Index Numbers

20.1 Introduction
• An index number is a statistical value that measures the change in a
variable with respect to time
• Two variables that are often considered in this analysis are price and
quantity
• With the aid of index numbers, the average price of several articles in
one year may be compared with the average price of the same
quantity of the same articles in a number of different years
• There are several sources of ‘official’ statistics that contain index
numbers for quantities such as food prices, clothing prices, housing,
wages and so on
 20.2 Simple index numbers
• We will examine index numbers that are constructed from a single item
only
• Such indexes are called simple index numbers
• Current period = the period for which you wish to find the index number
• Base period = the period with which you wish to compare prices in the
current period
• The choice of the base period should be considered very carefully
• The choice itself often depends on economic factors
1. It should be a ‘normal’ period with respect to the relevant index
2. It should not be chosen too far in the past
 20.2 Simple index numbers (cont…)

• The notation we shall use is:

– pn = the price of an item in the current period
– po = the price of an item in the base period

• Price relative

– The price relative of an item is the

ratio of the price of the item in the
current period to the price of the
same item in the base period
– The formal definition is:
pn
Price relative 
po
 20.2 Simple index numbers
(cont…)
• Simple price index
– The price relative provides a ratio
that indicates the change in price
of an item from one period to
another
– A more common method of
expressing this change is to use a
simple price index
– The formal
Simple definition
price index is:  100
 price relative
pn
  100
po
 20.2 Simple index numbers (cont…)

• The simple price index finds the percentage change in the price of an item from one
period to another

– If the simple price index is more than 100, subtract 100 from the simple price
index. The result is the percentage increase in price from the base period to the
current period

– If the simple price index is less than 100, subtract the simple price index from 100.
The result is the percentage by which the item cost less in the base period than it
does in the current period
 20.3 Composite index numbers

• A composite index number is constructed from changes in a

number of different items

• Simple aggregate index

– the simple aggregate index has appeal because its nature is simplistic and it
is easy to find
– The formal definition is:

Where
Spn = the sum of the prices in the current period
Spo = the sum of the prices in the base period
Simple aggregateindex 
pn
 100

po 
 20.3 Composite index numbers
(cont…)
• Simple aggregate index (cont…)

– Even though the simple aggregate index

is easy to calculate, it has serious
disadvantages:
1. An item with a relatively large price can dominate the index
2. If prices are quoted for different quantities, the simple aggregate index will yield a different answer
3. It does not take into account the quantity of each item sold

– Disadvantage 2 is perhaps the worst

feature of this index, since it makes it
possible, to a certain extent, to
manipulate the value of the index
 20.3 Composite index numbers (cont…)

• Averages of relative prices

– This index also does not take into account the quantity of each item sold,
but it is still a vast improvement on the simple aggregate index
– The formal definition is:

 pn 
  p o
 100 

Average of relative prices 
k

where
k = the number of items
pn = the price of an item in the current period
po = the price of an item in the base period
 20.4 Weighted
numbers
• The use of a weighted index number or weighted index allows greater impo
• Information other than simply the change in price over time can then be u
sold or quantity consumed for each item

• Laspeyres index
20.4 Weighted index numbers (cont…)

– The formula is:

Laspeyres index 
p q
n o
 100
p q
o o

Where:
qo =the quantity bought (or sold) in the base period

pn = price in current period

po = price in base period

– Thus, the Laspeyres index measures the relative change in the cost of
purchasing these items in the quantities specified in the base period
 20.4 Weighted index numbers (cont…)
• Paasche index

– The Paasche index uses the consumption in

the current period
– It measures the change in the cost of
purchasing items, in terms of quantities
relating to the current period
– The formal definition
Paasche index 
ofpnthe
qn Paasche index is:
 100
p q o n

Where:
pn = the price in the current period
po = the price in the base period
qn = the quantity bought (or sold) in the current period
 20.4 Weighted
numbers (con
• Comparison of the Laspeyres and Paasche indexes

