BMS1024 Topic2

Descriptive
Statistics
BMS1024 MANAGERIAL STATISTICS
Key Concepts
The central location is the extent to which all
the data values group around a typical or

central value.
The variation is the amount of dispersion, or
scattering of values
The shape is the pattern of the distribution of
values from the lowest value to the highest

value.
BMS1024 Managerial Statistics
Numerical Descriptive
Measures for a Sample
SUMMARY MEASURES
Central
Location
Mean
Median
Mode
Variation
Quartiles
Range
Interquartile Range
Variance
Standard deviation
Coefficient of Variance
Five-number summary consists

of the minimum value, Q1,
median, Q3 and maximum value.
Measures of Central
Location
SUMMARY
Central Location
Arithmetic
Mean
Median
Mode
X
i 1
Middle value in
the ordered array
Most frequently
observed value
Measures of Central
Location
THE ARITHMETIC MEAN
The arithmetic mean (mean) is the most common
measure of central location

For a sample of size n:
n
X
Sample size
X
i 1
X1 X 2 X n
n
Observed values
5
Measures of Central
Location
THE ARITHMETIC MEAN
The most common measure of central location
Mean = sum of values divided by the number of values
Affected by extreme values (outliers)
EXAMPLE 1
The data given below are the 2008 profits (rounded to
billions of dollars) of 12 companies selected from all over
the world.
8 12 7 17 14 45 10
13 17 13 9 11
Compute the mean profit for these companies.
Solution:
12
8 12 11 176
X
14.67
12
12
12
i 1
The mean profit is $ 14.67 billion.

Measures of Central
Location
THE MEDIAN
In an ordered array, the median is the middle number
(50% above, 50% below)

Not affected by extreme values
Measures of Central
Location
THE MEDIAN
The median of an ordered set of data is located at the
(n+1)/2 ranked value.

If the number of values is odd, the median is the
middle number.
If the number of values is even, the median is the
average of the two middle numbers.

Note that (n+1)/2 is NOT the value of the median, only
the position of the median in the ranked data.

EXAMPLE 2
Refer to same data as provided in the previous
example.
Compute the median profit for those companies.
Solution:
First, rank the values:

7, 8,
9,
10,
11,
12,
13,
14,
17,
17,
45
13,
The median is in between the 6th and 7th values (or at

the 6.5th position)
12 13
12.5
Hence, the median
2
The median profit is $ 12.5 billion.

10
Measures of Central
Location
THE MODE
Value that occurs most often
Not affected by extreme values
Used for either numerical or categorical data
There may be no mode
There may be several modes
11
EXAMPLE 3
Refer to same data in the previous example.
Determine the mode for the data.
Solution:
First, rank the values:

7, 8,
9,
10,
11,
12,
13,
14,
17,
17,
45
13,
13 occurs twice. 17 also occurs twice.

The modes are $13 billion and $17 billion.
12
Measures of Central
Location
Review Example
House Prices:
$2,000,000
500,000
300,000
100,000
100,000
Sum 3,000,000
Mean:
($3,000,000/5)
= $600,000
Median: middle value of ranked data
= $300,000
Mode: most frequent value
= $100,000
Learn how to compute mean using the
Mode SD function on your scientific
calculator!
13
Measures of Central
Location
WHICH MEASURE TO CHOOSE?
The mean is generally used, unless extreme
values (outliers) exist.

Then median is often used, since the median
is not sensitive to extreme values. For

example, median home prices may be
reported for a region; it is less sensitive to
outliers.
14
Quartile Measures
Quartiles split the ranked data into 4 segments with an
equal number of values per segment.

