Unit 4: Index Numbers, Forecasting and Time Series Analysis

Uses of Index Numbers; Methods of constructing; Index Numbers; Types and Methods of
forecasting; Steps in forecasting; Time series analysis; Time Series Decomposition.

Index Numbers
Definitions:

1. “Index numbers are devices for measuring differences in the magnitude of a

group of related variables.” – Croxton & Cowden

2. “An index number is a statistical measure designed to show changes in a variable

or a group of related variables with respect to time, geographic location or other
characteristics such as income, profession, etc.” – Spiegel

3. “In its simplest form an index number is the ratio of two index numbers
expressed as a percent. An index number is a statistical measure – a measure
designed to show changes in one variable or in a group of related variables over
time, or with respect to geographic location, or in terms of some other
characteristics.” – Patternson

4. “In its simplest form, an index number is nothing more than a relative number,
or a ‘relative’ which expresses the relationship between two figures, where one
of the figures is used as a base.” – Morris Hamburg

5. “Generally speaking, index numbers measure the size or magnitude of some

object at a particular point in time as a percentage of some base or reference
object in the past.” – Berenson & Levine

Uses of Index Numbers:

1. They help in framing suitable policies:

2. They reveal trends and tendencies:
3. They are important in forecasting future economic activities:
4. Index numbers are very useful in deflating:

Problems in the Construction of Index Numbers:

1. The Purpose of the Index

2. Selection of a Base Period
3. Selection of Number of Items
4. Price Quotations
5. Choice of an Average
6. Selection of Appropriate Weights
7. Selection of an Appropriate Formula

Methods of Constructing Index Numbers:

Index
Numbers

Unweighted Weighted

Simple Simple Weighted Weighted

Aggregative Average Aggregative Average of
of Relatives Relatives

Unweighted Index Numbers:

1. Simple Aggregative Method: Formula for price index is as
∑ P1 ×100
P01=
∑ P0
where, ∑ P1 =¿ Total of current year prices for various commodities,

∑ P 0=¿ Total of base year prices for various commodities.

Limitations: i) The units used in the price or quantity quotations can exert a big
influence on the value of the index.
ii) No consideration is given to the relative importance of the
commodities.

Q1. From the following data construct an index for 2006 taking 2005 as base:
Commodity: A B C D E

Price in 2005 (₹): 50 40 80 110 20

Price in 2006 (₹): 70 60 90 120 20

Solution: Construction of Price Index

Commodity Price in 2005 ( P0 ) Price in 2006 ( P1 )

A 50 70

B 40 60

C 80 90

D 110 120

E 20 20
 ∑ P 0=¿ 300 ∑ P1 =¿ 360

P01=
∑ P1 ×100= 360 ×100=120
∑ P0 300

This means that as compared to 2005, in 2006 there is a net increase in the
prices of commodities included in the index to the extent of 20%.

Q2. For the data given below, calculate the index number by taking: (i) 1995 as the
base year, (ii) 2002 as the base year, (iii) 1995 to 1997 as the base period.
Price of Price of
Year Year
Commodity X Commodity X

1995 4 2000 10

1996 5 2001 9

1997 6 2002 10

1998 7 2003 11

1999 8

Solution: (i) Index numbers taking 1995 as the base year

Price of Index Numbers Price of Index Numbers

Year Commodity (1995 = 100) Year Commodity (1995 = 100)

X X

1995 4 100 2000 10 (10/4) x 100 = 250

1996 5 (5/4) x 100 = 125 2001 9 (9/4) x 100 = 225

1997 6 (6/4) x 100 = 150 2002 10 (10/4) x 100 = 250

1998 7 (7/4) x 100 = 175 2003 11 (11/4) x 100 = 275

1999 8 (8/4) x 100 = 200

(ii) Index numbers taking 2002 as the base year

Price of Index Numbers Price of Index Numbers

Year Commodity (2002 = 100) Year Commodity (2002 = 100)