– The Laspeyres index measur

expenditures on base year q
 20.4 Weighted
numbers (con
• Comparison of the Laspeyres and Paasche indexes (cont…)

– Since the Paasche index u

 20.4 Weighted index numbers (cont…)

• Fisher’s ideal index

– Fisher’s ideal index is the geometric

mean of the Laspeyres and Paasche
indexes
– Although it has little use in practice, it
Fisher' s index  Laspeyres index Paasche index 
does demonstrate the many different
 pnqothat
types of index  pnqcan
n
be used
 100
 p o o o n
q p
– The formal definition is:
q
 20.5 The Consum
• The measure most commonly used in Australia as a general indicator of the rate of price change for
consumer goods and services is the consumer price index

• The Australian CPI assumes the purchase of a constant ‘basket’ of goods and services and measures
price changes in that basket alone

– a measure of Index (CPI

• The description of the CPI commonly adopted by users is in terms of its perceived uses; hence there are
frequent references to the CPI as

inflation
– a measure of changes in
purchasing power, or
– a measure of changes in the cost
of living
 20.5 The Consum
• The CPI has been designed as a general measure of price inflation for the household sector.
• The CPI is simply a measure of the changes in the cost of a basket, as the prices of items in it change
• From the September quarter 2005 onwards, the total basket has been divided into the following 11 major commodity groups:

– food
– alcohol and tobacco
– clothing and footwear

Index (CPI) (co

– housing
– household contents and services
– health
– transportation
– communication
– research
– education
– financial and insurance services
 20.5 The Consum
Index (CPI) (co
• Historical details of the CPI

– Retail prices of food, other g

average rentals of houses ha
 20.5 The Consum
Index (CPI) (co
• The conceptual basis for measuring price changes

– The CPI is a quarterly mea

change in average retail pr
 20.5 The Consum
Index (CPI) (co
• The index population

– Because the spending patte

groups in the population di
 20.5 The Consum
Index (CPI) (co
• Details of the 15th series CPI

– Since 1960, when the CP

compiled, the ABS has m
 20.5 The Consum
• Collecting prices

– This involves collecting prices from many sources, including

supermarkets, department stores, footwear stores,
restaurants, motor vehicle dealers and service stations,
dental surgeries, etc.

Index (CPI) (co

– In total, around 100 000 separate price quotations are
collected each quarter
– Prices of the goods and services included in the CPI are
generally collected quarterly
– The prices used in the CPI are those that any member of the
public would have to pay on the pricing day to purchase the
specified good or service
– Any sales or excise taxes that the consumer must pay when
purchasing specific items are included in the CPI price
 20.5 The Consum
• Periodic revision of the CPI

– The CPI is periodically revised in order to ensure it

continues to reflect current conditions

Index (CPI) (co

– CPI revisions have usually been carried out at
approximately 5-yearly intervals

• Changes in quality

– it is necessary to ensure that identical or equivalent

items are priced in successive time periods
– This involves evaluating changes in the quality of
goods and services
 20.5 The Consum
Index (CPI) (co
• Long-term linked series

– A single series of index num

constructed by linking toge
 20.6 Using th

• There are a number of situ

the CPI is used to make adj
20.7 Index numbers as a measure of deflation

• One of the uses for price indexes is to measure the changes in

the purchasing power of the dollar
• This is known as deflation
• In order to eliminate the effect of inflation and obtain a clear
picture of the ‘real’ change, the values must be deflated
• For example, to deflate an actual salary and express it in terms
of ‘real’ salary (of the base year), use:

CPI in base year

' Real' salary  actual salary in current year
CPI in current year
 20.8 Other typ
• Producer price indexes
– Several producer price indexes (PPIs) are
produced and published

Australian ind
– PPIs can be constructed as either output
measures or input measures

– Output indexes measure change in the prices

of goods and/or services sold by a defined
sector of the economy

– Input indexes measure changes in the prices

of goods and/or services purchased by a
particular economic sector
 20.8 Other typ
Australian indexes
• International trade price indexes
– The international trade price indexes are intended to br
of goods imported into Australia (the export price index

