Describing the Data

using Numerical Measures

IS 106 - FUNDAMENTALS OF COMPUTING
Objectives

1. Compute the mean, median, mode, and weighted mean for a set of data and
understand what these values represent.
2. Compute the range, interquartile range, variance, standard deviation and know
what these values means.
3. Compute a z score and the coefficient of variation and understand how they
are applied in decision making situations.
4. Understand and apply some basic statistical and mathematical formulas in
analyzing numeric data behavior.

IS 106 – QUANTITATIVE METHODS

Introduction

o Graphs and charts ---

 provide effective tools for transforming data into information – this is just
the starting point!
 do not reveal all the information contained in a dataset.

o To complete our descriptive toolkit ---

 quantify the center of data and its spread – with numerical measures

IS 106 – QUANTITATIVE METHODS

Why learn?

o Suppose you are an ad manager

 Your task is to create an ad claiming that your company’s tire last longer

 You could:

• sample your tires and from your competition

• and graph each data in a histogram

IS 106 – QUANTITATIVE METHODS

Why learn?

o You should:
 Compute the summary mileage measures for the various tire brands

o To effectively describe data:

 combine graphical tools with numerical measures

IS 106 – QUANTITATIVE METHODS

 Measures of Center and
Location

IS 106 – QUANTITATIVE METHODS

Measures of Center and Location

o Histograms are an effective way of converting quantitative data to

information
 It can show us the center of data and degree of spread

o Numerical measures help fully describe a quantitative data

 It can give us numerical measure of center and spread

IS 106 – QUANTITATIVE METHODS

Recall !

o“ What do we call numerical measures derived from a sample? ”

IS 106 – QUANTITATIVE METHODS

Parameters and Statistics

o Parameter
 A measure computed from the entire population

 As long as the population does not change, the value of the

parameter will not change

IS 106 – QUANTITATIVE METHODS

Parameters and Statistics

o Statistics
 A measure computed from a sample that has been selected from a
population
 The value of the statistic will depend on which sample is selected

IS 106 – QUANTITATIVE METHODS

Mean

o A numerical measure of the center of a set of quantitative measures

 computed by dividing the sum of the values by the number of values in
the data.

 Population Mean, Sample Mean

IS 106 – QUANTITATIVE METHODS

Population Mean

o The average for all values in the population computed by dividing

the sum of all values by the population size.

IS 106 – QUANTITATIVE METHODS

Population Mean

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the data for the variable of interest for all items in the
population. The data must be quantitative.

2. Sum all the values in the population.

3. Divide the sum by the number of values in the population.

IS 106 – QUANTITATIVE METHODS

Population Mean - Example

FOSTER CITY HOTEL. The manager of a small hotel in Foster

City, California, was asked by the corporate vice president to analyze
the Sunday night registration information for the past eight weeks.
Specifically, the goal is to identify the average number of rooms
rented on Sunday.

IS 106 – QUANTITATIVE METHODS

Population Mean - Example

IS 106 – QUANTITATIVE METHODS

Population Mean - Example

1. Collect data for the quantitative variable of interest.

IS 106 – QUANTITATIVE METHODS

Population Mean - Example

2. Add the data values.

= 121
IS 106 – QUANTITATIVE METHODS
Population Mean - Example

3. Divide the sum by the number of values in the population

Parameter Measure

Therefore, the average number of rooms

rented on Sundays for the past eight weeks is
15.125.

IS 106 – QUANTITATIVE METHODS

Sample Mean

o The average for all values in the sample computed by dividing the
sum of all sample values by the sample size.

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the sample data

2. Add the values in the sample.

3. Divide the sum by the sample size.

IS 106 – QUANTITATIVE METHODS

Sample Mean - Example

oTask: Compute the mean starting salary.

IS 106 – QUANTITATIVE METHODS

Sample Mean - Example

1. Collect the sample data

IS 106 – QUANTITATIVE METHODS

Sample Mean - Example

2. Add the values in the sample

IS 106 – QUANTITATIVE METHODS

Sample Mean - Example

3. Divide the sum by the sample size.

o Therefor, the average starting salary for the sample of seven

managers place is $170,571.43

IS 106 – QUANTITATIVE METHODS

The Impact of Extreme Values on the Mean

o Recall: The mean is the balance point for the data.

o But! It has a potential disadvantage

o The Disadvantage: It can be affected by extreme values.

