Unit Xiii - Analysis of Time Series: Notes Structure
Unit Xiii - Analysis of Time Series: Notes Structure
Unit Xiii - Analysis of Time Series: Notes Structure
166
Analysis of Time Series
Understand forecasting and Deseasonalisation
NOTES
13.2 TIME SERIES ANALYSIS
Time series are influenced by a variety of forces. Some are continuously
effective other make themselves felt at recurring time intervals, and still
others are non-recurring or random in nature. Therefore, the first task is
to break down the data and study each of these influences in isolation.
This is known as decomposition of the time series. It enables us to
understand fully the nature of the forces at work. We can then analysis
their combined interactions. Such a study is known as time-series
analysis.
13.2.1 COMPONENTS OF TIME SERIES:
The factors that are responsible for bringing about changes in a
time series, also called the components of time series, are as follows:
Secular Trends (or General Trends)
Seasonal Movements
Cyclical Movements
Irregular Fluctuations
Secular Trends:
Secular trend is the main component of a time series which results
from long term effects of socio-economic and political factors. It shows
the growth or decline in a time series over a long period. It is the type of
tendency which continues to persist for a very long period. Prices and
export and import data, for example, reflect obviously increasing
tendencies over time.
Seasonal Trends:
Seasonal trends are short term movements occurring in data due
to seasonal factors. The short term is generally considered as a period in
which changes occur in a time series with variations in weather or
festivities. For example, it is commonly observed that the consumption of
ice-cream during summer is generally high and hence an ice-cream
dealer's sales would be higher in some months of the year while
relatively lower during winter months. Employment, output, exports, etc.,
are subject to change due to variations in weather. Similarly, the sale of
garments, umbrellas, greeting cards and fire-works are subject to large
variations during festivals like Valentine’s Day, Eid, Christmas, New
Year's, etc. These types of variations in a time series are isolated only
when the series is provided biannually, quarterly or monthly.
Cyclic Movements
Self-Instructional Material
It is a long term oscillations occurring in a time series. These
167
Analysis of Time Series oscillations are mostly observed in economics data and the periods of
such oscillations are generally extended from five to twelve years or
NOTES more. These oscillations are associated with the well known business
cycles. These cyclic movements can be studied provided a long series of
measurements, free from irregular fluctuations, is available.
Irregular Fluctuations
It happens when a sudden changes occurring in a time series
which are unlikely to be repeated. They are components of a time series
which cannot be explained by trends, seasonal or cyclic movements.
These variations are sometimes called residual or random components.
These variations, though accidental in nature, can cause a continual
change in the trends, seasonal and cyclical oscillations during the
forthcoming period. Floods, fires, earthquakes, revolutions, epidemic,
strikes etc., are the root causes of such irregularities.
13.2.2 ANALYSIS OF TIME SERIES
The objective of the time series analysis is to identify the
magnitude and direction of trends, to estimate the effect of seasonal and
cyclical variations and to estimate the size of the residual component.
This implies the decomposition of a time series into its several
components. Two lines of approach are usually adopted in analyzing a
given time series:
The additive model
The multiplicative model
It is not always necessary for the time series to include all four
types of variations; rather, one or more of these components might be
missing altogether. For example, when using annual data the seasonal
component may be ignored, while in a time series of a short span having
monthly or quarterly observations, the cyclical component may be
ignored
13.3 MEASUREMENT OF TRENDS
Moving average method
Least square method
13.3.1 MOVING AVERAGE METHOD
Moving average method is a simple device of reducing
fluctuations and obtaining rend values with a fair degree of accuracy. In
this method the average value of a number of years (months, weeks, or
days) is taken as the trend value for the middle point of the period of
moving average. The process of averaging smoothes the curve and
reduces the fluctuations.
The first thing to be decided in this method is the period of the
moving average. What it means is to take a decision about the number of
consecutive items whose average would be calculated each time.
