APPLIED TIME SERIES ST 3009

Dr. Nadeeka Basnayake

RATIONALE

Most of the real-life processes are time related. This

course is designed to provide students univariate
time series techniques and models in an applied
setting.
LEARNING OUTCOMES

After successful completion of the course the student should

be able to use appropriate univariate time series models
for forecasting.
 COURSE CONTENTS
Introduction: Areas of application, Objectives of time series analysis,
Components of time series, Descriptive analysis.

Distributional properties: Independence, Autocorrelation, Stationary.

Probability models to time series: Random walk, Autoregressive model,

Moving Average model, mixed models, parameter estimation, Diagnostics.

Forecasting: Optimal forecasts, Forecasts for ARMA models, Exponential

Smoothing forecasting method.
OTHER DETAILS
Teaching/ Learning Methods: Interactive lectures/online lectures
and independent learning activities

Method/s of evaluation:
End of semester examination (80%)
Continuous assessment (20%) [2 inclass assignments]
SUGGESTED READING
•Forecasting Methods and Applications (Makridakis, S.
Weelwright, S. C. and Hyndman, R. J.)

•The analysis of Time Series: An Introduction (Chatfield, C),

Forecasting and Control (Box, G. E. P., Jenkins, G. M. and
Reinsell)
INTRODUCTION: A TIME SERIES
A time series is a sequence of measurements of the same variable
collected over time. Most often, the measurements are made at
regular time intervals.

"Time series models are used to

forecast future events based on
previous events that have been
observed (and data collected) at
regular time intervals."
(Engineering Statistics Handbook, 2010)
 REGULAR
TIME
INTERVAL

OVERTIME
DIFFERENCE FROM REGRESSION
The data are not necessarily independent and not necessarily identically
distributed.

Ordering is very important because there is dependency and changing the

order could change the meaning of the data.
SOME EXAMPLES
▪ continuous monitoring of a person's heart rate
▪ hourly readings of air temperature
▪ daily closing price of a company stock
▪ monthly rainfall data
▪ yearly sales figures
REVISIT THE FIRST TS PLOT
INTERPRETATION
• There was a period in 1989 when no passengers were carried — this was due to an
industrial dispute.
• There was a period of reduced load in 1992. This was due to a trial in which some
economy class seats were replaced by business class seats.
• A large increase in passenger load occurred in the second half of 1991.
• There are some large dips in load around the start of each year. These are due to holiday
effects.
• There is a long-term fluctuation in the level of the series which increases during 1987,
decreases in 1989, and increases again through 1990 and 1991.
• There is a period of missing observations.
Any model will need to take all these features into account in order to effectively
forecast the passenger load into the future.
THANK YOU!

See you at the next lecture!

16