You are on page 1of 20

25 Jul 2022

Numerical Measures

Measures of Central Tendency


- Describes the “center” of data

 Mean
 median
 mode

Mean (Arithmetic mean)


 the average of a given set of data
 obtained by dividing the sum of all the
observations by the number of
observations totaled.the average value of
all the data.

Mean = sum of all observations divided


by the number of observations

1
25 Jul 2022

Mean
 Given the sample data X1, X2, …,Xn,
the sample mean is given by

Example: Mean
On 5 tests, a student has made grades of
82, 93, 86, 92, and 79. Find the mean for
his test grades.

2
25 Jul 2022

Median
 divides the distribution into equal parts
 The median of a set of observations
arranged in an increasing or decreasing
order of magnitude is the middle value
when the number of observations is odd
or the arithmetic mean of the two middle
values when the number of observations
is even.

Formula for the position of the


median
If number of observation is odd,
Position of median = [(n+1)/2]th
observation

If number of observation is even,


Position of middle values are (n/2)th
observation and [(n/2)+1]th observation.

3
25 Jul 2022

Example: Median
On 5 tests, a student has made grades of
82, 93, 86, 92, and 79. Find the median
for his test grades.

Ascending Order: 79, 82, 86, 92, 93

Median = 3rd observation = 86

10

Example: Median
The nicotine contents for a random sample of
6 cigarettes of a certain brand are found to
be 2.3, 2.7, 2.5, 2.9, 3.1, and 1.9 milligrams.
Find the median.

Ascending Order: 1.9, 2.3, 2.5, 2.7, 2.9, 3.1


Median = average of 3rd and 4th observations
= (2.5 + 2.7) / 2 = 2.6

11

12

4
25 Jul 2022

13

Mode
 value which occurs most often or with the
greatest frequency.

Remark.
 May not always exist ( This is certainly
true if ALL observations occur with the
same frequency)
 may be more than one

14

Example: Mode
Consider the following data sets:
a. 8, 4, 9, 2, 3, 2, and 1 Mode: 2
b. 10, 20, 30, 30, 40, 70, 60, 60, 90, and
100 Mode: 30 and 60
c. 3, 3, 9, 9, 4, 5, 6, 5, 6, and 4
Mode: does not exist

15

5
25 Jul 2022

Comparing Mean, Median and Mode

Consider the following data set:


1, 2, 3, 3, 3, 3, 4, 5
Mean = 3
Median = 3
Mode = 3

16

Comparing Mean, Median and Mode

Consider the following data set:


1, 2, 3, 3, 4, 5, 8, 8, 22
Mean = 6.22
Median = 4
Mode = 8

17

Comparing Two sets of data


Consider the following sets of data:

1st set of data: 9, 10 and 11 Mean = 10

2nd set of data: 1, 10 and 19 Mean = 10

What is the difference between the two sets


of data?

18

6
25 Jul 2022

Measures of Variation
 describes how widely spread the
observations are
 range
 variance
 standard deviation
 coefficient of variation

19

Situation
Consider the following measurements, in liters, for
two samples of orange juice bottled by companies
A and B:

Sample A 0.97 1.00 0.94 1.03 1.11


Sample B 1.06 1.01 0.88 0.91 1.14

20

Range
Range = highest observation – lowest
observation

 not that useful since only the extremes


and not all the observations are used

21

7
25 Jul 2022

22

23

Variance and Standard Deviation


Widely used measure of variation
Variance - average squared deviations of
the observations from their mean

24

8
25 Jul 2022

25

Standard Deviation
-square root of the variance of the
observations

26

27

9
25 Jul 2022

28

Coefficient of Variation
 the ratio of the standard deviation to its
mean, expressed in percent
 a relative measure of dispersion useful
when comparing dispersion of two or more
data sets with different units

CV= 100*standard deviation/|mean|

29

30

10
25 Jul 2022

Measures of Position or Relative


Standing
 describes the standing or location of an
observation relative to the rest of the data

 Quartiles
 Deciles
 Percentiles

31

Percentiles
 divides the set of data into 100 equal
parts
 Pi - ith percentile of the data set.
 at least i percent of the data set is less
than or equal to the value of Pi
 Percentiles are from P1 to P99.