25%
Q1 = lower
quartile
25%
Q1
25%
Q2
25%
Q3
Q3 = upper
quartile
The first quartile, Q1, is the value for which 25% of the observations
are smaller and 75% are larger
Q2 is the same as the median (50% are smaller, 50% are larger)
Only 25% of the values are greater than the third quartile
15
Quartile Measures
LOCATING QUARTILES
Find a quartile by determining the value in the appropriate
position in the ranked data, where
First quartile position:
Second quartile position:
Third quartile position:
Q1 = (n+1)/4 ranked value

Q2 = (n+1)/2 ranked value
Q3 = 3(n+1)/4 ranked value
where n is the number of observed values

16
Quartile Measures
GUIDELINES
Rule 1: If the result is a whole number, then the quartile is
equal to that ranked value.
Rule 2: If the result is a fraction half (2.5, 3.5, etc), then the
quartile is equal to the average of the corresponding ranked
values.
Rule 3: If the result is neither a whole number or a fractional
half, you round the result to the nearest integer and select that
ranked value.
17
Quartile Measures
LOCATING THE FIRST QUARTILE
Sample Data in Ordered Array: 11 12 13 16 16 17 18 21 22
First, note that n = 9.
Q1 = is in the (9+1)/4 = 2.5 ranked value of the ranked data, so use
the value half way between the 2nd and 3rd ranked values,
so
Q1 = 12.5
Q1 and Q3 are measures of non-central location

Q2 = median, a measure of central location
18
EXAMPLE 4
Refer to same data as in the previous example.
Find all quartiles and interpret their results.
Solution:
First, compute the position of each quartile value.

Then, find the quartile value in ranked data.
Quartile
Q1
Q2
Q3
Position
(12+1)/4
= 3.15 3
(12+1)/2
= 6.5
3(12+1)/4 =
9.45 9.5
12.5
15.5
Value
19
EXAMPLE 4 Continued
Q1 = 9. This result indicate that 25% of the companies
have profits equal to or lesser than $ 9 billion. Also, 75%
of the companies have profits equal to or greater than $
9 billion.
Q2 = 12.5. This result indicate that 50% of the
companies have less than $ 12.5 billion profit. Also, 50%
of the companies have more than $ 12.5 billion profit.
Q3 = 15.5. This result indicate that 75% of the
companies have less than $ 15.5 billion profit. Also, 25%
of the companies have more than $ 15.5 billion profit.
20
Measures of Variation/
Dispersion/ Variability
Variation measures the spread, or dispersion, of
values in a data set:
Range
Interquartile Range
Variance
Standard Deviation
Coefficient of Variation
Small
dispersion
Large
dispersion
21
Measures of Variation
RANGE
Simplest measure of variation

Difference between the largest and the smallest
values:
Range = Xlargest Xsmallest

Example:
22
RANGE
Disadvantages of the range:
Ignores the way in which data are distributed
Sensitive to outliers
23
INTERQUARTILE RANGE
Problems caused by outliers can be eliminated by
using the interquartile range (IQR).

The IQR can eliminate some high and low values and
calculate the range from the remaining values.

Interquartile Range = 3rd quartile 1st quartile
= Q3 Q1
24
INTERQUARTILE RANGE
Example of a five-number summary:
IQR isnt affected by the

outliers because it shows
only the dispersion in the
middle 50% of the data!
25
EXAMPLE 5
Refer to the following data: (continuation of previous
examples)
8 12 7 17 14 45 10
13 17 13 9 11
Compute the range and interquartile range.
Solution:
Range 45 7 38
IQR Q3 Q1 15.5 9 6.5
26
Outlier Detection
For the data 2, 5, 6, 9, 12, we have the following five-number summary:
Xminimum = 2; Q1 = 3.5;
Median = 6; Q3 = 10.5; Xmaximum = 12
Range = 12-2 = 10
IQR = Q3 Q1 = 10.5 3.5 = 7
To determine if there are outliers we must consider the numbers that
are 1.5*IQR beyond the quartiles.
Below lower quartile Q1 1.5*IQR = 3.5 10.5 = 7

Above upper quartile Q3 + 1.5*IQR = 10.5 + 10.5 = 21
Since none of the data are outside the interval from 7 to 21, there are
no outliers.
27
EXERCISE
exercises and examples)
8 12 7 17 14 45 10
13 17 13 9 11
Is there any outlier in the data? If yes, remove that outlier
and find the summary measures for the new data.
28
VARIANCE
The variance is the average