 An extreme value on the high end can pull the mean upward from the center.

IS 106 – QUANTITATIVE METHODS

Impact of Extreme Values - Example

o What if our previous example ( Management Salaries) had been slightly

changed.

o We will change the salary from $316,000 to $1,000,000.

IS 106 – QUANTITATIVE METHODS

Impact of Extreme Values - Example

1. Collect the sample data

Extreme Value

IS 106 – QUANTITATIVE METHODS

Impact of Extreme Values - Example

2. Add the values.

IS 106 – QUANTITATIVE METHODS

Impact of Extreme Values - Example

3. Divide the sum buy the number of values in the sample.

IS 106 – QUANTITATIVE METHODS

Impact of Extreme Values - Example

Conclusion:
o With only one value in the sample changed, the mean is now substantially higher than before.

o Because the mean is affected by extreme values, it may be a misleading measure of data’s center.

IS 106 – QUANTITATIVE METHODS

Median

o Another measure of center of data

o A center value that divides a data array into two halves

 denotes the population median
 denotes the sample median

Data that have been arranged in numerical order.

IS 106 – QUANTITATIVE METHODS

Median

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the sample data

2. Sort the data from smallest to largest, forming a data array.

3. Calculate the median index.

4. Find the median.

IS 106 – QUANTITATIVE METHODS

Median - Example

IS 106 – QUANTITATIVE METHODS

Median - Example

1. Collect the sample data

IS 106 – QUANTITATIVE METHODS

Median - Example

2. Sort the data from smallest to largest.

IS 106 – QUANTITATIVE METHODS

Median - Example

3. Calculate the median index.

  1   1
𝑖= 𝑛
2
𝑖= (7)
2 𝑖=3.5
    𝑖= 4

IS 106 – QUANTITATIVE METHODS

Median - Example

4. Find the median.

IS 106 – QUANTITATIVE METHODS

Median – Example with an Extreme Value

=4

IS 106 – QUANTITATIVE METHODS

Skewed and Symmetric Distributions

o Data in a population or sample can be either symmetric or skewed

 depending on the distribution of data around the center.

IS 106 – QUANTITATIVE METHODS

Skewed and Symmetric Distributions

o Symmetric Data
 Datasets whose values are evenly spread around the center.

 Mean and Median are equal.

IS 106 – QUANTITATIVE METHODS

Skewed and Symmetric Distributions
o Skewed Data
 Datasets that are not symmetric

 The mean will be larger or smaller than the median.

 Right Skewed

• The mean is larger than the median

 Left Skewed

• The mean is smaller than the median

IS 106 – QUANTITATIVE METHODS

Skewed and Symmetric Distributions

IS 106 – QUANTITATIVE METHODS

Skewed and Symmetric Distributions

oManagement Salaries.

Mean
> Median

Right Skewed
IS 106 – QUANTITATIVE METHODS
Mode

o Another measure of central location

o A value in a data set that occurs most frequently

o A data set may have more than one mode if multiple values tie for
the most frequently occurring values.

o If no value occurs more frequently than any other, there is no mode.

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the sample data.

2. Organize the data into a frequency distribution.

3. Determine the value(s) that occur(occurs) most frequently.

IS 106 – QUANTITATIVE METHODS

Mode - Example

IS 106 – QUANTITATIVE METHODS

Mode - Example

1. Collect the sample data.

IS 106 – QUANTITATIVE METHODS

Mode - Example

2. Organize the data into a frequency distribution

IS 106 – QUANTITATIVE METHODS

Mode - Example

3. Determine the value(s) that occur(occurs) most frequently.

IS 106 – QUANTITATIVE METHODS

Mode – Common Mistake

o Stating the mode as being the frequency of the most frequently

occurring value.

o In our example,
 The modes are 2 and 4, the occurred 6 times.

IS 106 – QUANTITATIVE METHODS

 Other Measures of
Center and Location
WEIGHTED MEAN

PERCENTILES

Q U A RT I L E S

IS 106 – QUANTITATIVE METHODS

Weighted Mean

o The mean of data values that have been weighted according to their
relative importance.