X X

1995 4 (4/10) x 100 = 40 2000 10 (10/10) x 100 = 100

 1996 5 (5/10) x 100 = 50 2001 9 (9/10) x 100 = 90

1997 6 (6/10) x 100 = 60 2002 10 (10/10) x 100 = 100

1998 7 (7/10) x 100 = 70 2003 11 (11/10) x 100 = 110

1999 8 (8/10) x 100 = 80

(Iii) Index numbers taking 1995 to 1997 as the base period

Average = (4 + 5 + 6)/3 = 5
Hence 1996 will be taken as 100.
Price of Index Numbers Price of Index Numbers

Year Commodity (1996 = 100) Year Commodity (1996 = 100)

X X

1995 4 (4/5) x 100 = 80 2000 10 (10/5) x 100 = 200

1996 5 (5/5) x 100 = 100 2001 9 (9/5) x 100 = 180

1997 6 (6/5) x 100 = 120 2002 10 (10/5) x 100 = 200

1998 7 (7/5) x 100 = 140 2003 11 (11/5) x 100 = 220

1999 8 (8/5) x 100 = 160

2. Simple Average of Price Relatives Method:

P01=
∑ ( P1
P0
× 100
)
N

where N refers to the number of items (commodities) whose price relatives are
thus averaged.

Q1. From the following data, construct an index for 2003 taking 2002 as base by the
average of relatives method using (i) arithmetic mean, and (ii) geometric mean
for averaged relatives:
Commodity Price in 2002 (₹) Price in 2003 (₹)

A 50 70

B 40 60

C 80 90
 D 110 120

E 20 20

Solution: (i) Index number using arithmetic mean of price relatives

Commodity Price in 2002 (₹) Price in 2003 (₹) P1
Price relatives ×100
P0
P0 P1

A 50 70 70
×100 = 140.0
50
B 40 60
150.0
C 80 90
112.5
D 110 120
109.1
E 20 20
100

P
∑ P1 × 100 = 611.6
0

P01 = 611.6/5 = 122.32

(ii) Index numbers using Geometric mean of price relatives

Commodity Price in 2002 Price in 2003 Price Log P

(₹) (₹) relatives

P0 P1 P1
P= × 100
P0

A 50 70 140 2.1461

B 40 60 150 2.1761

C 80 90 112.5 2.0512

D 110 120 109.1 2.0378

E 20 20 100 2.0000

∑ log P =
10.4112

P01= Antilog ¿
¿ 120.9
Q2. Prepare index numbers of price for three years with average price as base from
the data given below:
Rate per rupee Commodities

A B C

1st year 10 kg. 4 kg. 3 kg.

2nd year 9 kg. 3.5 kg. 3 kg.

3rd year 9 kg. 3 kg. 2.5 kg.

Solution: Convert the price into rupees per 40 kg. then determine average price and
with this average price as base compute relatives.
Average First year Second year Third year

Unit Price = 100

Price P Price P Price P
(Base)

A 40 kg. 4.3 4.0 93 4.4 102 4.4 102

B 40 kg. 11.6 10.0 86 11.4 98 13.3 115

C 40 kg. 14.2 13.3 94 13.3 94 16.0 113

Total of relatives 273 294 330

Average of relatives 91 98 110

Note: P indicates price relatives. For 1st year 10 kg. of commodity A costs ₹ 1. Hence, 40
kg. of commodity A will cost 40/10 = ₹ 4.0.
Similarly, other prices obtained are 4.3 i.e. (4+4.4+4.4)/3.

