DEPARTMENT OF STATISTICS,

GOVERNMENT ARTS COLLEGE, COIMBATORE – 641018

SUBJECT TITLE : TIME SERIES AND INDEX NUMBERS

SUBJECT CODE : 18 BST 23C
PREPARED BY : Dr. P. VASANTHAMANI
MOBILE NUMBER : 9994575462

UNIT V

TESTS FOR INDEX NUMBERS

Fisher has given some criteria that a good index number has to satisfy. They are called (i) Unit test
(ii)Time reversal test (iii) Factor reversal test (iv) Circular test. Fisher has constructed in such a
way that this index number satisfies most of these tests and hence it is called Fisher’s Ideal Index
number.

Unit test

This requires the formula to be independent of the units in which prices and quantities are
quoted.

If rice is one of the commodities and a formula gives a result on the basis of its price per
kg. and quantity in kg., the formula should give the same result even when its corresponding price
per ton and quantity in tons are taken into account. Index number shows the relative change and if
the price has doubled in the current year in comparison with the base year, it is so whether kg. or
ton is the unit.

All the methods except the simple aggregative method satisfy this test.

The following example shows the different results given by the simple aggregative method
although the price condition is the same. Laspeyre’s, Paasche’s and Fisher’s formulae give the
same result in spite of the difference in units.

Item Unit Price Quantity Price Quantity

 P0 P1 q0 q1 P0q0 p1q0 p0q1 P1q1

Rice Ton 3000 4500 1 2 3000 4500 6000 9000

Cloth Metre 100 200 4 5 400 800 500 1000

p0 = p1 = p0q0 = p1q0 = p0q1 = p1q1 =

Total - -
3100 4700 3400 5300 6500 10000

By Simple Aggregative Method

∑ 𝑝1 4700
P01 =√∑ 𝑝0 𝑋 100 = 𝑥 100 = 151.61
3100

By Laspeyre's Formula

∑𝑃 𝑞 5300 5300
P01 = ∑ 𝑃1 𝑞0 x 100 = 3400 x = = 155.88
0 0 34

By Paasche's formula,

∑𝑃 𝑞 10000 2000
P01 = ∑ 𝑃1𝑞0 x 100 = 65000 x 100 = = 153.85
0 0 13

By Fisher's formula

5300 2000 5300000

P01 =√𝑃 01𝐿 𝑃 01𝑃 = √ 𝑋 =√ = 154.86
34 13 221

The same prices and quantities are quoted below in different units:

Price Quantity
Item Unit
P0 P1 q0 q1 P0q0 p1q0 p0q1 P1q1
 Rice Kg 3 5.5 1000 2000 3000 4500 6000 9000

Cloth Cm 1 2.0 400 500 400 800 500 1000

p0q0 = p1q0 = p0q1 = p1q1 =

Total p0 = 4 p1 = 6.5 - -
3400 5300 6500 10000

Totals except those of p0 and p1 remain the same and so Laspeyre’s , Paasche’s and
Fisher’s formulae give the same results as earlier.
By Simple Aggregative Method,
∑𝑃 6.5
P01 = ∑ 𝑃1 x 100 = x 100 = 162.50
0 4

Time reversal test

Fisher has pointed out that a formula for an index number should maintain time consistency by
working both forward and backward with respect to time. This is called time reversal test. Fisher
describes this test as follows.

“The test is that the formula for calculating an index number should be such that it gives the same
ratio between one point of comparison and the other, no matter which of the two is taken as base
or putting in another way the index number reckoned forward should be the reciprocal of that
reckoned back ward”. A good index number should satisfy the time reversal test.

This statement is expressed in the form of equation as P01 × P10 = 1.

Fisher’s formula, Marshall-Edgeworth formula, Kelly’s formula, Simple Aggregative Method

and Weighted and unweighted Geometric Means of Relatives Methods satisfy this test.

Prove that Fisher’s formula satisfies time reversal test

Time reversal test is satisfied when P01 × P10 = 1.(omitting the factor 100)

Using Fisher’s formula

Hence, P01 × P10 = √1 = 1

Factor reversal test

This test is also suggested by Fisher According to the factor reversal test, the product of price index
and quantity index should be equal to the corresponding value index.

In Fisher’s words “Just as each formula should permit the interchange of two times without giving
inconsistent results so it ought to permit interchanging the prices and quantities without giving
inconsistent results. i.e, the two results multiplied together should give the true ratio”.