IS 106 – QUANTITATIVE METHODS

Weighted Mean

o Consider this:

o The above formula is what we have used to compute for the mean of a sample.

o In this case, each x value is given equal weight in the computation

o However, there will be times, when some other values are weighted more than
the other.

IS 106 – QUANTITATIVE METHODS

Weighted Mean

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the desired data and determine the weight to be assigned to each data
value.

2. Multiply each weight by the data value and sum these.

3. Sum the weights for all values.

4. Compute the weighted mean.

IS 106 – QUANTITATIVE METHODS

Weighted Mean - Example

oOne of the most common usage of weighted mean measure is in computing your
General Point Average (GPA).

IS 106 – QUANTITATIVE METHODS

Weighted Mean - Example

1. Collect the desired data and determine the weight to be assigned to each data
value.

1.00 1.00 1.00 1.00 1.00 1.00 1.25

3 3 3 3 3 3 3
IS 106 – QUANTITATIVE METHODS
Weighted Mean - Example

2. Multiply each weight by the data value and sum these.

= (1.00 * 3) + (1.00 * 3) + (1.00 * 3) + (1.00 * 3) + (1.00 * 3) + (1.00 *

3) + (1.25 * 3 )

= 3.0 + 3.0 + 3.0 + 3.0 + 3.0 + 3.0 + 3.75

= 21.75

IS 106 – QUANTITATIVE METHODS

Weighted Mean - Example

3. Sum the weights for all values.

= 3.0 + 3.0 + 3.0 + 3.0 + 3.0 + 3.0 + 3.00

= 21

IS 106 – QUANTITATIVE METHODS

Weighted Mean - Example

4. Computed the weighted mean.

  𝛴 𝑤 𝑖 𝑥𝑖 21.75
𝜇𝑤 = = = 1.0357=1.04
𝛴 𝑤𝑖 21

Your GPA is 1.04.

IS 106 – QUANTITATIVE METHODS

Percentiles

o Used to describe the location of the data in terms other than center of data.

o Definition:
 the pth percentile in a data array is a value that divides the data set into two parts.

 the lower segment contains at least p% and the upper segment contains at least 100
– p%

IS 106 – QUANTITATIVE METHODS

Percentiles

o Suppose:
 You are enrolling in a university and took an entrance exam. You then received the result
saying that your score is at the 90th percentile. What does it mean?

• It means that you scored as high or higher than 90% of the other students.

 What if you scored at 50th percentile?

IS 106 – QUANTITATIVE METHODS

Percentile Location Index

o Allows us to point the exact value associated with the percentile.

IS 106 – QUANTITATIVE METHODS

Percentiles – How to?

1. Sort the data in order from the lowest to the highest value.

2. Determine the percentile location index.

3. Locate the percentile value.

a) If i is not an integer, round the value up to the next highest integer. The pth
percentile is located at the rounded index position.

b) If i is an integer, the pth percentile is the average of the values at location index
positions i and i + 1

IS 106 – QUANTITATIVE METHODS

Percentiles – Example?

IS 106 – QUANTITATIVE METHODS

Percentiles – Example

1. Sort the data in order from the lowest to the highest value.

IS 106 – QUANTITATIVE METHODS

Percentiles – Example

2. Determine the percentile location index.

  𝑃 80
ⅈ= ( 𝑛 )= ( 30 ) =24
100 100

IS 106 – QUANTITATIVE METHODS

Percentiles – Example

3. Locate the percentile value.

o Because i = 24 is an integer value, the 80th percentile is found by averaging the values in

the 24th and 25th positions.

o Therefor, the distance on the 80th percentile that will be subject to surcharge is :

20.5 + 21 = 20.75

IS 106 – QUANTITATIVE METHODS

Quartiles

o Quartiles in a data array are those values that divide the data set into four equal-
sized groups.

o The median corresponds to the second quartile.

o Can be approximated manually using the same method as for percentiles.

IS 106 – QUANTITATIVE METHODS

Quartiles

o First quartile (25th percentile)

 The value at or below in which there is at least 25% (a quarter) of the data

 and at or above which there is at least 75% of the data.

o Second Quartile (50th percentile)

 There is 50% at or below the data and 50% at or above the data

IS 106 – QUANTITATIVE METHODS

Quartiles

o Third Quartile (75th percentile)

 The value at or below which there is at least 75% of the data

 and at or above which there is at least 25% of the data

o Fourth Quartile
 The rest

IS 106 – QUANTITATIVE METHODS

Quartiles – Example?

o Let’s say we’re only interested in the 3rd quartile of this data.