Weighted Index Numbers:

1. Weighted Aggregative Indices:

(i) Laspeyres method (L): P01=

∑ p1 q0 × 100
∑ p0 q0
(ii) Paasche method (P): P01=
∑ p1 q1 × 100
∑ p0 q1

( )
∑ p 1 q 0 + ∑ p1 q 1
(iii) Dorbish and Bowley’s method:
P01=
L+ P
=
∑ p 0 q 0 ∑ p0 q 1 ×100
2 2
 (iv)

(v)
Fisher’s ideal method:

Marshall -Edgeworth method:

P01=√ L× P=
√ ∑ p 1 q 0 × ∑ p 1 q 1 ×100
∑ p 0 q0 ∑ p 0 q 1

P01=
∑ ( q 0 +q 1) p1 × 100= ∑ p1 q0 +∑ p 1 q 1 ×100
∑ ( q 0 +q1 ) p0 ∑ p0 q0 +∑ p 0 q 1

(vi) Kelly’s method: P01=

∑ p1 q × 100 where q=
q 0 + q1
∑ p0 q 2

Q1. Construct index numbers of price from the following data by applying:
a) Laspeyres method b) Paasche method
c) Bowley’s method d) Fisher’s ideal method
e) Marshall-Edgeworth method
2002 2003
Commodity
Price Quantity Price Quantity

A 2 8 4 6

B 5 10 6 5

C 4 14 5 10

D 2 19 2 13

Solution: Calculation of various indices

2002 2003

Commodity Price Quantity Price Quantity p1 q0 p0 q 0 p1 q1 p0 q1

p0 q0 p1 q1

A 2 8 4 6 32 16 24 12

B 5 10 6 5 60 50 30 25

C 4 14 5 10 70 56 50 40

D 2 19 2 13 38 38 26 26

∑ p1 q 0 ∑ p 0 q 0 ∑ p1 q 1 ∑ p 0 q 1
= 200 = 160 = 130 = 103

a) Laspeyres method (L): P01=

∑ p1 q0 × 100= 200 × 100=125
∑ p0 q0 160
b) Paasche method (P): P01=
∑ p1 q1 × 100= 130 ×100=126.21
∑ p0 q1 103

c) Bowley’s method:

( ) (
∑ p 1 q 0 + ∑ p1 q 1
)
200 130
+
P01=
L+ P
=
∑ p 0 q 0 ∑ p0 q 1 ×100=
160 103
×100
2 2 2
¿ 125.6

d) Fisher’s ideal method: P01=√ L× P=

√ ∑ p 1 q 0 × ∑ p 1 q 1 ×100
∑ p 0 q0 ∑ p 0 q 1
¿
√ 200 130
×
160 103
×100=125.6

e) Marshall -Edgeworth method:

P01=
∑ ( q 0 +q 1) p1 × 100= ∑ p1 q0 +∑ p 1 q 1 ×100
∑ ( q 0 +q1 ) p0 ∑ p0 q0 +∑ p 0 q 1
200+130
¿ × 100=125.47
160+103

Q2. From the following data construct a price index number of the group of four
commodities by using the appropriate formula:
Base Year Current Year
Commodity
Price per unit Expenditure (₹) Price per unit Expenditure (₹)

A 2 40 5 75

B 4 16 8 40

C 1 10 2 24

D 5 25 10 60

Solution: Construction of price index

Commodity p0 q0 p1 q1 p0 q 0 p0 q1 p1 q0 p1 q1

A 2 20 5 15 40 30 100 75

B 4 4 8 5 16 20 32 40

C 1 10 2 12 10 12 20 24

D 5 5 1 6 25 30 50 60
 0

91 92 202 199

Fisher ideal index:

P01=
√ ∑ p 1 q 0 × ∑ p1 q 1 ×100=
∑ p 0 q0 ∑ p0 q 1 √ 202 199
91
×
92
×100=219.12

Q3. Calculate the weighted price index from the following data:
Price during
Materials Quantity
Units 2002 2003
required required
(₹) (₹)

Cement 100 lb. 500 lb.

