TIME SERIES ANALYSIS

&
INDEX NUMBERS

UNIT-II
 Meaning of Time
Series

Statistical data which is recorded with its time of occurrence is

called a time series.

The yearly output of wheat recorded for the last twenty five
years, the weekly average price of eggs recorded for the last
52 weeks, the monthly average sales of a firm recorded for
the last 48 months or the quarterly average profits recorded
for the last 40 quarters etc., are examples of time series data.
 Applications in Business
decision making

• Analysis of past behavior

• Forecasting
• Comparative study
• Evaluation of performance
• Estimation of trade cycles
 Components of a
Time series
Original Data( O or Y)

Long-term Movement Short-time Fluctuations

or ( O-T )
Trend
Or secular Trend Regular Short-time Irregular or
( T) Fluctuations( S+ C) Random Fluctuations

Seasonal Variations( S) Cyclical Fluctuations (C)

 1. Secular Trend or
Long-term Movement or Trend

• According to Simpson and Kafka “ Trend also called

secular or long term trend, is the basic tendency of
production, sales, income, employment, or the like to
grow or decline over a period of time. Some important
characteristics are:

• Three aspects
• Different trends during different periods
• Relative concept
 2. Regular Short-Time
Oscillations
Most of the time series are influenced by such factors or
forces which repeat themselves periodically. The
variations arising out on account of such regular or
periodical repetitions are called regular short-time
oscillations, which may be classified into the following
two categories:
a) Seasonal variations
b) Cyclical Fluctuations
 3. Irregular or Random
Fluctuations

A type of variation in time series that reflects the random

variation of the time series values which is completely
unpredictable. For ex. Floods, earthquakes etc.
 Time series decomposition
models

The purpose of decomposition models is to break a time

series into its components:
Trend(T), Cyclical(C), Seasonality(S), and Irregularity(I).
Decomposition of time series aims to isolate influence of
each of the four components on the actual series so as
to provide a basis for forecasting.
 1. Multiplicative Model

The actual values of a time series , represented can be

found by multiplying four components at a particular
period. The effect of the four components on time
series is interdependent. The multiciplicative time
series model is defined as:
Y= TxCxSxI
 2. Additive Model

It is assumed that the effect of various components can

be estimated by adding the various components of a
time series. It is stated as
Y= T +C+S+I
Here C, S and I are absolute quantities and can have
positive or negative values. It is assumed that these
four components are independent of each other.
 Measurement of Trend

The following are the important methods which are used

in estimating the trend: Linear trend and non-linear
trend
Linear trend
1. Free hand curve or Graphic method
2. Semi-averages method
3. Method of least squares
 1. Free hand curve or
Graphic method
This is the simplest method of studying trend. Under this
method, the given data are plotted on a graph paper
and a trend line is fitted to the data just by inspecting
the graph of the series.
 2. Semi-averages method

When this method is used the given data are divided into
two parts, preferably, with the equal no. of years.

After the data have been divided into two equal parts, an
average of each part is obtained. We thus get two
points. Each point is plotted at the mid point of the
class interval covered by the respective part and then
the two points are joined by a straight line which gives
us the required trend line. The line can be extended
downwards or upwards to get intermediate values or to
predict future values.
 3. Method of least squares

This method is most widely used in practice. When this

method is applied, a trend line is fitted to the data in such
a manner that the following two conditions are satisfied:
(i) The sum of deviations of the actual values of Y and the
computed values of Y is zero.
(ii) The sum of the squares of deviations of the actual and
the computed values is least from this line.
That is why this method is called the method of Least
Squares. The line obtained by this method is known
as the line of ‘ best fit’.
 NON-LINEAR TREND

The following are the methods of measuring non-linear

trends:
1. Freehand or Graphic Method
2. Moving Average Method
3. Weighted moving average method
 Moving Average Method

When a trend is to be determined by this method, the

average value for a no. of years(or months, or weeks) is
secured, and this average is taken as the normal or
trend value for the unit of time falling at the middle of
the period covered in the calculation of the average.
The effect of averaging is to give a smoother curve,
lessening the influence of the fluctuations that pull the
annual figures away fro the general trend.
The formula for 3- yearly moving average will be:
(a+b+c)/3, (b+c+d)/3, (c+d+e)/3, (d+e+f)/3……………
 Forecasting using Moving Averages
and Exponential Smoothing

• Moving Averages- the method of moving averages

attempts to forecast values on the basis of the average of values
of the past few periods. Successive values of moving averages
are calculated, by taking average of the values of a certain no. of
periods by including the latest value and dropping the oldest
one. The moving average values are used as forecast.

