or 5th
decile. The first quartile is equivalent to the 25th percentile. The third quartile
is the same as the 75th percentile.

1. Quartiles

a. First Quartile (Q1) : Q1 = lq + ¿

b. Third Quartile (Q3) : Q3 = lq + ¿

where Q1 = first quartile

Q3 = second quartile
N = total number of frequency
lq = lower limit of the quartile class
cf< = cumulative frequency of the immediately preceding
class
fq = frequency of the quartile class
Example 1:

Class Limits Midpoint Frequency

/Intervals Exact limits (X) (f) cf<
125 - 129 124.5 - 129.5 127 1 50
120 - 124 119.5 - 124.5 122 2 49
115 - 119 114.5 - 119. 5 117 3 47
110 - 114 109.5 - 114.5 112 6 44
105 - 109 104.5 - 109.5 107 8 38 ← Q3
100 - 104 99.5 - 104.5 102 10 30 cum. Freq. prec. Q3

95 - 99 94.5 - 99.5 97 6 20
90 - 94 89.5 - 94.5 92 4 14 ← Q1
85 - 89 84.5 - 89.5 87 4 10 ( cum. Freq. prec. Q1
80 - 84 79.5 - 84.5 82 2 6
75 - 79 74.5 - 79.5 77 3 4
70 - 74 69.5 - 74..5 72 1 1
N = 50

To compute for the quartiles:

a. Q1 is located where 25% of 50 = 12.5 (refer to cf< where 12. 5 is near. In the table it
is at 14)

Q1 = lq + ¿

50
Q1 = 89.5 + 4
4( )
−10
5 = 92.62

b. Q3 is located where 75% of 50 = 37.5 (refer to cf< where 37.5 is near. In the table it
is at 38)
 Q3 = lq + ¿
150
Q3 = 104.5 + 4
8(
−30
)
5 = 109.19

2. Percentiles (Pp)

Pp = lp + ¿

where Pp = percentage of the distribution, i.e. 10%, 20%, 45%, etc.

lp = exact lower limit of the percentile class

pN = part of N to be counted off in order to reach P

cf< = cumulative frequency of the immediately preceding class
fq = frequency of the percentile class
i = class interval size

Using Example 1:

Class Limits Midpoint Frequency

/Intervals Exact limits (X) (f) cf<

125 - 129 124.5 - 129.5 127 1 50

120 - 124 119.5 - 124.5 122 2 49

115 - 119 114.5 - 119. 5 117 3 47 ← P90

110 - 114 109.5 - 114.5 112 6 44 ← P80

105 - 109 104.5 - 109.5 107 8 38 ← P70

100 - 104 99.5 - 104.5 102 10 30 ← P60

95 - 99 94.5 - 99.5 97 6 20 ← P30 & P40

90 - 94 89.5 - 94.5 92 4 14
85 - 89 84.5 - 89.5 87 4 10 ← P20

80 - 84 79.5 - 84.5 82 2 6 ← P10

75 - 79 74.5 - 79.5 77 3 4 cum. Freq. prec. P10

70 - 74 69.5 - 74..5 72 1 1
N = 50
 pN = 10% of 50 = 5 P10 = 79.5 + [ (5 – 4) / 2 ] 5 = 82.00
pN = 20% of 50 = 10 P20 = 84.5 + [ (10 – 6) / 4 ] 5 = 89.50
pN = 30% of 50 = 15 P30 = 94.5 + [ (15 – 14) / 6 ] 5 = 95.33
pN = 40% of 50 = 20 P40 = 94.5 + [ (20 – 14) / 6 ] 5 = 99.5
pN = 60% of 50 = 30 P60 = 99.5 + [ (30 – 20) / 10 ] 5 = 104.5
pN = 70% of 50 = 35 P70 = 104.5 + [ (35 – 30) / 8 ] 5 = 107.62
pN = 80% of 50 = 40 P80 = 109.5 + [ (40 – 38) / 6 ] 5 = 111.17
pN = 90% of 50 = 45 P90 = 114.5 + [ (45 – 44) / 3 ] 5 = 116.17