5.0 8.0
Timber c. ft. 2000 c. ft.
9.5 14.2
Steel cwt. 50 cwt.
34.0 42.0
sheets
Per ‘000 20,000
12.0 24.0
Bricks

Solution:
Price during
Materials Quantity 2002 2003
Units Q p0 q p1 q
required Required (₹) (₹)

p0 p1

Cement 100 lb. 500 lb. 5 25 40

5.0 8.0
Timber c. ft. 2000 c. ft. 2000 19000 28400
9.5 14.2
Steel cwt. 50 cwt. 50 1700 2100
34.0 42.0
sheets
Per ‘000 20,000 20 240 480
12.0 24.0
Bricks

20965 31020

Kelly’s method: P01=

∑ p1 q × 100= 31020 × 100=147.96
∑ p0 q 20965

Weighted Average of Relatives:

 P01=
∑ PV , where P=Price relative and V = Value weights i.e., p0 q 0
∑V

p01= Antilog
{ ∑ V log p
∑V }, where P=
p1
p0
× 100 and V = Value weights i.e., p0 q 0

Q1. From the following data compute price index by supplying weighted average of
price method using: (i) arithmetic mean, and (ii) geometric mean.
p0 p1
Commodity q0
(₹) (₹)

Sugar 3.0 20 kg. 4.0

Flour 1.5 40 kg. 1.6

Milk 1.0 10 lt. 1.5

Solution: (i) Index number using weighted arithmetic mean of price relatives

Commodit p0 p1 V = p0 q 0 p1 PV
q0 P= × 100
y (₹) (₹) p0

20 60 400/3 8000
Sugar 3.0 kg. 4.0
60 1600/15 6400
Flour 1.5 40 1.6
10 150 1500
kg.
Milk 1.0 1.5
10 lt.

130 15900

P01=
∑ PV = 15900 =122.31
∑ V 130
There has been a 22.3% increase in prices over the base level.

(ii) Index number using weighted geometric mean of price relatives

p0 p1 V= p1 log p V log p
Commodity q0 p= × 100
(₹) (₹) p0
p0 q 0

Sugar 3.0 20 kg. 4.0 60 400/3 = 133.3 2.1249 127.49

4
Flour 1.5 40 kg. 1.6 60 1600/15 = 2.0282
106.7 121.69
Milk 1.0 10 lt. 1.5 10 2.1761
2
150.0
 21.761

130 270.94
7

p01= Antilog
{ ∑ V log p
∑V }
=Antilog { 270.947
130 }
=Antilog 2.084=120.9

Q2. By using the average of the quantities of two years as weights, compute a price
index:

Quantities Price (₹)

Commodity
2002 2003 2002 2003

A 10 16 20 25

B 9 7 25 28

C 20 24 40 40

Quantity or Volume index numbers:

a) Laspeyres method (L): Q01=

∑ q 1 p0 × 100
∑ q 0 p0

b) Paasche method (P): Q01=

∑ q 1 p1 × 100
∑ q 0 p1

c) Fisher’s method: Q01=√ L× P=

√ ∑ q1 p0 × ∑ q1 p 1 ×100
∑ q0 p0 ∑ q0 p 1
Q1. From the following data, compute a quantity index:
Quantities Price in
Commodity
2002 2003 2002

A 30 25 30

B 20 30 40

C 10 15 20

Q2. Compute by Fisher’s index formula the quantity index from the following data:
Commodit Pric
Price Total value Total value
y e

A 10 100 8 96
 14
B 16 96 98
10
C 12 36 40

Tests of adequacy of index number formulae:

a) Unit test
b) Time reversal test
c) Factor reversal test
d) Circular test

a) Unit Test: The unit test requires that the formula for constructing an index
should be independent of the units in which, or for which, prices and quantities
are quoted. Except for the simple (unweighted) aggregative index all other
formulae discussed.

b) Time reversal test: P01 × P10=1

i) Laspeyres method: P01 × P10=

∑ p 1 q 0 × ∑ p0 q 1 ≠1 the test is not
∑ p 0 q0 ∑ p1 q 1
satisfied.

ii) Paasche’s method: P01 × P10=

∑ p 1 q 1 × ∑ p0 q 0 ≠1 the test is not
∑ p 0 q1 ∑ p1 q0
satisfied.