(approximately) of squared
deviations of values from the
mean.
where
x = arithmetic mean
n = sample size
Xi = ith value of the variable X
X 2i = ith squared value of the variable X
29
STANDARD DEVIATION
Most commonly used measure of variation

Shows variation about the mean
Has the same units as the original data
n
Sample standard deviation:
i 1
n 1
n(n 1 )
i 1
30
STANDARD DEVIATION
Sample Data (xi) :

10
12
n8
14
15
17
18
18
24
Mean X 16
10
12 2 ... 24 2
10 12 ... 24
8 1
8 8 1
2178 128
7
8 7
4.3095
A measure of the average

scatter around the mean
Learn how to compute standard deviation using the Mode SD function

on your scientific calculator!
31
EXERCISE
exercise and examples)
8 12 7 17 14 45 10
13 17 13 9 11
(i)
Compute the variance and standard deviation.
(ii) Is there any difference in standard deviation when
an outlier is removed?
32
STANDARD DEVIATION
Comparing standard deviation
33
STANDARD DEVIATION
34
COEFFICIENT OF VARIATION (CV)
The coefficient of variation is the standard deviation
divided by the mean, multiplied by 100.

It is always expressed as a percentage (%).
It shows variation relative to mean.
It is a useful measure when:
data are measured in different units.
data are in the same units but the means are far apart.
s
CV
X
100%
35
COEFFICIENT OF VARIATION (CV)
STOCK A
Average price last year =
$50
Standard deviation = $5
CV A
5
100% 10%
50
STOCK B
Average price last year =
$100
CV
B
5
100% 5%
100
Standard deviation = $5
Relative to the mean, prices in stock B is less

variable compared to prices in stock A.
36
Exercise
The variation in the annual incomes of executives at
Nash Rambler Products, Inc is to be compared with the
variation in incomes of unskilled employees.
The observation from a sample of executives,
RM500,000 and s = RM50000.
For a sample of unskilled employees,
and s = RM3,200.
X =
= RM32000
Compare the relative dispersion in these two

distributions using coefficient of variation.
37
SUMMARY CHARACTERISTICS:
The more the data are spread out, the greater the range,
interquartile range, variance, and standard deviation.

The more the data are concentrated, the smaller the
range, interquartile range, variance, and standard

deviation.
If the values are all the same (no variation), all these
measures will be zero.

None of these measures are ever negative.
38
Shape of a Distribution
Describes how data are distributed
Measures of shape: Symmetric or skewed
39
Pearsons Coefficient of
Skewness
It is used to measure the degree of skewness of a
distribution.
Sk = 0 indicates a symmetrical distribution

Sk = +ve indicates a right-skewed distribution
Sk = -ve indicates a left-skewed distribution
Approximation Formula
3( X Median)
Sk
s
40
EXAMPLE 6
examples)
8 12 7 17 14 45 10
13 17 13 9 11
Compute the Pearsons coefficient of skewness and
describe the shape of the distribution.
Solution:
3( X Median) 314.67 12.5

Sk
0.6467
s
10.066
The distribution of the data is slightly skewed to the right.
41
General Descriptive
Stats Using Microsoft
Excel
Add-in Data
Analysis into your
Excel.
Go to Developer >>
Add-ins >> Select
Analysis ToolPak >>
Click OK button.
42
General Descriptive
Excel
1. Enter data.
2. Select Data.
3. Select Data
Analysis.
4. Select
Descriptive
Statistics and
click OK.
43
General Descriptive
Excel
5. Enter the cell
range.
6. Check the
Summary
Statistics box.
7. Click OK.
44
General Descriptive
Excel
Microsoft Excel
descriptive statistics
output, using the house
price data:
House Prices:
$2,000,000
500,000
300,000
100,000
100,000
45
Example: Simple
Interpretation
The average house prices is $ 600,000.
50 percent of the house prices are $300,000 and
below. 50 percent of the house prices are $300,000

and above.
The most houses are priced at $100,000.
The standard deviation is $800,000.
The range of house prices is $190,000.
The distribution of house prices is skewed to the right.
46
Numerical Descriptive
Measures for a Population
Descriptive statistics discussed previously
described a sample, not the population.