Suppose it has been decided that the period of the moving average would
be 5 years (months, weeks, or days) then the arithmetic average of the
first 2 items (number 1,2,34 and 5) would be placed against item no:3
and then the arithmetic average of item Nos:2,3,4,5 and 6would be
placed against item No: 4. This process would be repeated till the
arithmetic average of the last five items has been calculated.
Odd Period of Moving Average
Calculation of three yearly moving averages includes the following steps
1. Add up the values of the first 3 years and place the yearly sum
against the median year. (This sum is called moving total) Self-Instructional Material
169
Analysis of Time Series 2. Leave the first year value, add up the values of the next three
years and place it against its median year.
NOTES 3. This process must be continued till all the values of the data are
taken for calculation.
4. Each 3-yearly moving total must be divided by 3 to get the 3-year
moving averages, which is our required trend value.
The formula calculating 3 yearly moving averages is as follows
𝑎 +𝑏+𝑐 𝑏+𝑐+𝑑 𝑐+𝑑 +𝑒
, ,
3 3 3
Example:
Calculate the 3 yearly and 5 yearly moving averages of the data
Years 1 2 3 4 5 6 7 8 9 10 11 12
Solution:
Year Sales 3 Year 3 Year 5 Year 5 Year
Moving Moving Moving Moving
Total Average Total Average
(3) / 3 (4) / 5
1 5.2 --- -- --
2 4.9 15.6 5.2 -- --
3 5.5 15.3 5.1 25.7 5.14
4 4.9 15.6 5.2 26.2 5.24
5 5.2 15.8 5.27 26.7 5.34
6 5.7 16.3 5.41 27.0 5.4
7 5.4 16.9 5.63 28.0 5.6
8 5.8 17.1 5.7 28.8 5.76
9 5.9 17.7 5.23 28.3 5.66
10 6.0 17.1 5.7 27.7 5.54
11 5.2 16.0 5.33 --- ---
12 4.8 --- --- --- ---
Even Period of Moving Average:
The period of moving average is 4,6, or 8, it is even number. The
Self-Instructional Material four yearly total cannot be placed against any year as median 2.5 is
170
between the second and the third year. So the total should be placed in Analysis of Time Series
between the 2nd and 3rd years. We must centre the moving average in
order to place the moving average against the year NOTES
Steps to find even period of moving average:
1. Add up the values of the first 4 years and place the sum against
the middle of 2nd and 3rd year. (This sum is called 4 year moving
total)
2. Leave the first year value and add next 4 values from the 2nd year
onward and write the sum against its middle position.
3. This process must be continued till the value of the last item is
taken into account.
4. Add the first two 4-years moving total and write the sum against
3rd year.
5. Leave the first 4-year moving total and add the next two 4-year
moving total and place it against 4th year.
6. This process must be continued till all the 4-yearly moving totals
are summed up and centered.
7. Divide the 4-years moving total by 8 to get the moving averages
which are our required trend values
Example:
Find the 4 yearly moving average foe determining trend values in the
following time series data
Profit in(000) ₹ 12 14 16 15 13 14 18
Solution:
Years Profit Sum of 4 years Moving 4 yearly Moving
Fours Average Average Centered
2005 12
2006 14
57 14.25 (14.25 + 14.50)/ 2 =
14.38
2007 16
58 14.50 (14.50 + 14.50)/ 2 =
14.50
2008 15 Self-Instructional Material
2011 18
Advantages
Moving averages can be used for measuring the trend of any
series. This method is applicable to linear as well as non-linear trends.
Disadvantages
The trend obtained by moving averages generally is neither a
straight line nor a standard curve. For this reason the trend cannot be
extended for forecasting future values. Trend values are not available for
some periods at the start and some values at the end of the time series.
This method is not applicable to short time series
13.3.2 LEAST SQUARES METHOD
When the trend is linear the trend equation may be represented by
y = a + bt and the values of a and b for the line y = a + bt which
minimizes the sum of squares of the vertical deviations of the actual
(observed) values from the straight line, are the solutions to the so called
normal equations:
Ʃy = na + bƩt …………….. (1)
Ʃyt = aƩt + bƩt2 ………….(2)
Where n is the number of paired observations
The normal equation are obtained by multiplying y = a + bt, by
the coefficient of a and b, i.e., by 1 and t throughout and summing up.