iii) Fisher’s method: P01 × P10=

√ √
∑ p1 q 0 × ∑ p1 q1 × ∑ p0 q 1 × ∑ p 0 q0
∑ p0 q 0 ∑ p0 q1 ∑ p1 q 1 ∑ p1 q0

satisfied.
¿
√ ∑ p 1 q 0 × ∑ p1 q1 × ∑ p 0 q1 × ∑ p0 q 0 =1
∑ p 0 q 0 ∑ p0 q 1 ∑ p 1 q 1 ∑ p1 q 0
the test

c) Factor reversal test: P01 × Q01=

∑ p1q1
∑ p0q0

i) Laspeyres method: P01 × Q01=

∑ p 1 q 0 × ∑ q1 p 0 ≠ ∑ p 1 q 1 the test is
∑ p0q0 ∑ q0 p0 ∑ p0q0
not satisfied.

ii)

iii) Fisher method: P01 × Q01=

√ √
∑ p1 q 0 × ∑ p1 q1 × ∑ q1 p 0 × ∑ q 1 p1
∑ p0 q 0 ∑ p0 q1 ∑ q 0 p 0 ∑ q 0 p1
 ¿

satisfied.
√ ∑ p 1 q 0 × ∑ p1 q1 × ∑ q1 p0 × ∑ q1 p 1 = ∑ p 1 q 1
∑ p 0 q 0 ∑ p0 q 1 ∑ q0 p0 ∑ q0 p 1 ∑ p0 q 0
the test is

d) Circular test: p01 × p 12 × p20=1

i) Lasperyres method: p01 × p 12 × p20=

∑ p1 q 0 × ∑ p2 q1 × ∑ p0 q 2 ≠1 the
∑ p0 q 0 ∑ p1 q1 ∑ p2 q 2
test is not satisfied.

Q1. Calculate Fisher’s ideal index from the following data and prove that it satisfies
both time reversal and factor reversal tests.

2002 2003
Commodity
Price Expenditure Price Expenditure

A 8 80 10 120

B 10 120 12 96

C 5 40 5 50

D 4 56 3 60

E 20 100 25 150

Q2. Construct a Fisher’s ideal index from the following data and show that it satisfies
time reversal and factor reversal tests.

2002 2003
Commodity
Price Quantity Price Quantity

A 10 40 12 45

B 11 50 11 52

C 14 30 17 30

D 8 28 10 29

E 12 15 13 20
Time Series Analysis
Definitions:

6. “A time series is a set of statistical observations arranged in chronological order.”

– Morris Hamburg

7. “A time series consists of statistical data which are collected, recorded and
observed over successive increments of time.” – Patterson

8. “A time series may be defined as a collection of magnitudes belonging to

different time periods, of some variable or composite of variables, such as
production of steel, per capita income, gross national product, price of tobacco,
or index of industrial production.” – Ya-Lun-Chou

9. “When quantitative data are arranged in the offer of their occurrence, the
resulting statistical series is called a time series.” – Wessel & Wellet

10. “A time series is a set of observations taken at specified times, usually at ‘equal
intervals’. Mathematically, a time series is defined by the values Y1, Y2, … of a
variable Y (temperature, closing price of a share, etc.) at times t1, t2, … Thus Y is a
function of t symbolized by Y = F(t).” – Spiegel

Utility of Time Series Analysis:

1. It helps in understanding past behavior.
2. It helps in planning future operations.
3. It helps in evaluating current accomplishments.
4. It facilitates comparison.

Components of Time-Series:
1. Secular Trend
2. Seasonal Variations
3. Cyclical Variations
4. Irregular Variations

Q1. Calculate the 3-yearly moving averages of the production figures given below
and draw the trend:
Year Production Year Production

(in m. tonnes) (in m. tonnes)

 1989 15 1997 63

1990 21 1998 70

1991 30 1999 74

1992 36 2000 82

1993 42 2001 90

1994 46 2002 95

1995 50 2003 102

1996 56

Solution:
Calculation of 3-yearly moving averages

Year Production 3-yearly moving 3-yearly moving

total (in m. tonnes) average
(in m. tonnes)

