Scribd
Upload
28 views3 pages

Time Series and Forecasting

University Mathematics I: Olaniyi Evans

Uploaded by

Olaniyi Evans
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
28 views3 pages

Time Series and Forecasting

University Mathematics I: Olaniyi Evans

Uploaded by

Olaniyi Evans
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/ 3

29

TIME SERIES & FORECASTING

CONTENTS
Forecasting 271
Time Series Patterns 271
Smoothing Methods 273
Moving Averages 274
Weighted Moving Average 275
Exponential Smoothing 275
Forecast Accuracy 276
Trend Projection 277
Linear Regression Analysis 277
Nonlinear Trend Regression 279
Seasonality and Trend 280

FORECASTING
Forecasting is a technique of making predictions of the future based on past and
present data and by analysis of trends. Forecasting methods can be classified as
qualitative or quantitative. Qualitative methods involve the use of expert
judgment to develop forecasts, particularly appropriate when historical data are
unavailable. Quantitative forecasting methods can be used when historical data
are available.
If the historical data are past values of the variable to be forecast, the forecasting
procedure is a time series method and the historical data are a time series. A
time series refers to the past recorded values of the variables under
consideration. The data may relate to the past monthly sales of products, or daily
demands placed on services like electricity and transportation.
The aim of time series analysis is to determine a pattern in the time series and
then extrapolate the pattern into the future. Causal forecasting methods assume
that the variables have a cause-effect relationship and that one or more
independent variables could be used to predict the value of a single dependent
variable. For instance, a regression analysis may be used to develop an equation
showing how sales and ads spending are related.

TIME SERIES PATTERNS


If the pattern of a time series can be expected to continue in the future, the past
pattern can be used as a guide in selecting an appropriate forecasting method. A
useful first step is to construct a time series plot which is a graph of the
relationship between time and the time series variable; time is on the horizontal
axis and the time series values are on the vertical axis. Some of the common types
of data patterns:
Trends: These relate to the long-term persistent movements or changes in data
like price increases, population growth, and consumer preferences. Figure 29.1
provides some examples of trends.
Seasonal variations: These relate to same repeating patterns over successive
periods, which occur because of consumption patterns or social habits, during
different times of a year (e.g., the demand for products like sweaters/coats, soft
drinks, and refrigerators). Figure 29.2 illustrates seasonal variations.
Cyclical variations: These exists if the time series plot shows an alternating
sequence of points below and above the trend line beyond one year. It could arise
272 Olaniyi Evans | University Mathematics

out of the phenomenon of business cycles. The business cycle refers to the
periods of expansion followed by periods of contraction. The period of a business
cycle may vary from one year to thirty years. Figure 29.3b provides an example
of cyclical variations.
Random or irregular variations: These refer to the erratic movements in
the data which cannot be easily attributed to the trend, seasonal or cyclical
components. Such variations can arise out of a wide variety of factors like sudden
weather changes, a communal clash or strike. These are random in nature; their
future occurrence and the resulting effects on demand are difficult to forecast.
The effects of the events can be eliminated by smoothing the time series data. An
example of random variations is provided in Figure 29.3a.

Figure 29.1 Examples of Trends

Figure 29.2 Seasonal Variations

Figure 29.3 Random/irregular and cyclical variations


a. Random or irregular variations b. Cyclical variations

In historical time series, one of the major tasks is to remove the trend in time
series, a process called decomposition. The trend line is then used to project
into the future. In most short-term forecasting situations, the cyclical component
is too small and tends to cancel each other out over time.
In most cases, the major task is the removal of seasonal variations from the time
series, a process called deseasonalization. By deseasonalizing the data,
analysts can better understand the underlying patterns and trends without the
interference of seasonal effects.
Chapter 29| Time Series & Forecasting 273

Purchase the full book at:


https://unimath.5profz.com/

We donate 0.5% of the book sales


every year to charity, forever. When
you buy University Mathematics (I &
II) you are helping orphans and the
less privileged.

You might also like