MMW-BASIC STATISTICS

Lesson 5: Measures of Position

DR. CELIA L. VERANO
What is measures of position?

• The median of a data divides the set of values into two

equal parts. The percentiles of a data divide it into hundredths
or 100 equal parts. A data has 99 percentiles, denoted by P1,
P2, … P99. Roughly speaking, the first percentile P1, is the
number that divides the bottom 1% of the data from the top
99%. Similarly, P3, the third percentile, is the number that
divides the bottom 3% of the data from the top 97%. Note
that the median is the P50 or 50th percentile.
 • Deciles are values which divide the data into ten equal parts. A data has
nine deciles, which denote by D2, D2, …D9. Basically, the first decile, D1 is
the number that divides the bottom 10% of the data from the top 90%. The
third decile, D3 is the number that divides the bottom 30% of the data from
top 70%.
• The most commonly used fractiles are quartiles, The quartiles of a
data divide the value into four equal parts. A set of data has three quartiles,
denoted by Q1, Q2 and Q3, where Q2 = P50 = D5. The First quartile, Q1, is the
number that divides the bottom 25% of the data from the top 75%.
 Measures of Position
Used to describe the position of a data value in relation to the rest of
the data.
1. Quartiles- Simply put, quartiles divide your data into quarters:
the lowest quarter(25%), two middle quarters(50% and 75%), and a
highest quarter (100%).
2. Percentiles- A percentile is a number where a certain
percentage of scores fall below that number. For example, a 90th
percentile marks the spot where 90% of values fall below that cut-off
point.
3. Deciles- are similar to quartiles. But where quartiles split the
data in four equal parts, deciles split the data into ten parts: The 10th,
20th, 30th, 40th, 50th, 60th, 70th, 80th, 90th and 100th percentiles.
 To illustrate ungroup data, consider the sets of contestants with ten members
each whose scores as follows:

Calculate the following:

Q1A = ¼(n+1) = ¼(11)=2.75, within 2nd and 3rd are 6 and

7 interpolate:
Step 1: 7–6=1
Step 2: 1 * 0.75 = 0.75
Step 3: 6 + 0.75 = 6.75, This means that 25% have
the scores of 6.75 or less in Set A.
 Q1B =¼(n+1) = ¼(11)=2.75, within 2nd and 3rd are 6 and 7 interpolate:
Step 1: 7–6=1
Step 2: 1 * 0.75 = 0.75
Step 3: 6 + 0.75 = 6.75, This means that 25% have the scores of 6.75 or
less in Set B.
Q3A = ¾ (n+1) = ¾ (11)=8.25, within 8th and 9th are 15 and 17 interpolate:
Step 1: 17 – 15 = 2
Step 2: 2 * 0.25 = 0.50
Step 3: 15 + 0.50 = 15.5,This means that 75% have the scores of 15.5 or
less in Set A. Q3B = 3/4 (n+1) = ¾ (11)=8.25, within 8th and 9th are 14 and 15
interpolate:
Step 1: 15 –14 = 1
Step 2: 1 * 0.25 = 0.25
Step 3: 14 + 0.25 = 14.25, This means that 75% have the scores of 14.25
 D4A = 4/10 (n+1) = 4/10(11)= 4.4, X4=9, X5=10; interpolate: 10-9=1; 1*.0.4=0.4;
D4=9.4

P65A = 65/100 (n+1) = 65/100(11)=7.15, X7= 13, X8=14;

interpolate: 14-13=1;1*0.15=0.15 ; P65 = 13.15
 To Illustrate grouped data, consider the table below:
Compute the P15, P80, Q1 and Q3. Show your solution.
A ge f cf
11- 20 5 5
21- 30 7 12
31- 40 12 24
41- 50 22 46
51- 60 8 54
61- 70 4 58
71- 80 2 60
To tal 60
To determine the class containing P15:
we compute
(n/100)(N)=(15/100)(60)=9
The interval containing P15 is 21-30. With Lp15 = 20.5 and fp15=7, therefore we have
P15 = Lp15 + (15/100(60)-CF<p15)/fp15 * (i)
P15= 20.5 + {(9-5)/7}*10
P15 = 26.21 or 26 years. This means that 15% or 9 persons among the vacationers have
age of 26 years or less.
To determine the class containing P80
we compute
(n/100)(N)=(80/100)(60)=48
The interval containing P48 is 51-60. With Lp80 = 50.5 and fp80=8, therefore we have
P80 = Lp80 + (80/100(60)-CF<p80)/fp80 * i
P80= 50.5 + {(48-46)/8}*10
P80 = 53 years. This means that 80% or 48 persons among the vacationers have age of 53
years or less.
To determine the class containing Q1
we compute
(n/4)(N)=(1/4)(60)=15
The interval containing Q1 is 31-40. With Lq1 = 30.5 and fq1=12, therefore we have
Q1= Lq1 + (1/4(60)-CF<q1)/fq1 * i
Q1= 30.5 + {(15-12)/12}*10
Q1 = 33 years. This means that 25% or 15 persons among the vacationers have age of 33 years or
less.
 To determine the class containing Q3
we compute
(n/4)(N)=(3/4)(60)=45
The interval containing Q1 is 41-50. With Lq3 = 40.5 and fq3=22, therefore we
have
Q3= Lq3 + (3/4(60)-CF<q3)/fq3 * c
Q3= 40.5 + {(45-24)/22}*10
Q3 = 50.05 or 50 years. This means that 75% or 45 persons among the vacationers
have age of 50 years or less.
Interquartile Range (IQR)
The IQR describes the middle 50% of values when ordered
from lowest to highest. To find the interquartile range (IQR), ​
first find the median (middle value) of the lower and upper
half of the data. These values are quartile 1 (Q1) and quartile
3 (Q3). The IQR is the difference between Q3 and Q1.
Example: If Q3 = 50 and Q1= 33
IQR = Q3 – Q1 = 50 – 33 = 17 years, this means that the
spread of the middle half is at 17 years of age.
ESSENTIAL QUESTIONS

• Is P50=Q2=D5=Median, why?

• The following are test scores of 15 students in a statistics class:

• 70 77 65 56 99 62 79 73 85 87 92 82 78 83 90

a. Find the 80th percentile, Give the brief interpretation of it.

b. Find Q1.
c. Find the percentile rank for the score 82. Give the brief interpretation of it.

• What is Fractiles in Statistics?