1989 15 - -

1990 21 66 22.00

1991 30 87 29.00

1992 36 108 36.00

1993 42 124 41.33

1994 46 138 46.00

1995 50 152 50.67

1996 56 169 56.33

1997 63 189 63.00

1998 70 207 69.00

1999 74 226 75.33

2000 82 246 82.00

2001 90 267 89.00

2002 95 287 95.67

2003 102 - -
Calculation of 5-yearly moving averages

Year Production 5-yearly moving 5-yearly moving

total (in m. tonnes) average
(in m. tonnes)

1989 15 - -

1990 21 - -

1991 30 144 28.8

1992 36 175 35.0

1993 42 204 40.8

1994 46 230 46.0

1995 50 257 51.4

1996 56 285 57.0

1997 63 313 62.6

1998 70 345 69.0

1999 74 379 75.8

2000 82 411 82.2

2001 90 443 88.6

2002 95 - -

2003 102 - -

Q2. Evaluate the trend values using the data given by taking a four-yearly moving
average:
Year Value Year Value

1990 12 1997 100

1991 25 1998 82

1992 39 1999 65

1993 54 2000 49

1994 70 2001 34

1995 87 2002 20

1996 105 2003 7

Solution:
Calculations for 4-yearly moving average
Year Value 4-yearly moving 4-yearly moving 4-yearly moving
total average average centered

1990 12 - - -

1991 25 - - -

130 32.5

1992 39 39.75

188 47.0

1993 54 54.75

250 62.5

1994 70 70.75

316 79.0

1995 87 84.75

362 90.5

1996 105 92.00

374 93.5

1997 100 90.75

352 88.0

1998 82 81.00

296 74.0

1999 65 65.75

230 57.5

2000 49 49.75

168 42.0

2001 34 34.75

110 27.5

2002 20 - - -

2003 7 - - -
Method of Least Squares:

y=a+bx …. (1)

∑ y=na+b ∑ x
∑ xy =a ∑ x +b ∑ x 2
Q1. Below are given the figures of production (in thousand quintals) of a sugar
factory:
Year: 1997 1998 1999 2000 2001 2002 2003

Production (in ‘000

80 90 92 83 94 99 92
qtls.):

(i) Fit a straight-line trend to these figures.

(ii) Plot these figures on a graph and show the trend line.
Solution: Fitting the straight-line trend
Production (y) x = year- Trend values
Year x2 xy
(in ‘000 qtls.) 2000 (yc)

1997 80 -3 9 -240 84

1998 90 -2 4 -180 86

1999 92 -1 1 -92 88

2000 83 0 0 0 90

2001 94 1 1 94 92

2002 99 2 4 198 94

2003 92 3 9 276 96

n=7 ∑ y= 630 ∑ x =0 ∑ x 2=28 ∑ xy =56

y=a+bx …. (1)
630
∑ y=na+b ∑ x 630=7 a+(0)b 630=7 a a=
7
=90
56
∑ xy =a ∑ x +b ∑ x 2 56=(0)a+28 b 56=28 b b= =2
28
y=90+2 x
For x=−3 y=90+2 (−3 )=90−6=84
For x=−2 y=90+2 (−2 )=90−4=86
For x=−1 y=90+2 (−1 )=90−2=88
For x=0 y=90+2 ( 0 )=90−0=90
For x=1 y=90+2 ( 1 )=90+2=92
For x=2 y=90+2 ( 2 )=90+ 4=94
For x=3 y=90+2 ( 3 )=90+ 6=96
MEASUREMENT OF SEASONAL VARIATIONS:
1. Method of Simple averages (weekly, monthly or quarterly)
2. Ration-to-trend method
3. Ration-to-moving average method
4. Link relative method

Monthly average for January

Seasonalindex for January= × 100
Average of monthly averages

1. Method of Simple averages

Q1. Assuming that trend is absent, determine if there is any seasonality in the data
given below:
Year 1st quarter 2nd quarter 3rd quarter 4th quarter

2000 3.7 4.1 3.3 3.5

2001 3.7 3.9 3.6 3.6

2002 4.0 4.1 3.3 3.1

2003 3.3 4.4 4.0 4.0

What are the seasonal indices for various quarters?