This requires the formula to be such that

∑𝑃 𝑞
P01 x Q01 =∑ 𝑃1 𝑞1, after ignoring the factor 100 in each index.
0 0

Fisher’s is the only formula which satisfies this test.

Prove that Fisher’s index satisfies factor reversal test

Factor reversal test is satisfied if

Thus, Fisher’s Index satisfies Factor reversal test.

Circular Test

Circular test is an extension of the time reversal test. If three years 0, 1 and 2 are under
consideration, this requires the formula to be such that
P01 x P12 x P20 = 1

P01 is the index number of the second year in comparison with the first year, P12 is the index
number of the third year in comparison with the second and P2() is the index number of the first
year in comparison with the third.
Fisher’s formula does not satisfy this test. The simple aggregative method, G.M.of relatives
method and Kelly’s formula satisfy this test
The table below gives the prices of base year and current year of 5 commodities with their
quantities. Use it to verify whether Fisher’s ideal index satisfies time reversal test.

Solution:Index number by Fisher’s ideal index method

Fisher’s Index number satisfies time reversal test.

 Calculate the price index and quantity index for the following data by Fisher’s ideal formula and
verify that it satisfies the factor reversal test.

Solution

Hence, Fisher ideal index number satisfies the factor reversal test.
CHAIN BASE INDEX NUMBERS
When the data are available for more than two years, the method available besides the fixed
base method for computing index numbers, is the chain base method. Under this, link relatives are
calculated first. Link relative is a price (or quantity) relative with the condition that the base year
is the preceding year. Whenever more than one commodity is considered, the link relatives of all
the commodities are averaged (simple or weighted). In other words, the link relatives as well as
their averages are index numbers in which for each year the preceding year is the base year. These
averages of link relatives show the conditions of the different years in comparison with their
preceding years and are found to be of great use by businessmen and industrialists. They are
chained together to common base year for long term analysis using the formula,

𝐶𝑢𝑟𝑟𝑒𝑛𝑡 𝑦𝑒𝑎𝑟 𝑙𝑖𝑛𝑘 𝑟𝑒𝑙𝑎𝑡𝑖𝑣𝑒 𝑥 𝑃𝑟𝑒𝑐𝑒𝑑𝑖𝑛𝑔 𝑦𝑒𝑎𝑟 𝑐ℎ𝑎𝑖𝑛 𝑖𝑛𝑑𝑒𝑥

Chain Index = 100

As long as the base year is common, the chain base indices are likely to be same as the
fixed base indices. Sometimes, we may wish to convert chain base indices (C.B.I.) to fixed base
indices (F.B.I.) (where in the bases become different) or vice versa. The formula for such
conversions as suggested by some authors is

𝐶𝑢𝑟𝑟𝑒𝑛𝑡 𝑦𝑒𝑎𝑟 𝐶.𝐵.𝐼 𝑥 𝑃𝑟𝑒𝑐𝑒𝑑𝑖𝑛𝑔 𝑦𝑒𝑎𝑟 𝐹.𝐵.𝐼

Current year F.B.I = 100

Example 8 : Construct (a) fixed base and (b) chain base index numbers from the following data
relating to production of electricity.

Year 1981 1982 1983 1984 1985 1986 1987 1988

Production 25 27 30 24 28 29 31 35

Year 1989 1990 1991 1992 1993 1994 1995 1996

Production 40 41 36 32 37 38 39 40

Solution
 1981 25 100 100.00 100.00
1982 27 108 108.00 108.00
1983 30 120 111.11 120.00
1984 24 96 80.00 96.00
1985 28 112 116.67 112.00
1986 29 116 103.57 116.00
1987 31 124 106.90 124.00
1988 35 140 112.90 140.00

1989 40 160 114.29 160.01

1990 41 164 102.50 164.01

1991 36 144 87.80 144.00

1992 32 128 88.89 128.00
1993 37 148 115.63 148.01
1994 38 152 102.70 152.01
1995 39 156 102.63 156.01
1996 40 160 102.56 160.00

Quantities of production are given for 16 years. The production of "every year is divided
by that of 1981, i.e., 25 and is multiplied by 100 to get the fixed base quantity indices (Q01) given
in col (3).
For calculating link relatives (L.R.) of col. (4), quantity of every year is divided by that of its
preceding year and is multiplied by 100.
Link relatives are converted into chain base- indices (Q01) given in. col.(5) using the usual
formula.

