Scribd
Upload
10 views6 pages

Chapter 5

Chapter 5 discusses time series data analysis, focusing on its purpose for forecasting and identifying fluctuations over time. It outlines the components of time series, including trend, seasonal, cyclical, and irregular components, and introduces methods for trend analysis such as the Least Squares Method and Moving Average Method. Additionally, it explains the additive and multiplicative models for estimating seasonal variations and calculating seasonal indices.

Uploaded by

NURASYIKIN shamsuddin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views6 pages

Chapter 5

Chapter 5 discusses time series data analysis, focusing on its purpose for forecasting and identifying fluctuations over time. It outlines the components of time series, including trend, seasonal, cyclical, and irregular components, and introduces methods for trend analysis such as the Least Squares Method and Moving Average Method. Additionally, it explains the additive and multiplicative models for estimating seasonal variations and calculating seasonal indices.

Uploaded by

NURASYIKIN shamsuddin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

CHAPTER 5

Time Series Data Analysis


By
Noor Fadhilah Mohd Ramlan
Introduction
A time series is a set of data observed over a period of time (can be hourly, daily,
weekly, monthly or yearly)
Purpose :
To identify the fluctuations due to certain factors, use it to make forecasting or
predictions
Forecasting or predicting is a tools in any decision making problem
Widely used in business
Eg : The opening price of a share of stock based on its past performance
Time series components
Trend Component (T) Seasonal Component (S) Cyclical Component (C) Irregular Component (I)
The movement repeats its The movements of a
The long term movement The movement repeats its pattern over period of time variable which is
where the value of the pattern every year around the (2-10 years) unpredictable
variable tends to increase same time
or decrease over a long Eg : The demand for umbrellas Exist due to changes of Usually caused by unusual
period of time (>10 years) something events
will increase every rainy
Eg : Consumer Price Index, season, number of accident Eg : The business cycle, Cannot be estimated
road accident will increase during festival economic recession, changes
of government policy Eg : Tsunami, earthquake
LSM  x  y Trend analysis
 xy n
To obtain the line of the best fit (trend b To describe a historical
equation) from the data  x
2

Suitable for long-term period data


x  n
2
pattern
Purpose :
The trend equation is:
T  a  bx To predict the future based
on the past after minimizing
where T = trend
the variation involved
x = time period
a = estimated trend at time a  y x
 b 
zero (y-intercept)  n  There consist of 2 methods :
b = increase in the trend per n  
unit of time (slope) Least squares method
(LSM), Moving average
method (MAM)
MAM
Calculate by adding n data values in a time series, then
divide by the number of data
Can be used to forecast the data value for the next
period but not for periods which are too far in the
future
There are 3 types:
3-period moving average, 5-period moving average, 4-
quarter moving average
Seasonal Variation
Additive model Multiplicative model
Actual data = T + S + residual variation Actual data = T x S x residual variation
Estimate trend values by using LSM Estimate trend values by using MAM
Estimate seasonal index before Estimate seasonal index before
forecasting actual data forecasting actual data

Used it to find seasonal index


Seasonal index is how much the average for that particular periods tends to be above or below the
grand average
There are 2 models : Additive and multiplicative model

You might also like