• For ex. When 3-period moving averages are calculated then the
first value obtained serves as a forecast for the period 4; the
second one is a forecast for the period 5 and so on.
 Previous years questions of Time-
Series
• What is time series? Explain the various components of
time series. Also give the importance of time series.
• What effect does seasonal variability have on a time-
series? What is the basis for this variability for an
economic time-series?
• What are the components of time Series? How would you
find out the trend values in a time series by the method of
least squares?
• Fit a straight line trend by the method of least squares to
the following data: -
Year : 2012 2013 2014 2015 2016 2017
Sales of T.V. sets (in’000): 7 10 12 14 17
24
18
Q. A food processor uses a moving average to forecast
next month’s demand. Past actual demand(in units) is
shown below:
Month 43 44 45 46 47 48 49 50 51
Actual Demand (in
Units) 105 106 110 110 114 121 130 128 137

• Compute a simple five-month moving average to forecast

demand for month 52.
• Compute a weighted three-month moving average where the
weights are highest for the latest months and descend in
order of 3, , 1.

19
 Index
Number
 Index number

An index number can be defined as a relative measure

describing the averages changes in any quantity over
time. In other words, an index number measures the
changing value of prices, quantities, or values over a
period of time in relation to its value at some fixed
point in time, called the base period.
It has no unit and is always expressed as a percentage
term as follows:
Index number = (Current period value/ Base period
value) x 100
• For example. Suppose the price of a certain product doubles relative to
a year. As a result of this, the index of price would rise. So an index
number can be with respect to a variable such as a price and
demonstrates the change in that variable in present relative to a base
year.

• An index number is not an absolute measure, it measures the

percentage change in a variable over time. It does so by comparing
the value of a variable at present to its value at a base year.

• Index number gives a quantitative foundation to qualitative statements

like prices are falling or rising.

• index numbers show changes in average. In effect, it means if the

average change is 5% then some goods might not change exactly at 5%.
 Types of Index Numbers

Index no. are broadly classified into three main

categories:
(i) Price indexes,
(ii) quantity indexes
(iii) value indexes
 Price indexes
These index are of two types:
i. Single price index
ii. Composite price Index

The single price index measures the percentage change in the

current price per unit of a product to its base period price.

A composite price index measures the average price change for

a basket of related items from abase period to the current
period. For ex. The WPI reflects the general price level for a
group of items taken as a whole.
 (ii) quantity indexes

A quantity index measures the relative change in

quantity levels of a group of items consumed or
produced such as agricultural and industrial production,
imports and exports, between two time periods.
The two most common quantity indexes are the
weighted relative of aggregates and the weighted
average of quantity relative index.
 (iii) value indexes

A value index measures the relative changes in total

monetary worth of an item, such as inventories, sales,
or foreign trade, between the current and base periods.
 Characteristics of index
(1) Expressed in numbers
Following are the important characteristics of index numbers.
● A change in terms of the absolute values
percentage may not be comparable.
● Index numbers are expressed in
percentage, so they remove this barrier.
Although, we do not use the percentage sign.
● It is possible to compare the agricultural
production and industrial production and at
the same time being expressed in percentage,
we can also compare the change in prices of
different commodities.

(2) Relative measures or measures of ● Index numbers measure a net or relative

net changes change in a variable or a group of variables.
● For example, if the price of a certain
commodity rises from ₹10 in the year 2007 to
₹15 in the year 2017, the price index number
will be 150 showing that there is a 50%
increase in the prices over this period.
(3) Measure change over a ● Index numbers measure the net change among the
related variables over a period of time or at two or more
period of time or in two or places.
more places ● For example, change in prices, production, and
more, over the two periods or at two places.