3. Deciles (Dd)

Dd = ld + ¿

where Dd = decile number of the distribution, i.e., 1st decile, 2nd decile,
3rd decile, 4th decile, etc.

l = exact lower limit of the decile class

d

dN = part of N to be counted off to reach the decile class

cf< = cumulative frequency of the class immediately preceding
the decile class
fd = frequency of the decile class
i = class interval size

Using Example 1 again:

Class Limits Midpoint Frequency

/Intervals Exact limits (X) (f) cf<
125 - 129 124.5 - 129.5 127 1 50

120 - 124 119.5 - 124.5 122 2 49

115 - 119 114.5 - 119. 5 117 3 47 ← D9

110 - 114 109.5 - 114.5 112 6 44 ← D8

105 - 109 104.5 - 109.5 107 8 38 ← D7
100 - 104 99.5 - 104.5 102 10 30 ← D6

95 - 99 94.5 - 99.5 97 6 20 ← D3 & D4

90 - 94 89.5 - 94.5 92 4 14

85 - 89 84.5 - 89.5 87 4 10 ← D2
80 - 84 79.5 - 84.5 82 2 6 ← D1

75 - 79 74.5 - 79.5 77 3 4 cum. Freq. prec. D1

70 - 74 69.5 - 74..5 72 1 1
 N = 50

Solution:

First Decile: D1 = l1 + ¿ where dN /10= (1)(50) /10 = 5

= 79.5 + ( 5−4
2 )
5

D1 = 82

Second Decile: D2 = l2 +¿ where dN /10= (2)(50)/10 = 10

= 84.5 + ( 10−6
4 )
5

D2 = 89.5

Third Decile: D3 = l3 +¿ where dN /10= (3)(50)/10 = 15

= 94.5 + ( 15−14
6 )
5

D3 = 95.33

Fourth Decile: D4 = l 4 +¿ where dN /10= (4)(50)/10 = 20

20−14
= 94.5 +
6
5 ( )
D4 = 99.5

Fifth Decile (may not be computed) since this is equivalent to the Median or Q2 or P50

Sixth Decile: D6 = l 6 +¿ where dN /10= (6)(50)/10 = 30

= 99.5 + ( 30−20
10 )
5

D6 = 104.5

Seventh Decile: D7 = l 7 +¿ where dN /10= (7)(50)/10 = 35

= 104.5 + ( 35−30
8 )
5

D7 = 107.62

Eight Decile: D8 = l 8 +¿ where dN /10= (8)(50)/10 = 40

= 109.5 + ( 40−38
6 )
5

D8 = 111.17
Ninth Decile: D9 = l 9 +¿ where dN /10= (9)(50)/10 = 45

= 114.5 + ( 45−44
3 )
5

D9 = 116.17

END OF LESSON

ASSIGNMENT:
1. On the assumption that the variables are discrete, compute the mean, median & mode for
the following data:

a. 5, 6, 6, 6, 6, 7, 7
b. 3, 3, 4, 4, 4, 5, 6, 6
c. 1, 2, 2, 2, 3, 3, 3, 4, 4
d. 16, 22, 21, 17, 18, 20, 22, 22, 19

2. In 100 rolls of a die the frequencies of the six possible events are as follows:

X1 f1

1 19
2 15
3 15
 4 20
5 14
6 17

Compute the arithmetic mean for the distribution.

3. Given:

Class Intervals f

210 – 219 1
200 – 209 3
190 – 199 8
180 – 189 13
170 – 179 17
160 – 169 22
150 – 159 29
140 – 149 25
130 – 139 18
120 – 129 12
110 – 119 5

Compute the following:

1. Mean, Median & Mode

2. Q1 & Q3

3. P29 , P35 , P67 , P85

4. D2 , D4 , D7, D9

4. Given:

Class Intervals f

40000 – 44999 8
35000 – 39999 25
30000 – 34999 49
25000 – 29999 76
20000 – 24999 121
15000 – 19999 169
10000 – 14999 115
5000 - 9999 87
0 - 4999 55

Compute the following:

1. Mean, Median & Mode

2. Q2 & Q3

3. P15 , P40 , P74 , P95

4. D1 , D3 , D6, D8