Solution: Computation of seasonal indices

Year 1st quarter 2nd quarter 3rd quarter 4th quarter

2000 3.7 4.1 3.3 3.5

2001 3.7 3.9 3.6 3.6

2002 4.0 4.1 3.3 3.1

2003 3.3 4.4 4.0 4.0

Total 14.7 16.5 14.2 14.2

Average 14.7 4.125 3.55 3.55

=3.675
4

Seasonal
98.66 110.74 95.30 95.30
Index

3.675+ 4.125+3.55+3.55
The average of averages ( General average )= =3.725
4
Quarterly average
Seasonalindex= ×100
General average
first quarter average 3.675
Seasonalindex for first quarter= ×100= ×100=98.66
General average 3.725
second quarter average 4.125
Seasonalindex for second quarter= × 100= ×100=110.74
General average 3.725
2. Ration-to-trend method
Find the seasonal variations by the ratio-to-trend method from the data given below:
Year 1st quarter 2nd quarter 3rd quarter 4th quarter

1999 30 40 36 34

2000 34 52 50 44

2001 40 58 54 48

2002 54 76 68 62

2003 80 92 86 82

Solution: Calculating the trend values by the method of least squares

Yearly
Yearly avg. x=year- Trend
Year x2 Xy
totals 2001 values
(y)

1999 140 35 -2 4 -70 32

2000 180 45 -1 1 -45 44

2001 200 50 0 0 0 56

2002 260 65 1 1 65 68

2003 340 85 2 4 170 80

n=5 ∑ y=¿ ∑ x =¿0 ∑ x 2=¿ 1 ∑ xy =¿1

280 0 20

y=a+bx …. (1)
280
∑ y=na+b ∑ x 280=5 a+(0)b 280=5 a a=
5
=56
120
∑ xy =a ∑ x +b ∑ x 2 120=(0)a+10 b 120¿ 10 b b=
10
=12
y=56 +12 x
For x=−2 y=56 +12 (−2 )=56−24=32
For x=−1 y=56 +12 (−1 )=56−12=44
For x=0 y=56 +12 ( 0 )=56−0=56
For x=1 y=56 +12 ( 1 ) =56+12=68
For x=2 y=56 +12 ( 2 )=56+24=80

12
Quarterly increments= =3
4

Calculations of the quarterly trend values:

For 1999, trend value for the middle quarter i.e. half of 2 nd quarter and half of 3rd
quarter is 32.
Quarterly increment is 3.
So, the trend value of 2nd quarter is 32-(3/2)=32-1.5=30.5 and trend value of 3rd quarter
is 32+(3/2)=32+1.5=33.5
Trend values
Year 1st quarter 2nd quarter 3rd quarter 4th quarter

1999 30.5- 32-(3/2)=30.5 32+(3/2)=33. 33.5+3=36.5

3=27.5 5
2000 44-(3/2)=42.5 48.5
39.5 44+(3/2)=45.
2001 54.5 60.5
5
51.5
2002 66.5 72.5
57.5
63.5
2003 78.5 84.5
69.5
75.5
81.5

Ratio-to-trend values
Year 1st quarter 2nd quarter 3rd quarter 4th quarter

1999 30 40 107.46 93.15

×100=109.09 ×100=131.15
27.5 30.5

86.08 122.35
2000 109.89 90.72
77.67 106.42
2001 93.91 79.34
85.04 114.29
2002 97.84 85.52
105.96 117.20
2003 105.52 97.04

Total 463.84 591.41 514.62 445.77

Average 92.77 118.28 102.92 89.15

Seasonal
92.05 117.36 102.12 88.46
Index

92.77+118.28 +102.92+89.15
The average of averages ( General average )= =100.78
4
Quarterly average
Seasonalindex= ×100
General average
first quarter average 92.77
Seasonalindex for first quarter= ×100= ×100=92.05
General average 100.78
second quarter average 118.28
Seasonalindex for second quarter= × 100= × 100=117.36
General average 100.78

Ratio-to-Moving Average Method:

Q1. Calculate seasonal indices by the ratio-to-moving average method, from the
following data:
Year 1st Qtr. 2nd Qtr. 3rd Qtr. 4th Qtr.