(4) Specialised average ● Simple averages like, mean, median, mode, and more
can be used to compare the variables having similar
units.
● Index numbers are specialised average, expressed in
percentage, and help in measuring and comparing the
change in those variables that are expressed in different
units.
● For example, we can compare the change in the
production of industrial goods and agricultural goods.

(5) Measuring changes that ● Cost of living, business activity, and more are complex
things that are not directly measurable.
are not directly measurable ● With the help of index numbers, it is possible to
study the relative changes in such phenomena.

28
 USES OF INDEX
NUMBERS
We have known the features and types of the Index numbers. For a further
comprehensive study, we will now discuss the uses of Index numbers.
• Index numbers are useful in many basic to complicated studies. Like it is
used in the basic study of human population in a country and also it is used
to determine the extinction rate of the rare animals in a particular region.
There are many more usages of Index Numbers, let us find out:
• It helps in measuring changes in the standard of living as well as the price
level.
• Wage rate regulation is consistent with the changes in the price level. With
the determination of price levels, wage rates may be revised.
• Government policies are framed following the index number of prices. This
price stability inherent to fiscal and economic policies is based on index
numbers.
• It gives a pointer for international comparison concerning different
economic variables—for instance, living standards between two countries.
 Advantages of Index Number
Index numbers are one of the most widely used statistical tools. Some of the
advantages or uses of index numbers are as follows:
(1) Help in formulating policies ● Most of the economic and business decisions
and policies are guided by the index numbers.
● Example:
● To increase DA, the government refers to the
cost-of-living index.
● To make any policy related to the industrial or
agricultural production, the government refers to
their respective index numbers.
(2) Help in study of trends ● Index numbers help in the study of trends in
variables like, export-import, industrial and
agricultural production, share prices, and more.
(3) Helpful in forecasting ● Index numbers not only help in the study of
past and present behaviour, they are also used for
forecasting economic and business activities.

30
(4) Facilitates comparative study ● To make comparisons with respect to time
and place especially where units are different,
index numbers prove to be very useful.
● For example, change in ‘industrial
production’ can be compared with change in
‘agricultural production’ with the help of index
numbers.

(5) Measurement of purchasing ● Index numbers, such as cost inflation index

power of money to maintain help in measuring the purchasing power of
standard of living money at different times between different
regions.
● Such analysis helps the government to
frame suitable policies for maintaining or raising
the standard of living of the people.

(6) Act as economic barometer ● Index numbers are very useful in knowing
the level of economic and business activities of
a country. So, these are rightly known as
economic barometers

31
 Limitations of Index
Number
We know everything existing has both advantages and limitations. Index
numbers have a lot of advantages, but to an extent, this is when their
limitations creep up. The limitations of index numbers are as follows:
• There are chances for errors given that index numbers come as a result of
samples. These samples are put together after deliberation, which creates
chances for errors. It can also be found in weights or base periods etc.
• It is always calculated based on items. Items that are so selected may not
exactly be in trend, which in turn creates an inaccurate analysis.
• Multiple methods can be used to formulate index numbers. Due to this
multiplicity of methods, outcomes may bring forward a different set of
values which may further lead to confusion.
• The index numbers show the approximate indications of the relative
changes that occur. Moreover, the changes in variables that are compared
over a prolonged time may fall short on reliability.
• The selection of representative commodities may be skewed. It is since
these commodities are based on samples.
32
 Methods of base year

Generally in price index numbers changes in various

years are measured on the basis of base year. There are
two methods of base year:
1. Fixed- base method
2. Chain-base method
 Fixed- base method

In this method base year remain fixed. It means that

index numbers of all other years are prepared on the
basis of a particular year or period. Fixed base can also
be of two types:
i. Single- year fixed base
ii. Multi-year fixed base
 (i) Single- year fixed base

In this method any normal year or period is selected as

base year. The price of base year is denoted as po and
the prices of other year as p1 and the following formula
is used for the calculation of index number or price
relatives:
Index number = (p1 x 100 )/ po
 (ii)Multi-year fixed base

