Scribd
Upload
23 views

Time Series Analysis

Uploaded by

minhtrietvo01012003
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
23 views

Time Series Analysis

Uploaded by

minhtrietvo01012003
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 28

TIME SERIES

ANALYSIS
MEANING &
DEFINITIONS
A time series is……
 A set of data depending on the time
 A series of values over a period of time
 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 income, price of
tobacco, index of industrial production.
 Time is act as a device to set of common stable
reference point.
 In time series, time act as an independent variable
to estimate dependent variables
Mathematical presentation of
Time Series
 A time series is a set of observation
taken at specified times, usually at
‘equal intervals’.
 Mathematically a time series is
defined by the values Y1, Y2…of a
variable Y at times t1, t2…. Thus,
Y= F(t)
CAUSES OF VARIATIONS IN
TIME SERIES DATA
 Social customs, festivals etc.
 Seasons
 The four phase of business :
prosperity, decline, depression,
recovery
 Natural calamities: earthquake,
epidemic, flood, drought etc.
 Political movements/changes, war
etc.
IMPORTANCE OF
TIME SERIES
ANALYSIS
 A very popular tool for Business
Forecasting.
 Basis for understanding past
behavior.
 Can forecast future activities/planning
for future operations
 Evaluate current
accomplishments/evaluation of
performance.
 Facilitates comparison
Time Series - Examples
 Stock price, Sensex
 Exchange rate, interest rate, inflation
rate, national GDP
 Retail sales
 Electric power consumption
 Number of accident fatalities
COMPONENTS OF
TIME SERIES
WHAT IS COMPONENTS?

 Characteristicmovements
or fluctuations of time
series.
Types of Components

• Secular Trend or Trend


1.

• Seasonal Variations/Fluctuations
2.

• Cyclical Variations/Fluctuations
3.

• Irregular Variations/Movements
4.
SECULAR TREND OR TREND

 The general tendency of the data to


grow or decline over a long period of
time.
 The forces which are constant over a
long period (or even if they vary they do
so very gradually) produce the trend.
For e.g., population change,
technological progress, improvement in
business organization, better medical
facility etc.
 E.g., Formation of rocks
 Downward trend-declining death rate
 Upward trend-population growth
 Mathematically trend may be Linear or
non-linear
PURPOSE OF
MEASURING
TREND

Knowledge of Study of other


Estimation
past behavior components
SEASONAL
VARIATIONS/FLUCTUATIONS
 The component responsible for the regular rise
or fall (fluctuations) in the time series during a
period not more than 1 year.
 Fluctuations occur in regular sequence
(periodical)
 The period being a year, a month, a week, a
day, or even a fraction of the day, an hour etc.

 Term “SEASONAL” is meant to include any kind of


variation which is of periodic nature and whose
repeating cycles are of relatively short duration.
 The factors that cause seasonal variations are: (a)
Climate & weather condition, (b) Customs traditions &
habits
CHACTERISTICS/FEATURES OF
SEASONAL VARIATIONS
 Regularity
 Fixed proportion
 Increase or Decrease
 Easy fore cast
PURPOSE OF MEASURING
SEASONAL VARIATIONS
 Analysis of past behavior of the series
 Forecasting the short time
fluctuations
 Elimination of the seasonal variations
for measuring cyclic variations
EXAMPLES OF SEASONAL
VARIATIONS
 Crops are sown and harvested at certain
times every year and the demand for
the labour gowing up during sowing and
harvesting seasons.
 Demands for wollen clothes goes up in
winter
 Price increases during festivals
 Withdraws from banks are heavy during
first week of the month.
 The number of letter posted on
Saturday is larger.
CYCLIC VARIATIONS
 Cycle refers to recurrent variations in
time series
 Cyclical variations usually last longer
than a year
 Cyclic fluctuations/variations are long
term movements that represent
consistently recurring rises and
declines in activity.
BUSINESS CYCLE
 Consists of 4 phases: prosperity,
decline, depressions, recovery
purpose
 Measures of past cyclical behavior
 Forecasting
 Useful in formulating policies in
business
IRREGULAR VARIATIONS
 Also called erratic, random, or
“accidental” variations
 Do not repeat in a definite pattern
 Strikes, fire, wars, famines, floods,
earthquakes
 unpredictable
CHARACTERISTICS
 Irregular & unpredictable
 No definite pattern
 Short period of time
 No Statistical technique
ANALYSIS OR
DECOMPOSITION OF
TIME SERIES
CONSISTS OF……
• Discovering
• Measuring
• Isolating
• Components of the time series
MATHEMATICAL MODELS OF .

TIME SERIES 

Additive model Multiplicative model


1. We assume that the data is 1. We assume that the data is
the sum of the time series the product of the various
components. components.
Yt = T + S + C + I Yt = T× S ×C × I
2. If the data do not contain one 2. If trend, seasonal variation, or
of the components (e.g., cycle is missing, then the
cycle) the value for that value
missing component is zero. is assumed to be 1.
Suppose there is no cycle,
then Suppose there is no cycle, then
Yt = T + S + I Yt = T× S × I
3. The seasonal component is 3. The seasonal factor of
independent of trend, and multiplicative model is a
thus magnitude of the proportion (ratio) to the
seasonal swing is constant trends, and thus the
over time. magnitude of the seasonal
swing increases or decreases
according to the behavior of
trend
OVERVIEW
 TIME SERIES
 IMPORTANCE
 COMPONENTS
 ANALYSIS
 MODELS
THANK YOU

You might also like