Prepare index numbers from the average prices of three groups of commodities given below by
taking the base year as 1998 and the weights as 5,3 and 2 respectively.
Group 1998 1999 2000 2001 2002
I 50 55 52 49 55
II 4 5 3 5 6
III 10 10 11 10 9
Solution

Price Price Relatives (P) WP WP Fixed

base
I I III I I III I I III Prices I.N

1998 50 4 10 100 100 100 500 300 200 1000 100.0

1999 52 5 10 110 125 100 550 375 200 1125 112.5

2000 52 3 22 204 75 110 520 225 220 965 96.5

2001 49 5 10 98 125 100 490 375 200 1065 106.5

2002 55 6 9 110 150 90 550 450 180 1180 118

The price of each commodity in every year is divided by its price in 1998 and is multiplied
by 100 to get the price relative (P). The price relatives of the three commodities are multiplied by
5, 3 and 2 respectively to get WP values. They are added year wise (WP) and the total is divided
by 10 (W) to get fixed base index numbers.

From the following prices of three groups of commodities for the years 1993 to 1997, find the
chain base index numbers.

Groups 1993 1994 1995 1996 1997

I 4 6 8 10 12
II 16 20 24 30 36
III 8 10 16 20 24
Solution

Prices Link Relatives (P) Total Mean Chain

Groups (P Base
I II III I II III (P)
I.N) I.N

1993 4 4 16 8 100.00 100 100 300.00 100.00 100.00

1994 6 6 20 10 150.00 125 125 400.00 133.33 133.33

1995 8 8 24 16 133.33 120 160 413.33 137.78 183.70
1996 10 10 30 20 125.00 125 125 375.00 125.00 229.63
1997.12 12 36 24 120.00 120 120 360.00 120.00 275.56

The price of each commodity in every year is divided by its price in the preceding year and
is multiplied by 100 to get the link relative(P). As no weight is given, link relatives are added year
wise and the total is divided by 3. The average of each year is multiplied by the chain index number
of the preceding year and is divided by 100 to get the chain index number of that year. (Refer to
the formula to calculate chain base index number from the link relatives).
For the first year (1993) the link relatives and the chain base index number are taken as 100 each.
Note: If weights are given, weighted averages of the link relatives are to be calculated for
all the years before converting them into chain index numbers.

COST OF LIVING INDEX

Cost of living index number shows the impact of changes in the prices of a number of
commodities and services on a particular class of people in the current year in comparison with
the base year. Cost of living index number is also known as consumer price index number. It is
essential to assess the change in retail price and to decide the quantum of allowance to be provided
to the employees to offset the change in price and to keep them at their standard of living. Though
the general problems have narrowed down, each aspect still needs careful approach.
Main steps in the construction of Cost-of-Living Index Number:
1. The Purpose. At the outset, the class of people for whom the index number is intended is
to be identified. The knowledge of their area of living, their ways of life, their necessities,
their habits, etc. play an important role in getting good results. As far as possible the
 individuals of a group should have equal income.
2. The Base Year. Similar survey might have been conducted earlier. The current interest
might be to study the subsequent changes. For example, the pay scales of the employees
of Tamil Nadu Govt, were revised in 1994. For any future consideration of the employees,
1994 is to be taken as the base year.
3. Family Budget Enquiry. A sample survey, known as family budget enquiry, is conducted
and the items to be included, their quantity, etc. are found. It is customary to have the items
under the five heads (i) Food (ii) Clothing (iii) Fuel and Lighting (iv) House Rent and (v)
Miscellaneous. From the families of the concerned class of people, a sample of adequate
size is selected. From each such family, the details of the different items consumed, their
quality and quantity are noted. Though the items come under five groups stated earlier,
many sub groups are likely under each group. For example, food includes sugar, pulses,
wheat, rice, etc. Miscellaneous group consists of Movie, Medicine, Education and others.
It should be remembered that non-consumption monetary transactions such as payments
to insurance, provident fund, etc. are not considered.