When the Number of Years is Odd
We can use this method when we are given odd number of years. It is
easy and is widely used in practice. If the number of items is odd, we
can follow the following steps:
1. Denote time as the t variable and values as y
2. Middle year is assumed as the period of origin and find out
deviations
3. Square the time deviations and find t 2.
4. Multiply the given value of y by the respective deviation of t and
find the total Ʃty.
5. Find out the values of y; get Ʃy
6. The value so obtained are placed in the two quations
i. Ʃy = na + bƩt
Self-Instructional Material ii. Ʃyt = aƩt + bƩt2; find out the value of a and b
7. The calculated values of a and b are substituted and the trend
172
value of y are found for various values of t. Analysis of Time Series
When the number of years is odd the calculation will be simplified by NOTES
taking the mid year as origin and one year as unit and in that case
Ʃt = 0 and the two normal equations take the form
Ʃy = na ; Ʃyt = bƩt2
Ʃ𝐲 Ʃ𝐲𝐭
Hence a = ,b=
𝑛 Ʃ𝐭²
Example :
Calculate trend values by the method of least square from data given
below and estimate the sales for 2003
Solution:
y t ty t2
1996 70 -2 -140 4
1997 74 -1 -74 1
1998 80 0 0 0
1999 86 1 86 1
2000 90 2 180 4
Since Ʃt = 0
Ʃ𝐲 400 Ʃ𝐲𝐭 52
a= = = 80 , b = = 𝟏𝟎 = 5.2
𝑛 5 Ʃ𝐭²
Hence, y = 80 + 5.2 x t
Self-Instructional Material
Therefore y1996 = 80 + 5.2 ( - 2) = 80 – 10.4 = 69.6
173
Analysis of Time Series y1997 = 80 + 5.2 ( -1) = 80 – 5.2 = 74.8
y1998 = 80 + 5.2 ( 0 ) = 80 + 0 = 80
NOTES
y1996 = 80 + 5.2 ( 1) = 80 + 5.2 = 85.2
y1996 = 80 + 5.2 ( 2) = 80 + 10.4 = 90.4
For 2003, t will be 5. Putting t = 5 in the equation
Y2013 = 80 + 5.2 (5\0 = 80 + 26 = 106
Thus the estimated sales for the year 2003 is ₹106 lakhs
When the Number of Years is Even
When the number of years is even the origin is placed in the midway
between the two middle years and the unit is taken to be half year instead
of one year. With this change of origin and scale we have
Ʃt = 0
Ʃ𝐲 Ʃ𝐲𝐭
Hence a = ,b=
𝑛 Ʃ𝐭²
Example:
Production of a company for 6 consecutive years is given in the
following table. Calculate the trend value by using the method of least
square
Production 12 13 18 20 24 28
Solution:
y t ty t2
174
Analysis of Time Series
2005 28 2.5 70 6.25 27.37
NOTES
2
n = 6 Ʃy = 115 Ʃt = 0 Ʃty = 57.5 Ʃt = 17.5
Since t = 0
Ʃ𝐲 115 Ʃ𝐲𝐭 57.5
a= = = 19.17 , b = = 17.5 = 3.28
𝑛 6 Ʃ𝐭²
175
Analysis of Time Series 13.4.1 METHODS OF CONSTRUCTING SEASONAL INDICES
NOTES There are four methods of constructing seasonal indices.
1. Simple averages method
2. Ratio to trend method
3. Percentage moving average method
4. Link relatives method
Simple Average Method :
The time series data for each of the 4 seasons (for quarterly data)
of a particular year are expressed as percentages to the seasonal average
for that year. The percentages for different seasons are averaged over the
years by using simple average. The resulting percentages for each of the
4 seasons then constitute the required seasonal indices.
Steps to calculate Simple Average Method:
(i) Arrange the data by months, quarters or years according to the data
given.
(ii) Find the sum of the each months, quarters or year.
(iii) Find the average of each months, quarters or year.