– As the prices used in the indexes are expressed in Austr

relative value of the Australian dollar and overseas curr
 20.8 Other typ
Australian indexes
• The All-Ordinaries index
– The All-Ordinaries index (also know as the ‘All-Ords’) is an Australia
share-price movements of the largest 500 Australian companies
– The market capitalisation of these companies totals about 95% of t
 Summary

• We have interpreted an
range of index numbers
In today’s lecture

Introduction and definitions

Three ways to measure probability

Laws of probability
 Introduction

Probability is the language we use to model uncertainty.

We all intuitively understand that few things in life are certain.

There is usually an element of uncertainty or randomness around
outcomes of our choices.

In business this uncertainty can make all the difference between a

good investment and a poor one.

Hence, an understanding of probability and how we might

incorporate this into our decision-making processes is important.
 Definitions

We often use the letter P to represent a probability.

For example, P(Rain) would be the probability that it rains.

An Experiment is an activity where we do not know for certain

what will happen, but we can observe what happens. For
example:
We will ask someone whether or not they have used our
product.
We will observe the temperature at midday tomorrow.
We will toss a coin and observe whether it shows “heads” or
“tails”.
 An Outcome is one of the possible things that can happen.

For example, suppose that we are interested in the shoe size of the
next customer to come into a shoe shop.
Possible outcomes include:
“eight”
“twelve”
“nine and a half”
In any experiment, one, and only one, outcome occurs.

The Sample space is the set of all possible outcomes. For

example, it could be the set of all shoe sizes.

An Event is a set of outcomes. For example “the shoe size of the

next customer is less than 9” is an event. It is made up of all of
the outcomes where the shoe size is less than 9.
More stuff...

Probabilities are usually expressed in terms of fractions, decimals

or percentages.

Therefore we could express the probability of it raining today as

1
P(Rain) =
20=0.05=5%.

All probabilities are measured on a scale from zero to one.

- An impossible event has a probability of zero
- A certain event has a probability of one
- Can you imagine where abouts on this scale a likely event will
lie? Or an extremely unlikely event?
The collection of all possible outcomes - the sample space - has
a probability of 1.
For example:
- Suppose an experiment has only two outcomes - success or
failure
- Then P(success or failure)

=1
- Suppose we have a fair six-sided die
Another example:
- Then P(1 or 2 or 3 or 4 or 5 or 6) = 1
 Two events are said to be mutually exclusive if both can not
occur simultaneously. In the example above, the outcomes success
and failure are mutually exclusive.

Two events are said to be independent if the occurrence of one

does not affect the probability of the second occurring.

For example, if you toss a coin and look out of the window, the
events “get heads” and “it is raining” would be independent.
 An example of non-independence
Imagine I go into the Student’s Union and pick a student at
random.
I’m interested in the probability that they are studying engineering.
If the student I pick is female does this alter the probability that
they are studying engineering? Is it more or less likely?

The events “the student is female” and “the student is

studying engineering” are not independent.

There is a smaller proportion of female students on engineering

courses than on other courses at the University!
How do we measure probability?

There are three main ways in which we can measure probability:

- Classical
- Frequentist
- Subjective
All three obey the basic rules described so far.

Different people argue in favour of the different views of probability

and some will argue that each kind has its uses depending on the
circumstances.
Classical probability

This view is based on the concept of equally likely events.

If we toss a fair coin, we have two possible outcomes - Heads or

Tails. Both outcomes are equally likely. Thus

P(Head ) =1 and P(Tail ) =1

2 2
 Another commonly used example is rolling dice.

There are six possible outcomes - {1, 2, 3, 4, 5, 6} - if the die is

fair, each of them should have an equal chance of occurring.

Hence P(1) =16,P(2)=6,

What about other calculations, such as P(Even Number)?