4. The Prices. The average price paid for each item is to be gathered from the shops of the
region. The prices are retail prices. As mentioned earlier under general problems in the
construction of index numbers, it is a difficult task to gather and to arrive at an average
price of an item. The shops where many of the families buy and the most likely prices in
those shops are to be noted before finding their average. It is advisable to entrust
experienced and conscientious enumerators with this work. Cash prices are taken into
account and not the credit prices which include interest. But black market prices are to be
taken as such if the items are essential and they are not available in the open market.
Discounts and rebates when allowed for all the families are accounted for.
5. The Average. Both arithmetic mean and geometric mean can be used, the former
owing to its case of calculation and the latter owing to its suitability.
6. The Formula. Two formulae are available. They are given below.
i) Aggregate Expenditure Method or Weighted
Aggregative Method: In the usual notations, the
 ∑ 𝑝1 𝑞0
Cost of Living Index Number = X 100
∑ 𝑝0 𝑞0

It is the most popular method, and the formula is nothing but Laspeyre’s. On the basis of
base year quantities, total expenditures in current year and base year are calculated and the
percentage of change is worked out.
(ii) Family Budget Method or Weighted Averages of Relatives Method.
The formula under this method as given in usual notations is
∑ 𝑊𝑃
Cost of Living Index Number = ∑𝑊

Weights (W) are determined on the basis of the family budget enquiry wherein the relative
importance of the items within a group and the relative importance of a group to the total are
known. When W is base year value (p0q0), both the methods become one and the same.
Instead of finding the weighted arithmetic mean of price relatives as in the above formula,
weighted geometric mean may also be calculated if required, using the following formula:

∑ 𝑊 logP
Cost of Living Index Number = Antilog ( ∑𝑊
)

Uses:

1. Cost of living index numbers are the indicators of changes in real wages. Money wages
are changing and so are prices. Cost of living index numbers help to know whether
money wages overtake the rising prices or are overpowered by them.
2. Decisions on dearness allowance are based on the cost-of-living indices.
3. They are further used for deflation of income and value in national accounts

Construct cost of living index, for 2000 taking 1999 as the base year from the following data using
‘Aggregate Expenditure’ Method.

Article Quantity in 1999 1999 2000

(Kg.)
A 6 5.75 6.00
B 1 5.00 8.00
C 6 6.00 9.00
D 4 8.00 10.00
E 2 2.00 1.80
F 1 20.00 15.00
Solution
Quantity Price
Article
1999 (q0) 1999(p0) 2000(p1) p1q0 p0q0
A 6 5.75 6.00 36.00 34.50
B 1 5.00 8.00 8.00 5.00
C 6 6.00 9.00 54.00 36.00
D 4 8.00 10.00 40.00 32.00
E 2 2.00 1.80 3.60 4.00
F 1 20.00 15.00 15.00 20.00
P1q0 = p0q0 =
Total - - -
156.60 131.50
∑𝑃 𝑞
Cost of Living Index Number = ∑ 𝑃1 𝑞0 X 100
0 0

156.60
= 131.50 X 100

= 119.09
Example 12 : Calculate the cost of living index number form the following date
Item Base Year Price Current year price Weight
Food 39 47 4
Fuel 8 12 1
Clothing 14 18 3
House rent 12 15 2
Miscellaneous 25 30 1

Solution
Weight 𝑷
Item P0 P1 P = 𝑷𝟏 x 100 WP
W 𝟎

Food 39 47 4 120.51 482.04

Fuel 8 12 1 150.00 150.00
Clothing 14 18 3 128.57 385.71
House rent 12 15 2 125.00 250.00
Miscellaneous 25 30 1 120.00 120.00
 ∑ 𝑊𝑃 1387.75
Cost of Living Index Number = ∑𝑊
= = 126.16
11

Example 13 : Using geometric mean, calculate the cost of living index number for the year 2000.
Commodity Prince (1990) Price (2000) Weight
Food 60 108 40
Clothing 50 984 17
Fuel and Lighting 40 65 13
House Rent 125 225 27
Miscellaneous 120 240 3

Solution
P=
Commodity P0 P1 W 𝑷𝟏 LogP WlogP
x 100
𝑷𝟎
Food 60 108 40 180.0 2.2553 90.2120
Clothing 50 984 17 188.0 2.2742 38.6614
Fuel and Lighting 40 65 13 162.5 2.2909 28.7417
House Rent 125 225 27 180.0 2.2553 60.89.31
Miscellaneous 120 240 3 200.0 2.3010 6.9030
Total - - W=100 - - (W logP)
=225.4112

∑ 𝑊 logP
Cost of Living Index Number = Antilog ( ∑𝑊
)

225.4112
= Antilog ( )
100
= Antilog 2.2541
= 179.51