When there is a difficulty in selecting a particular year as

a base year, the average price of a few years is taken as
a base price and this average price is expressed as po.
 Chain-base method

In this method price relative (also known as link relative)

for every current year is calculated on the basis of price
of the immediately preceding year.
For ex. If index numbers are to be constructed from 2005
to 2009, then for 2005 the year 2004 will be taken as
base and similarly 2005 will be base for 2006, 2006 for
the year 2007 and so on.
Methods of constructing
index numbers
Methods of constructing
index numbers
 1. Unweighted index
numbers
In this method no weight is assigned to various items and
it is assumed that all the items have equal weight or
equal relative importance, it is of two types:
a. Simple Aggregative method
b. Simple average of price relatives Method
 a. Simple Aggregative
method
In this method price of all commodities in base year and
current year are added seperately and they are
denoted as Σ po and Σ p1 respectively. The total of
current year Σ p1 is divided by the total of base year Σ po
and the quotient is multiplied by 100 symbolically:
Index number (P01) = (Σ p1 / Σ po )x100
 b. Simple average of price relatives
Method

In this method, first of all price relatives(P.R.) of the

various items included in the index are obtained,.
Index number (P01) = Σ((p1 / po )x100) ) /N
 2.Weighted index numbers

Weighted index numbers are those index numbers in

which comparative or relative importance is assigned to
different commodities and on account of this
adjustment these index numbers are considered more
rational and logical it is again of two types:
a. Weighted aggregative method
b. Weighted average of price relatives method
 a. Weighted aggregative method

In this method appropriate weights are assigned to

various commodities to reflect their their relative
importance. If these weights are based on the actual
quantity, the symbol ‘q’ is used for it and if weights are
assigned on estimates, symbol of ‘w’ is appropriate.
Index number = (Σ p1 q0 / Σ po q0 )x100
Or (Σ p1 w / Σ po w )x100
There are various methods on this basis which are as
follows:
 1. Laspeyre’s method

In this method, weights are assigned by the quantities(q0)

in the base year. This index considers the ratio of
current year value to base year value to measure the
change in price level. Hence focuses on maintaining the
standard of living of the base year.
Index number (P01) = (Σ p1 q0 x100) / Σ po q0
 2. Paasche’s method

In this method, weights are assigned by the quantities

(q1) in the current year.
Index number (P01) = (Σ p1 q1 x100) / Σ po q1
 3. Marshall & Edgeworth’s
index
According to them the sum of base year and current year
quantities may be used as theweights. Hence,
Marshall & Edgeworth’s index
(P01) = Σ p1 ( qo + q1 ) x 100
Σ po ( qo + q1 )
 4. Dorbish & Bowley’s Index

They suggested that the effect of the bias in the two

indices may be eliminated by taking their arithmetic
average. Therefore,
Dorbish & Bowley’s Index
(P01) = 1 Σ p1 qo Σ p1 q1 x 100
2 Σ po qo Σ p1 q1
 5. Fisher Index
According to them price index should be equal to the
geometric mean of the Laspeyre’s and Paasche’s
indices. Fisher’s index is called ‘ideal’ because it
satisfies all the tests of adequacy of index numbers.
Fisher Index,
(P01) = √ (Laspeyre’s Index x Paasche’s Index)

P01=√∑p1q0/∑p0q0)×∑p1q1/∑p0q1×100
50
51
Previous years questions of index
no.
Q. What is index number? Discuss its utility.
Q. Explain the uses of index numbers. What problems are
involved in the construction of index numbers?
Q. What is Fisher’s ideal formula for preparing index
number? Does it satisfy the time reversal test and
factor reversal test? Explain.
Q. “Index Numbers are devices for measuring changes in
the magnitude of a group of related variables”. Discuss
this statement and point out the important uses of
index numbers.
Calculate the Fishers Ideal Index number from the
following data:
Commodities Base Year (2015) Current Year(2016)
Price Quantity Price Quantity
A 12 10 15 12
B 15 7 20 5
C 24 5 20 9
D 5 16 5 14

53