32

Example: Percentile
Consider P45. P45 divides the data set into
45% at the left of P45 and 55% at the
right of P45.

Position of Pi = (i/100)(n+1) where n is the


number of observations in the set of data

33

11
25 Jul 2022

Example: Percentile
Remark. The set of observations must be
arranged in ascending order.

Consider the following set of data:


2, 6, 8, 9, 14, 16, 21, 27, 28, 29, 34
Find 44th percentile.

Solution:
Position of P44 = (44/100)(11+1) = 5.28

34

35

Rules:
▪ If the resulting positioning is an integer,
the particular numerical observation
corresponding to that positioning point is
chosen.
▪ If the resulting positioning point is
halfway between two integers, the
average of their corresponding
observations is computed.
▪ If the resulting positioning point is
neither an integer nor a value halfway
between two integers, a simple rule is to
round to the nearest integer and select
the numerical value of the corresponding
observation.
36

12
25 Jul 2022

37

38

Quartiles
 divide the set of data into 4 equal parts
 denoted by Qi, where i indicates the ith
quartile of the data set.
 Quartiles are from Q1 to Q3.

Position of Qi = (i/4)(n+1)

39

13
25 Jul 2022

40

Deciles
 divide the set of data into 10 equal parts
 denoted by Di, where i indicates the ith
decile of the data set.
 Deciles are from D1 to D9.

Position of Di = (i/10)(n+1)

41

42

14
25 Jul 2022

43

Measure of Skewness
 A set of observations is symmetrically
distributed if its graphical representation
(histogram, bar chart) is symmetric with
respect to a vertical axis passing through
the mean.
 For a symmetrically distributed population
or sample, the mean, median and mode
have the same value

44

Symmetric Distribution

45

15
25 Jul 2022

Measure of Skewness
skewed distribution – not symmetrically
positively skewed distribution - a
greater proportion of the observations are
less than or equal to the mean; this
indicates that the mean is larger than the
median.
The histogram of a positively skewed
distribution will generally have a long right
tail; thus, this distribution is also known
as being skewed to the right.

46

Positively Skewed Distribution

47

Measure of Skewness
negatively skewed distribution - has
more observations that are greater than
or equal to the mean
-mean is less than the median
The histogram of a negatively skewed
distribution will generally have a long left
tail; thus, the phrase skewed to the left
is applied here.

48

16
25 Jul 2022

Negatively Skewed Distribution

49

Measure of Skewness
The formula for the coefficient of skewness
is given by

SK = 3(mean – median) / stan. dev.

50

Measure of Skewness
 SK = 0 - a symmetric distribution

 SK > 0 - a positively skewed distribution

 SK < 0 - a negatively skewed


distribution

51

17
25 Jul 2022

52

Skewness: Box and Whisker Plots,


and Coefficient of Skewness
S<0 S=0 S>0

Negatively Symmetric Positively


Skewed (Not Skewed) Skewed
© 2002 Thomson / South-Western Slide 3-53

53

Kurtosis
 Peakedness of a distribution
◼ Leptokurtic: high and thin
◼ Mesokurtic: normal in shape
◼ Platykurtic: flat and spread out

Leptokurtic

Mesokurt
ic Platykurtic

© 2002 Thomson / South-Western Slide 3-54

54

18
25 Jul 2022

Kurtosis
 Measure of peakness of a distribution
 indicates the extent to which the values of
the variable fall above or below the mean
and manifests itself as a fat tail

55

KURTOSIS
 Leptokurtic – Kurt > 3
 Platykurtic -- Kurt < 3
 Normal distribution – Kurt = 3; SK = 0

56

ZERO EXCESS KURTOSIS


 metric that compares the kurtosis of a
distribution against the kurtosis of a
normal distribution

 EXCESS KURTOSIS = kurtosis - 3


Leptokurtic – Excess Kurt > 0
Platykurtic -- Excess Kurt < 0
Normal distribution – Excess Kurt = 0; SK = 0

57

19
25 Jul 2022

58

20

You might also like