IS 106 – QUANTITATIVE METHODS

Quartiles – Example

  𝑃 75
ⅈ= ( 𝑛=
) ( 30 ) =22.5=23
100 100

o Therefor, the third quartile is the 23rd value from low end of the sorted data.

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots

o A descriptive tool
 that incorporates the median and the quartiles to graphically display data.

o Used to identify outliers that are usually small or large data values that lie
mostly by themselves.

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots

o 
o Definition:

 A graph that is composed of two parts: a box and whiskers

• The box has a width that ranges from the first quartile () to the third quartile ()

• A vertical line through the box is placed at the median.

• Limits are then located at a value that is 1.5 times the difference between and below and above

• The whiskers extend to the left to the lowest value within the limits and to the right to the

highest value within the limits.

IS 106 – QUANTITATIVE METHODS

How to?

o
1.  Sort the data values from low to high.

2. Calculate the 25th percentile (1st quartile), the 50th percentile(median), and 75th percentile(3rd
quartile).

3. Create a graph with the data values on the horizontal axis. Draw a box so the ends
correspond to and .

4. Draw a vertical line through the box at the median. Half the data values in the box will be on
either side of the median.

IS 106 – QUANTITATIVE METHODS

How to?

o
5.  Use the interquartile range () to compute for upper and lower limits.
 Lower Limit =

 Upper Limit =

 Outliers = any values outside these limits are referred to as outliers.

6. Draw the whiskers using dashed lines from each end of the box to the lowest and highest
value within the limits.

7. Plot the outliers by marking it with asterisks(*).

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

1. Sort the data values from low to high.

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

2. Calculate the 25th percentile (1st quartile), the 50th percentile (median), and
75th percentile (3rd quartile).

Q1 = 12th value Q2 = 23rd value Q3 = 34th value

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

o
3.  Create a graph and draw the box so the ends corresponds to and .

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

4. Draw a vertical line through the box at the median.

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

o
5.  Compute for upper and lower limits.
 Lower Limit =

 Upper Limit =

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

6. Draw the whiskers

IS 106 – QUANTITATIVE METHODS

Box and Whisker Plots - Example

7. Plot the outliers.

IS 106 – QUANTITATIVE METHODS

Data Level Issues

o Before using any numerical measure, we should always consider the

level of data we are using it for.
 One of the common mistake is to compute means on nominal-level data

IS 106 – QUANTITATIVE METHODS

Data Level Issues - Example

o Computing means on nominal-level data:

A major electronics manufacturer recently surveyed a sample of customers to determine

whether they preferred black, white, or colored stereo cases. The data were coded as follows:

IS 106 – QUANTITATIVE METHODS

Data Level Issues - Example

Conclusion would be:

Customers prefer a color somewhere between black and white but closer to white – meaningless.

IS 106 – QUANTITATIVE METHODS

Guide to avoid Data Level Issues

IS 106 – QUANTITATIVE METHODS

 Measures of
Variation
IS 106 – QUANTITATIVE METHODS
Consider this scenario.

o Bryce Lumber Company

 The BLC has two manufacturing facilities. The division vice president asked the two
managers to record their production output for five days (below). However, instead of
reporting the whole data set, the managers gave only the mean and median of their data.

IS 106 – QUANTITATIVE METHODS

Consider this scenario.

o Bryce Lumber Company

 Based on the statistics, the vice president concluded that

However, if we try to look at the raw data . . .

IS 106 – QUANTITATIVE METHODS

Consider this scenario.

o Bryce Lumber Company

 we can see a very big difference in

the production of the two plants opposed

to the statistics only

o The difference is the production variation from day to day:

 Plant B is very stable while Plant A varies considerably with some low or
high output days.

IS 106 – QUANTITATIVE METHODS

Measures of Variation

o Looking at a data’s center can be misleading.

o To fully describe data, we need a measure of variation or spread.

IS 106 – QUANTITATIVE METHODS

Variation

o A set of data exhibits variation if all the data are not the same value.

o Some facts:
 there will always be variation in everything made by humans or that occurs in nature –
could be small, but it is there.