P(Even Number) =3
6=2.
This follows from the formula

P(Event) =Totalnumberofoutcomesinwhicheventoccurs
Total number of possible outcomes
Frequentist probability

When the outcomes of an experiment are not equally likely, we can

conduct experiments to give us an idea of how likely the different
outcomes are.

Examples
- Probability of producing a defective item in a manufacturing
process
We could monitor the process over a long period of time
The probability of a defective item could be measured by the
proportion of defectives in our sample
- Imagine we believed a coin was unfair
Toss the coin a large number of times
See how many heads you obtain, and express P(Head ) as a
proportion
By conducting experiments the probability of an event can easily
be estimated using the following formula:

Number of times an event occurs

P(Event) =
Total number of times experiment performed.
 The larger the experiment, the closer this probability is to the
“true” probability.

The frequentist view of probability regards probability as the long

run relative frequency (or proportion).

In the defects example, the “true” probability of getting a defective

item is the proportion obtained in a very large experiment (strictly
an infinitely long sequence of trials).
 In the frequentist view, probability is a property of nature.

In practice we cannot conduct infinite sequences of trials, and so

we never know the “true” values of probabilities.

We also have to be able to imagine a long sequence of “identical”

trials.

This does not seem to be appropriate for “one-off” experiments

like the launch of a new product.
Subjective/Bayesian Probability

We are probably all intuitively familiar with this method of

assigning probabilities:
- When we board an aeroplane, we judge the probability of it
crashing to be sufficiently small that we are happy to
undertake the journey
- The odds given by bookmakers on a football match reflect
people’s beliefs about which team will win

This view of probability does not fit within the frequentist

definition as the match cannot be played a large number of times.
 Such ways of thinking about probabilities are subjective.

This in itself, some think, is a problem - probabilities which two

people assign to the same event can be (very) different.

This becomes important if these probabilities are to be used in

decision making.
 LAWS OF
PROBABILITY
Multiplication law

The probability of two independent events E1 and E2 both

occurring is
P(E1 and E2) = P(E1) × P(E2).

For example, the probability of throwing a six followed by another

six on two rolls of a die is calculated as follows:
- The outcomes of the two rolls of the die are independent
- Let E1 denote a six on the first roll and E2 a six on the second
roll
- P(two sixes) = P(E1 and E2) = P(E1) × P(E2) = 1 6 ×6
36
This is the multiplication rule of probability.
This method of calculating probabilities extends to when there are
many independent events:

P(E1 and E2 and · · · and En) = P(E1) × P(E2) × · · · × P(En).

There is a more complicated rule for multiplying probabilities when

the events are not independent, and we will see this next week.
Addition law

The addition law describes the probability of any of two or more

events occurring.

The addition law for two events E1 and E2 is

P(E1 or E2) = P(E1) + P(E2)−P(E1 and E2).

This describes the probability of either event E1 or event E2

happening.
 Example

50% of families in a certain city subscribe to the morning

newspaper,
65% subscribe to the afternoon newspaper,
and 30% of the families subscribe to both newspapers.
What proportion of families subscribe to at least one
newspaper?

We are told that

- P(Morning) = 0.5
- P(Afternoon) = 0.65 and
- P(Morningand Afternoon)=0.3
 Recall the addition law for two events E1 and E2 is

P(E1 or E2) = P(E1) + P(E2) − P(E1 and E2).

Therefore

P(at least one paper) = P(Morning or Afternoon)

= P(Morning) + P(Afternoon)
− P(Morning and
Afternoon)
= 0.85.
= 0.5 + 0.65 − 0.3

So 85% of the city subscribe to at least one of the newspapers.

A more basic version of the rule works where events are mutually
exclusive.

If events E1 and E2 are mutually exclusive then

P(E1 or E2) = P(E1) + P(E2).

This simplification occurs because when two events are mutually

exclusive they cannot happen together and so P(E 1 and E2) = 0.