2001 68 62 61 63

2002 65 58 66 61

2003 68 63 63 67

Solution: Calculations for Moving averages

Year Qtr. Given 4-figure 4-figure 4-figure moving average

moving moving centered
figures
total average

2001 1 68 -

2 62 -

254 63.50

3 61 =(63.50+62.75)/
2=63.125
251 62.75

4 63
62.250
247 61.75

2002 1 65
62.375
252 63.00

2 58
62.750
250 62.50

3 66
62.875
253 63.25

4 61
63.875
258 64.50

2003 1 68
64.125
255 63.75

2 63
64.500
 261 65.25

3 63 -

4 67 -

Calculations for Ratio-to-moving averages

Year 1st Qtr. 2nd Qtr. 3rd Qtr. 4th Qtr.

2001 - - 96.63 101.20

2002 104.21 92.43 104.97 95.50

2003 106.04 97.67 - -

Total 210.25 190.10 201.60 196.70

Average 105.125 95.05 100.8 98.35

Season Index 105.304 95.21 100.97 98.52

General Average = (105.125+95.05+100.8+98.35)/4 = 99.83

105.125
Season Index for first quarter = ×100=105.30
99.83

Link Relative Method:

Q1. Apply the method of link relatives to the following data and calculate seasonal
indices:

Quarter 1999 2000 2001 2002 2003

I 6.0 5.4 6.8 7.2 6.6

II 6.5 7.9 6.5 5.8 7.3

III 7.8 8.4 9.3 7.5 8.0

IV 8.7 7.3 6.4 8.5 7.1

Solution: Calculations of seasonal indices by the method of link relatives

Year I Qtr. II Qtr. III Qtr. IV Qtr.

1999 6.0 6.5 7.8 8.7

 8.4

2000 5.4 7.9 9.3 7.3

2001 6.8 6.5 7.5 6.4

2002 7.2 5.8 8.0 8.5

2003 6.6 7.3 7.1

Year I Qtr. II Qtr. III Qtr. IV Qtr.

1999 - 108.33 120.00 111.54

2000 62.07 146.30 106.33 86.90

2001 93.15 95.59 143.08 68.82

2002 112.50 80.55 129.31 113.33

2003 77.65 110.60 109.59 88.75

Total 345.37 541.37 608.31 469.34

Average 86.34 108.27 121.66 93.87

Chain Relatives 100 100× 108.27 108.27 ×121.66 131.72× 93.87

=108.27 =131.72 =123.64
100 100 100

Corrected 100 108.27- 131.72-3.375 = 123.64-5.0625

Chain relatives 1.6875 = 128.345 = 118.5775
106.5825

Seasonal Index 88.2 94.00 113.2 104.58

'
Current seaso n s figure
Link Relative = '
×100
Previous seaso n s figure
' '
Current seaso n s average × previous seaso n s chain relative
Chain relatives =
100

The calculations in the above table are as:

Chain relative of the first quarter (on the basis of first quarter) = 100

86.34 ×123.64
Chain relative of the first quarter (on the basis of last quarter) = =106.75
100

The difference between these chain relatives = 106.75-100=6.75

Per quarter difference = 6.75/4=1.6875

Adjusted chain relatives obtained by subtracting (1x1.6875=1.6875), (2x1.6875=3.375),
(3x1.6875=5.0625) from the chain relatives of 2nd , 3rd, 4th quarters respectively.

Average of corrected chain relatives =

100+106.5825+128.345+118.5775
=113.37625 ≅ 113.38
4

Corrected chainrelatives
Seasonal index = ×100
113.38