Summary measures describing a population,
called parameters, are denoted with Greek

letters.
Important population parameters are the
population mean, variance, and standard

deviation.
47
Population Mean
The population mean is the sum of the values in
the population divided by the population size, N.
N
where
X
i 1
X1 X 2 X N
= population mean
N = population size
48
Population Variance
The population variance is the average of
squared deviations of values from the mean.
N
2
where
2
(
X
)
i
i 1
= population mean
Population
variance is seldom
used because we
usually rely on
sample data, not
population data!
N = population size
49
Population Standard
Deviation
The population standard deviation is the most
commonly used measure of variation.

It has the same units as the original data.
N
where
2
(
X
)
i
i 1
= population mean
N = population size
Population
standard deviation
is seldom used
because we
usually rely on
sample data, not
population data!

50
Sample Statistics
versus Population
Parameters
51
CLASS EXERCISE 1
The following data is the amount that a sample of 10
customers spent for lunch ($) at a fast-food restaurant:
7.42
6.29
5.90
4.89
(i)
5.83
6.50
8.34
9.51
7.10
6.80
List the five-number summary.
(ii) Compute the mean, mode, standard deviation, Q 1
and Q3.
(iii) Is the data skewed? If so, how?
(iv) Based on your results of (i) to (iii), what conclusions
can you reach concerning the amount that

customers spent for lunch?
52
At the end of this

lesson, you should be
able to:
Compute the measures of central location
and variation for ungrouped data

Interpret the measures of central location
and variation
Describe the shape of a distribution
53

BMS1024 Topic2

Caricato da

Informazioni sul documento

Titolo originale

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

BMS1024 Topic2

Caricato da

Copyright:

Formati disponibili

Descriptive

the data values group around a typical or

The variation is the amount of dispersion, or

The shape is the pattern of the distribution of

values from the lowest value to the highest

BMS1024 Managerial Statistics

BMS1024 Managerial Statistics

Five-number summary consists

BMS1024 Managerial Statistics

measure of central location

BMS1024 Managerial Statistics

The mean profit is $ 14.67 billion.

(50% above, 50% below)

BMS1024 Managerial Statistics

(n+1)/2 ranked value.

average of the two middle numbers.

the position of the median in the ranked data.

First, rank the values:

The median is in between the 6th and 7th values (or at

The median profit is $ 12.5 billion.

BMS1024 Managerial Statistics

First, rank the values:

13 occurs twice. 17 also occurs twice.

BMS1024 Managerial Statistics

BMS1024 Managerial Statistics

values (outliers) exist.

is not sensitive to extreme values. For

equal number of values per segment.

BMS1024 Managerial Statistics

Q1 = (n+1)/4 ranked value

where n is the number of observed values

Q1 and Q3 are measures of non-central location

First, compute the position of each quartile value.

BMS1024 Managerial Statistics

BMS1024 Managerial Statistics

BMS1024 Managerial Statistics

Simplest measure of variation

Range = Xlargest Xsmallest

BMS1024 Managerial Statistics

Disadvantages of the range:

Ignores the way in which data are distributed

BMS1024 Managerial Statistics

Problems caused by outliers can be eliminated by

using the interquartile range (IQR).

calculate the range from the remaining values.

Example of a five-number summary:

IQR isnt affected by the

BMS1024 Managerial Statistics

Median = 6; Q3 = 10.5; Xmaximum = 12

are 1.5*IQR beyond the quartiles.

Below lower quartile Q1 1.5*IQR = 3.5 10.5 = 7

BMS1024 Managerial Statistics

BMS1024 Managerial Statistics

The variance is the average

Most commonly used measure of variation

Sample standard deviation:

BMS1024 Managerial Statistics

Sample Data (xi) :

A measure of the average

Learn how to compute standard deviation using the Mode SD function

BMS1024 Managerial Statistics

Compute the variance and standard deviation.

(ii) Is there any difference in standard deviation when