These two laws are the basis of more complicated problem solving
we will see later.
 Lecture 5

CONDITIONAL PROBABILITY
 Introduction

In this chapter, we look at more complicated notions of probability,

and extend the multiplication rule for probability to cater for
events that are not independent.
So far we have only considered probabilities of single events or of
several independent events, like two rolls of a die.
For example, on two rolls of a fair, six-sided die, the probability
that I roll two sixes is

P(two sixes) = P(six and six)

= P(six) × P(six)
1
=
6×6
1
=
36.
 However, in reality, many events are related. For example, the
probability of it raining in 5 minutes time is dependent on whether
or not it is raining now.

We need a mathematical notation to capture how the probability

of one event depends on other events taking place.
We do this as follows:
 Consider two events A and B. We write

P(A|B)

for the probability of A given that B has already happened.

We describe P(A|B) as the conditional probability of A given B.

For example, the probability of it raining in 5 minutes time given

that it is raining now would be

P(Rain in 5 minutes|Raining now).

 Example

Utility companies need to be able to forecast periods of high

demand. They describe their forecasts in terms of probabilities.

Gas and electricity suppliers might relate them to air temperature.

For example,

P(High demand|air temperature is below normal) = 0.6

P(High demand|air temperature is normal) = 0.2
P(High demand|air temperature is above normal) = 0.05.
We can calculate these conditional probabilities using the formula

P(A|B) =P(AandB),
P(B)

that is, in terms of the probability of both events occurring,

P(A and B), and the probability of the event that has already
taken place, P(B).

To see how this formula works, let’s consider a simple example

based on the class of students in Exercises 4 (p.55).
 Height Weight Shoe Height Weight Shoe
Sex (m) (kg) Size Sex (m) (kg) Size
M 1.91 70 11.0 M 1.78 76 8.5
F 1.73 89 6.5 M 1.88 64 9.0
M 1.73 73 7.0 M 1.88 83 9.0
M 1.63 54 8.0 M 1.70 55 8.0
F 1.73 58 6.5 M 1.76 57 8.0
M 1.70 60 8.0 M 1.78 60 8.0
M 1.82 76 10.0 F 1.52 45 3.5
M 1.67 54 7.5 M 1.80 67 7.5
F 1.55 47 4.0 M 1.92 83 12.0

Suppose we want the probability that a student chosen at random

from this class will be female given that the student’s shoe size
is less than 8.

P(Female|Shoe size less than 8) =4

7.
 P(A|B) =P(AandB),
P(B)

This probability can also be calculated using the above formula as

follows:
7
P(Shoe size < 8) =
18

4
P(Shoe size < 8 and 18
female) =

P(Female|Shoe
and so size < 8) = P(Shoesize<8andfemale)
P(Shoe size < 8)
4/18
=
7/18
4
=
7.
Multiplication of probabilities

We saw in Chapter 4 that, if two events A and B are

independent, then

P(A and B) = P(A) × P(B).

Now we know that

P(A|B) =P(AandB),
P(B)
we can easily see that

P(A and B) = P(B) × P(A|B).

Of course it is also true that P(A and B) = P(A) × P(B|A).

 For example, consider a student chosen at random from the
example class.
Let F be the event “the student is female”
Let S be the event “the student’s weight is less than
60kg”
Then the probability that the student is female and has a weight
less than 60kg is

P(F and S ) = P(S) × P(F|S) =7

18×7 18

= P(F) × P(S|F) =4
18×4 18.
 Notice that, if M is the event “the student is male”, then

P(S |M) = 4/14

= 0.286

and this is not equal to P(S |F ) = 3/4 = 0.75.

So the probability of the student having a weight less than 60kg

depends on the student’s sex. The events S and F are not
independent.

Similarly, P(F |S ) = 3/7 = 0.429 while P(F |L) = 1/11 = 0.091,

where L is the event “the student’s weight is not less than
60kg”.
 LetB be the event “not B”.

So, for example,F = M.

Then we say that two events A and B are independent if

P(A|B) = P(A|B) = P(A).

