Chapter 3

Descriptive
Statistics
 Distinguish between measures of central
tendency, measures of variability, and
measures of shape
 Understand the meanings of mean, median,

mode, quartile, percentile, and range

 Compute mean, median, mode, percentile,

quartile, range, variance, standard deviation,

and mean absolute deviation
 Differentiate between sample and population
variance and standard deviation
 Understand the meaning of standard

deviation as it is applied by using the

empirical rule
 Understand box and whisker plots, skewness,

and kurtosis
 Measures of central tendency yield
information about “particular places or
locations in a group of numbers.”
 Common Measures of Location

◦ Mode
◦ Median
◦ Mean
◦ Percentiles
◦ Quartiles
 The most frequently occurring value in a data
set
 Applicable to all levels of data measurement

(nominal, ordinal, interval, and ratio)

 Bimodal -- Data sets that have two modes

 Multimodal -- Data sets that contain more

than two modes

 30, 32, 34, 34, 38, 39, 43,43,44,44,44, 47,49
 The mode is 44.
 There are more 44s

than any other value.

 Middle value in an ordered array of numbers.
 Applicable for ordinal, interval, and ratio data
 Not applicable for nominal data
 Unaffected by extremely large and extremely

small values.
 First Procedure
◦ Arrange observations in an ordered array.
◦ If number of terms is odd, the median is the
middle term of the ordered array.
◦ If number of terms is even, the median is the
average of the middle two terms.

 Second Procedure
◦ The median’s position in an ordered array is
given by (n+1)/2.
 Ordered Array includes:
3 4 5 7 8 9 11 14 15 16 16 17 19 19 20 21
22

 There are 17 terms in the ordered array.

 Position of median = (n+1)/2 = (17+1)/2 = 9
 The median is the 9th term, 15.
 If the 22 is replaced by 100, the median
remains at 15.
 If the 3 is replaced by -103, the median
remains at 15.
 Is the average of a group of numbers
 Applicable for interval and ratio data, not

applicable for nominal or ordinal data

 Affected by each value in the data set,

including extreme values

 Computed by summing all values in the data

set and dividing the sum by the number of

values in the data set
  X X X X  ...  X N
  1 2 3
N N
24  13  19  26  11

5
93

5
 18. 6
  X X X X  ...  X n
X  1 2 3

n n
57  86  42  38  90  66

6
379

6
 63.167
 Measures of central tendency that divide a
group of data into four subgroups

 Q1: 25% of the data set is below the first

quartile
 Q2: 50% of the data set is below the second

quartile
 Q3: 75% of the data set is below the third

quartile
 Q1 is equal to the 25th percentile

 Q2 is located at 50th percentile and equals

the median

 Q3 is equal to the 75th percentile

Quartile values are not necessarily members

of the data set
 Q1 Q2 Q3

25% 25% 25% 25%

©
 Ordered array: 106, 109, 114, 116, 121,
122, 125, 129

Q1: 25 109  114


i ( 8 )  2          Q 1   111 . 5
100 2
50 116  121
 Q2: i ( 8 )  4          Q 2   118 . 5
100 2
75 122  125
 Q3: i ( 8 )  6          Q 3   123 . 5
100 2
 Measures of variability describe the
spread or the dispersion of a set of data.
 Common Measures of Variability

◦ Range
◦ Interquartile Range
◦ Mean Absolute Deviation
◦ Variance
◦ Standard Deviation
◦ Z scores
◦ Coefficient of Variation
No Variability in Cash Flow Mean
Mean

Variability in Cash Flow Mean

Mean
 The difference between the largest and the
smallest values in a set of data
 Simple to compute
 Ignores all data points
except the
two extremes
 Example: 35, 37,38, 41,43,46,47,48
Range
Largest - Smallest
48 - 35 = 13
 Range of values between the first and third
quartiles
 Range of the “middle half”
 Less influenced by extremes

Interquartile   Range  Q3 Q1

 Data set: 5, 9, 16, 17, 18
 Mean:


 X

65
 13
N 5
 Deviations from the mean: -8, -4, 3, 4, 5
+5
+3 +4
-8 -4


 Average of the absolute deviations from the
mean

    X X  X  
M . A. D. 
 X
5 -8 +8 N
9 -4 +4 24
16 +3 +3 
17 +4 +4
5
18 +5 +5  4. 8
0 24
  Average of the squared deviations from the
arithmetic mean

    X X    X  
  X  
2
2


2
5 -8 64 
9 -4 16 N
16 +3 9 130

17 +4 16 5
18 +5 25  26.0
0 130
 Square root of the
variance
  X  
2

    X X    X   
2
2

N
5 -8 64 130
9 -4 16 
5
16 +3 9
 26.0
17 +4 16
18 +5 25

2
 
0 130
 26.0
 51
.
 Data are normally distributed (or
approximately normal)

Distance from Percentage of Values

the Mean Falling Within Distance

  1 68
  2 95
  3 99.7
  Average of the squared deviations from the
arithmetic mean

    X X  X XX  X  X 
2
2

2
2,398 625 390,625 S 
n 1
1,844 71 5,041
1,539 -234 54,756 663,866

1,311 -462 213,444 3
7,092 0 663,866  221,288.67
  X  X 
2
 Square root of the
sample variance
2
S 
    X X  X XX
n 1
2

663,866
2,398 625 390,625 
1,844 71 5,041
3
1,539 -234 54,756  221,288.67
1,311 -462 213,444 2
7,092 0 663,866 S S
 221,288.67
 470.41
 Ratio of the standard deviation to the mean,
expressed as a percentage
 Measurement of relative dispersion


C .V .   100 

 1  29 2  84
 1
 4.6  2
 10
 
. .    100
CV 1
1
CV
. .
2
2
 100
1 2

4.6 10
  100   100
29 84
 1586
.  1190
.
 Skewness
◦ Absence of symmetry
◦ Extreme values in one side of a
distribution
Negatively Symmetric Positively
Skewed (Not Skewed) Skewed
Mean Mode Mean Mean
Mode
Median
Median Mode Median

Negatively Symmetric Positively

Skewed (Not Skewed) Skewed
 Summary measure for skewness

3   M d 
S 

 If S < 0, the distribution is negatively skewed
(skewed to the left).
 If S = 0, the distribution is symmetric (not

skewed).
 If S > 0, the distribution is positively skewed

(skewed to the right).

   23
1
 2
 26  3
 29

M  26
d1 M d2  26 Md3  26
  12.3
1  2
 12.3  3
 12.3

3   M  d1 
3 2  M d2  
3 3  M 
d3
S  S S
1
 
1
1
2
 2
3
 3

3 23  26 3 26  26 3 29  26

  
12.3 12.3 12.3
 0.73 0  0.73
 It determines if a relationship exists between
two or more quantitative variables.
 Sometimes such a relationships are useful in

prediction, or cause.
 There are many different correlation

coefficients, each applying to a particular

circumstances and each calculated by
different formulas
 Pearson coefficient is the most frequently

used correlation coefficient

 R=nxy-(x)(y) / [nx2 – (y)2][ny2-(y2)]
 Example
Student Variable X Variable Y
A 20 20
B 18 16
C 18 20
D 15 12
E 10 10
x=81
y=78
x2=1373
y2=1300
xy=1328
R= 5[1328] – (81)(78)/[5(1373)-812][5(1300)-78]
R=322/355.61=0.9