 It could be

• a natural part of the process;

• or can be attributed to a special cause that is not considered random.

IS 106 – QUANTITATIVE METHODS

Measures of Variation

o There are several measures of variations, we’ll cover 4 of them:

 Range

 Interquartile Range

 Variance

 Standard Deviation

IS 106 – QUANTITATIVE METHODS

Range

o Computed by finding the difference between the maximum and minimum

values in a data set.

o The easiest to compute 

 𝑅=𝑀𝑎 𝑥𝑖𝑚𝑢𝑚 𝑉𝑎𝑙𝑢𝑒 − 𝑀𝑖𝑛𝑖𝑚𝑢𝑚 𝑉𝑎𝑙𝑢𝑒

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the data set and sort it from low to high value.

2. Determine the largest and smallest value in the data array.

3. Subtract the smallest from the largest.

IS 106 – QUANTITATIVE METHODS

Range - Example

o BLC Example Continued:

IS 106 – QUANTITATIVE METHODS

Range - Example

1. Collect the data set and sort it from low to high value

Plant A Plant B
15 23
20 24
25 25
30 26
35 27

IS 106 – QUANTITATIVE METHODS

Range - Example

2. Determine the largest and smallest value in the data array

o Plant A : 15 and 35

o Plant B : 23 and 27

IS 106 – QUANTITATIVE METHODS

Range - Example

3. Subtract the smallest from the largest.

o Therefor, plant A has a range five times as great as plant B.

IS 106 – QUANTITATIVE METHODS

Range – Disadvantage

1. Because we only use the high and low values, it is very sensitive to extreme
values.

2. Regardless of how many data values are in the sample or population, the
range is computed from only two values.

Therefor, it is a weak measure of variation.

IS 106 – QUANTITATIVE METHODS

Interquartile Range

o A measure of variation that tends to overcome the range’s susceptibility to

extreme values.

o Definition:
 A measure of variation that is determined by computing the difference between the third
and first quartiles.

 
𝐼𝑄𝑅=𝑇 h𝑖𝑟𝑑 𝑄𝑢𝑎𝑟𝑡𝑖𝑙𝑒−𝐹𝑖𝑟𝑠𝑡 𝑄𝑢𝑎𝑟𝑡𝑖𝑙𝑒
IS 106 – QUANTITATIVE METHODS
How to?

1. Sort the data into a data array from lowest to highest.

2. Compute the range.

3. Compute the first and third quartiles.

4. Compute the interquartile range.

IS 106 – QUANTITATIVE METHODS

Interquartile Range - Example

IS 106 – QUANTITATIVE METHODS

Interquartile Range - Example

1. Sort the data into a data array from lowest to highest.

IS 106 – QUANTITATIVE METHODS

Interquartile Range - Example

o 
2. Compute the range.

o Note: The range is sensitive to extreme values and that made our range very large.

IS 106 – QUANTITATIVE METHODS

Interquartile Range - Example

3. Compute the first and third quartiles.

  𝑃 25   𝑃 75
ⅈ= ( 𝑛 )= ( 100 ) =25 ⅈ= ( 𝑛 )= ( 100 ) =75
100 100 100 100

( + 178)/ 2 = 178 /2 = 220.50

IS 106 – QUANTITATIVE METHODS

Interquartile Range - Example

4. Compute the interquartile range.

o Note: The IQR would be unchanged even if the values on the high or low end of the distribution were
even more extreme.
IS 106 – QUANTITATIVE METHODS
Variance and Standard Deviation

o Both range and interquartile range does not utilize all the data available in the
computation
 Which means, there can be a lot of possible valuable information in the data that has been
ignored.

o Variance and Standard Deviation

 closely related measures that incorporates all the values from the data set.

IS 106 – QUANTITATIVE METHODS

Variance and Standard Deviation

o Standard Deviation is used as the measure of spread when the mean is used to
calculate central location – thus it measures spread around the mean.
 Stddev is small when the data is concentrated close to the mean
 Stddev is large when the data is loosely spread out of the mean

IS 106 – QUANTITATIVE METHODS

Population Variance and Standard Deviation

o Population Variance
 Average of the squared distances of the values from the mean.