It is easy to show that this is equivalent to

P(B|A) = P(B|A) = P(B).

If A and B are independent, then

P(A and B) = P(A)×P(B).

Example 1
For example, consider the following probabilities for customers at a
cafe who can choose either ice cream or treacle sponge:

Ice cream Treacle sponge

Male 0.250 0.150
Female 0.375 0.225

We see that

P(male) = 0.250 + 0.150

= 0.4,

and

P(female) = 0.375 + 0.225

= 0.6
= 1−P(male).
Now
P(Ice cream|Male)
0.4 =0.250= 0.625
and
P(Ice cream|Female)
0.6 =0.375= 0.625,
so Ice cream and Male are independent events.

In fact, the variables Sex and Dessert-choice are independent in

this example.

So the probability that a customer is male and chooses ice cream is

just

P(Male) × P(Ice cream) = 0.4 × 0.625

= 0.25
Example 2
Another example relates to the age and sex distribution of
purchasers of CDs at a music store:
under 30 30 to 50 over 50
Male 0.275 0.125 0.025
Female 0.325 0.175 0.075
From this table, we can calculate
P(Male) = P(Male and under 30) + P(Male and 30 to 50)
+ P(Male and over 50)
= 0.275 + 0.125 + 0.025 = 0.425
and
P(Female) = P(Female and under 30) + P(Female and 30 to 50)
+ P(Female and over 50)
= 0.325 + 0.175 + 0.075 = 0.575.
 under 30 30 to 50 over 50
Male 0.275 0.125 0.025
Female 0.325 0.175 0.075

Also, the age distribution of the customers is:

P(under 30) = P(Male and under 30) + P(Female and under 30)
= 0.275 + 0.325 = 0.6
P(30 to 50) = P(Male and 30 to 50) + P(Female and 30 to 50)
= 0.125 + 0.175 = 0.3
P(over 50) = P(Male and over 50) + P(Female and over 50)
= 0.025 + 0.075 = 0.1.
 under 30 30 to 50 over 50
Male 0.275 0.125 0.025
Female 0.325 0.175 0.075

Using this information we can calculate various probabilities such

as:

P(Male|30 to 50) =P(Maleand30to50) =0.125= 0.4167

P(30 to 50) 0.3
P(Female|30 to 50) = 1 − P(Male|30 to 50) = 1 − 0.4167 = 0.5833
 under 30 30 to 50 over 50
Male 0.275 0.125 0.025
Female 0.325 0.175 0.075

and
P(under 30|Male) =P(Maleandunder30) =0.275
P(Male) 0.425=0.6471

P(30 to 50|Male) =P(Maleand30to50) =0.125

P(Male) 0.425=0.2941

P(over 50|Male) = 1 − P(under 30|Male) − P(30 to 50|Male)

=1−0.6471−0.2941=0.0588.
Tree Diagrams

Tree diagrams or probability trees are simple ways of presenting

probabilistic information.

Let us first consider a simple example in which a fair coin is tossed

twice.

Suppose we are interested in the probability that we get a head on

both tosses.
This probability can be calculated as

P(Head and Head) = P(Head on 1st) × P(Head on 2nd|Head on 1st)

=1
2
×2
4.
=1
This example can be represented as a tree diagram in which
experiments are represented by circles (called nodes) and the
outcomes of the experiments as branches.

The branches are annotated by the probability of the particular

outcome.
0.25
Head
0.5

Head 0.5
0.5 Tail 0.25

0.5 Head 0.25

Tail 0.5

0.5
Tail
0.25
 Head 0.25
0.5

Head 0.5
0.5 Tail 0.25

0.5 Head 0.25

Tail 0.5

0.5
Tail
0.25

Here the probability of a Head followed by a Head is found by

tracing the branch corresponding to this outcome through the tree
and multiplying the corresponding probabilities together;
0.5 × 0.5 = 0.25.

Note that the ends of the branches of the tree are usually known
as terminal nodes. The probabilities at the terminal nodes should
add up to 1.