(iv) Find the average of averages, and it is called Grand Average (G)
(v) Compute Seasonal Index for every season (i.e) months, quarters or
year is given by
𝑆𝑒𝑎𝑠𝑜𝑛𝑎𝑙𝐴𝑣𝑒𝑟𝑎𝑔𝑒
Seasonal Index (S.I) = × 100
𝐺𝑟𝑎𝑛𝑑𝑎𝑣𝑒𝑟𝑎𝑔𝑒
Self-Instructional Material
176
Analysis of Time Series
2012 369 410 496 510
NOTES
2013 391 432 458 495
Solution:
𝑆𝑒𝑎𝑠𝑜𝑛𝑎𝑙𝐴𝑣𝑒𝑟𝑎𝑔𝑒
Seasonal Index (S.I) = × 100
𝐺𝑟𝑎𝑛𝑑𝐴𝑣𝑒𝑟𝑎𝑔𝑒
343 .83 + 412 + 461 .67+ 486 .83 1704 .33
Grand average = = = 426.0825
4 4
343 .83
S.I for I Q = × 100 = 80.69
426 .0825
177
Analysis of Time Series
461 .67
NOTES S.I for III Q = × 100 = 108.35
426 .0825
486 .83
S.I for IV Q = × 100 = 114.26
426 .0825
13.5 FORECASTING
Time series forecasting methods produce forecasts based solely on
historical values and they are widely used in business situations where
forecasts of a year or less are required. These methods used are
particularly suited to Sales, Marketing, Finance, Production planning etc.
and they have the advantage of relative simplicity. Time series
forecasting is a technique for the prediction of events through a sequence
of time.
The technique is used across many fields of study, from geology to
economics. The techniques predict future events by analyzing the trends
of the past on the assumption that future trends will hold similar to
historical trends. Data is organized around relatively deterministic
timestamps, and therefore, compared to random samples, may contain
additional information that is tried to extract.
Time series methods are better suited for short-term forecasts
(i.e., less than a year).
Time series forecasting relies on sufficient past data being
available and that the data is of a high quality and truly
representative.
Time series methods are best suited to relatively stable situations.
Where substantial fluctuations are common and underlying
Self-Instructional Material conditions are subject to extreme change, then time series
178
methods may give relatively poor results. Analysis of Time Series
Deseasonalised data being free from the seasonal impact manifest only
average valueof data.
Seasonal adjustment can be made by dividing the original data by the
seasonal index.
𝑶𝑹𝑰𝑮𝑰𝑵𝑨𝑳𝑫𝑨𝑻𝑨
Deseasonalised data = 𝑺𝑬𝑨𝑺𝑶𝑵𝑨𝑳𝑰𝑵𝑫𝑬𝑿 𝑿 𝟏𝟎𝟎
where an adjustment-multiplier 100 is necessary because the seasonal
indices are usually given in percentages.
In case of additive model
Yt = T + S + C + I
𝒔𝒆𝒂𝒔𝒐𝒏𝒂𝒍𝒊𝒏𝒅𝒆𝒙
Deseasonalised data = 𝒐𝒓𝒊𝒈𝒊𝒏𝒂𝒍𝒅𝒂𝒕𝒂 − 𝟏𝟎𝟎
𝒔𝒆𝒂𝒔𝒐𝒏𝒂𝒍𝒊𝒏𝒅𝒆𝒙
= 𝐘𝐭 − 𝟏𝟎𝟎
13.7 SUMMARY
Time series are influenced by a variety of forces. Some are Self-Instructional Material
continuously effective other make themselves felt at recurring
179
Analysis of Time Series time intervals, and still others are non-recurring or random in
nature. Therefore, the first task is to break down the data and
NOTES study each of these influences in isolation. This is known as
decomposition of the time series.
The objective of the time series analysis is to identify the
magnitude and direction of trends, to estimate the effect of
seasonal and cyclical variations and to estimate the size of the
residual component. This implies the decomposition of a time
series into its several components. Two lines of approach are
usually adopted in analyzing a given time series:
180