Better for manual calculations

IS 106 – QUANTITATIVE METHODS

Population Variance and Standard Deviation

o Population Standard Deviation

 Is the positive square root of the variance.

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

Bryce Lumber Company

The BLC has two manufacturing facilities. The division vice president asked
the two managers to record their production output for five days (below).
However, instead of reporting the whole data set, the managers gave only the
mean and median of their data.

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

o Let’s try computing for the variance and standard deviation of the BLC
scenario

o We’ll
 use the original variance formula

 Solve for plant A

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

1. Compute the mean

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

2. Get the deviation by subtracting the mean

from each value in our data.

Summing up the deviations will always result to Zero.

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

3. Squaring the deviations and summing them up.

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

3. Compute the variance.

  250
2
𝜎 = =50
5

oThe variance is 50 products squared.

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

4. Get back the original units of measure by

computing for the standard deviation.

  2
𝜎 =√ 𝜎
𝜎 =√ 50
 

 
products

IS 106 – QUANTITATIVE METHODS

Bryce Lumber Company – Variance & Stddev

o And if we compare plant A with B,

  2   2
𝜎 =√ 𝜎 𝜎 =√ 𝜎
𝜎 =√ 50
 
𝜎 =√ 2
 

   
products products
o We can see that Plant A has a standard deviation that is five times larger than Plant B’s.

IS 106 – QUANTITATIVE METHODS

How to? (Using the shortcut variance formula)

o
1.  Collect the quantitative data for the variable of interest for the entire population.

2. Use either the original or the shortcut formula to compute for the variance

3. (Assuming we use the shortcut) Find the sum of the x-values) and then square this sum .

4. Square each x value and sum these squared values ().

5. Now, compute the variance using the formula.

6. Compute the standard deviation.

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example

1. Collect the quantitative data for the variable of interest for the entire
population.

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example

2. Select a formula.

2
  (∑ 𝑥)
2
𝛴𝑥 −
2 𝑁
𝜎 =
𝑁

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example
2
 
o
3.  Find the sum of the x-values) 2 (∑ 𝑥 )
𝛴𝑥 −
2 𝑁
𝜎 =
and then square this sum . 𝑁

IS 106 – QUANTITATIVE METHODS

 
¿
Variance & Stddev - Example

o
  2 1849
4.  Square each x value and 𝛴𝑥 −
2 𝑁
𝜎 =
sum these squared values (). 𝑁
 

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example

5. Now, compute the variance using the formula.

 
= 2.4082 weeks squared

IS 106 – QUANTITATIVE METHODS

Variance & Stddev - Example

5. Compute for the standard deviation.

  2
𝜎 =√ 𝜎 =√ 2.4082=1.5518 𝑤𝑒𝑒𝑘𝑠

Thus, the standard deviation for the number of shipping weeks between
Vancouver and London for the seven shipments is 1.5518 weeks.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Standard Deviation

o There are slight differences with the formula for sample variance and standard
deviation compared to the one we used for the population
 The notations

 The n-1 denominator

IS 106 – QUANTITATIVE METHODS

Sample Variance and Standard Deviation

IS 106 – QUANTITATIVE METHODS

Sample Variance and Standard Deviation

o
o  The general reason for having (n-1) is that we want the average sample variance
to equal the population variation.
o Suppose we computed the variance of 5 samples from a population

o The average for these 5 sample variance () will be equal to the population variance IF

we use the n-1 divisor.

o If we use the n, we will get a value lesser than the population variance.

IS 106 – QUANTITATIVE METHODS

How to?

o
1.  Select the sample and record the data for the variable of interest.

2. Select a formula for variance.

3. Compute .

4. (Assuming we use the original formula) Determine the sum of the squared deviations of each x value

from .

5. Compute the sample variance using the selected formula.

6. Compute the sample standard deviations.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example

1. Select the sample and record the data for the variable of interest.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example

2. Select a formula to compute the variance.

𝑛
  2
∑ ( 𝑥𝑖 − 𝑥
´)
2 𝑖=1
𝑠 =
𝑛 −1

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example
𝑛
 
3. Compute for the sample mean. ∑ ( 𝑥 𝑖 − ´𝑥 )2
2 𝑖=1
𝑠 =
𝑛 −1

 
∑ 𝑥 30
´𝑥 = = =3.0
𝑛 10

The average number of defectives is 3.0.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example
𝑛
  ∑ ( 𝑥 𝑖 − 3.0 )2
𝑠 2= 𝑖=1
𝑛 −1
4. Determine the sum of the squared deviations.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example

5. We can now compute the variance.

The sample variance is 6 defectives squared.

IS 106 – QUANTITATIVE METHODS

Sample Variance and Stddev - Example

6. Compute the sample standard deviations.

 
2
𝑠= √ 𝑠 =6=2.4495

The sample deviation for number of defects per sample is 2.4495.

IS 106 – QUANTITATIVE METHODS

 Using the mean and
standard deviation together

IS 106 – QUANTITATIVE METHODS

Mean and Standard Deviation – 2gether

o Two of the most important measures that we’ve talked about is the
 mean

 standard deviation.

o There are several statistical tools that combine these two

IS 106 – QUANTITATIVE METHODS

Mean and Standard Deviation – 2gether

o Standard Deviation

 measures the variation or spread in a set of data

o For distributions having the same mean

 the distribution having the largest stddev has the greatest relative spread

o For distributions having different means

 the relative spread cannot be determined by merely comparing the standard
deviations

IS 106 – QUANTITATIVE METHODS

Coefficient of a Variation

oThe ratio of the standard deviation to the mean expressed as a percentage.

o Used to measure variation relative to the mean

 specifically for distributions with different means.

IS 106 – QUANTITATIVE METHODS

Coefficient of a Variation

IS 106 – QUANTITATIVE METHODS

Coefficient of a Variation

o By comparing the coefficients of variation for two or more distributions,

 the distribution with the largest CV is said to have the greatest relative
spread

IS 106 – QUANTITATIVE METHODS

Coefficient of a Variation

o In finance, the CV can be used to measure the relative risk of a stock portfolio.

o Assume portfolio A has

 Has an average return of 12%

 Standard deviation of 3%

o Assume portfolio B has

 Has an average return of 6%

 Standard deviation of 2%

IS 106 – QUANTITATIVE METHODS

Coefficient of a Variation

o
o  We can compute the CV as follows:


o Even though portfolio B has a lower stddev, it is still riskier than A because it
has greater CV.

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the sample (or population) data of interest.

2. Compute the mean and the standard deviation.

3. Compute the CV.

IS 106 – QUANTITATIVE METHODS

Standardized Data Values (Z Scores)

o The number of standard deviations a value is from the mean.

o Useful for comparing data from two or more distributions

 when the data scales for the two distributions are different.

IS 106 – QUANTITATIVE METHODS

Standardized Data Values (Z Scores)

IS 106 – QUANTITATIVE METHODS

How to?

1. Collect the population or sample values for the quantitative variable of

interest.

2. Compute the mean and standard deviation (population or sample).

3. Convert the values to standardize z-values..

IS 106 – QUANTITATIVE METHODS

Z Scores - Example

IS 106 – QUANTITATIVE METHODS

Z Scores - Example

1. Collect the population or sample values for the quantitative variable of

interest.

The Human Resource will collect the scores from the applicants who applied
using these two tests.

IS 106 – QUANTITATIVE METHODS

Z Scores - Example

2. Compute the mean and standard deviation (population or sample).

Assuming these data reflect the population of interest for the university, the population mean
can be computed using:

 AIMS:  BHS:

The standard deviation is computed using:

AIMS = 200 BHS = 12

IS 106 – QUANTITATIVE METHODS
Z Scores - Example

3. Convert the values to standardize z-values..

AIMS BHS
John’s Score of 2344 converts to Mary’s Score of 95 converts to

  𝑥 − 𝜇 2344 − 2000   𝑥−𝜇 95− 80

𝑧= = =1.72 𝑧= = =1.25
𝜎 200 𝜎 12

IS 106 – QUANTITATIVE METHODS

Z Scores - Example

Conclusion:

1. Compared to the average score on the AIMS Hiring Test, John’s score is 1.72 standard deviations higher.

2. Compared to the average score on the BHS Hiring Test, Mary’s score is only 1.25 standard deviations
higher.

Therefor, even though the two tests used different scales, standardizing the data allowed us
to see that John scored relatively better than Mary.

IS 106 – QUANTITATIVE METHODS