SST 411: TIME SERIES ANALYSIS 3 Credit Hours
Pre-requisite: SST 305
Purpose of the course
This course aims at equipping the learner with basic knowledge of theories needed in making
predictions of future values using past values.
Expected Learning Outcomes
By the end of this course students will be able to:
Measure and/or study various components of the time series namely: Trend, seasonal, cyclic
and random components.
Course Content
Concept of time series. Components of time series: trend, seasonal, cyclic and random. Methods
of analyzing the components. Use of filters in time series analysis. Time series processes: purely
random, random walk, moving average, autoregressive processes. Correlogram, periodogram and
spectral analysis.
TIME SERIES ANALYSIS FLOW CHART
WEEK TOPIC
WEEK 1 Definition and types of time series. Objectives of time series analysis
WEEK 2 Components, goals and models of time series analysis
WEEK 3 Measurement of trend component
WEEK 4 and 5 Filtering method
WEEK 6 Weighted moving average process
WEEK 7 Analyzing series that contains seasonal and cyclic variation
WEEK 8 Analyzing series that contains cyclic variation
WEEK 9 and 10 Probability models for time series
WEEK 11 & 12 Spectral analysis
WEEK 13 Examination
Mode of Delivery:
Virtual classes, Class lectures, discussions, problem solving, exercises.
Assessment:
Continuous Assessment: 30%
Final Exam: 70%
Core Reading materials
Chatfield C. (2016) The Analysis of Time Series: An Introduction. CRC Press New York.
ISBN 9780203491683
Recommended Reading Materials
1. Gupta S. C and Kapoor V. K (1994). Fundamentals of Applied Statistics. Sultan Chand
and Sons. ISBN 8170141516
2. Henrick Madsen (2007). Time Series Analysis. CRC Press NY ISBN 9781420059670
3. Douglas et al. (2015). Introduction to Time Series Analysis and Forecasting. John Wiley
and Sons, New Jersey
4. Wayne A. Fuller (1995). Introduction to Statistical Time series. John Wiley and Sons
ISBN 0471552399
Journals
The Journal of Statistical Methods and Applications. Springer
LESSON ONE
1.1 Introduction
In this lesson we introduce the time series analysis by looking at the four types. We will also
explain some definitions useful in the analysis of time series
1.2 Learning Outcomes
By the end of this lesson the learner will be able to:
1.2.1Define time series.
1.2.2List down and explain the four types of time series
1.2.3Distinguish between
(i) Discrete and Continuous time series
(ii) Deterministic and Stochastic time series
1.2.4 State the objectives of time series analysis
1.2.1 Definition
A time series is a collection of observations made sequentially with time. It is an arrangement of
statistical data in accordance with occurrence of time. Examples occur in many fields ranging
from economics to engineering.
A time series involves two variables one of which is time. For example population, Xt , in
different years, t.
1.2.2 Types of time series
There are four types of time series;
1 Economic time series
Many types of time series arise in economics. Examples include share prices on
successive days, export totals in successive months, average income in successive
months etc.
2 Physical time series
Many types of time series occur in the physical sciences particularly meteorology,
marine science and geophysics. Examples are rainfall on successive days and air
temperatures measured in successive hours, days or months.
3 marketing time series
This is especially in commerce. For example, analysis of sales figures in successive
weeks or months is an important problem in commerce. It is often important to
forecast future sales so as to plan production.
4 Demographic time series
This is the type of time series that occur in the study of population. An example is the
population of Kenya taken after every 10 years. Demographers want to predict
changes in the population for as long as ten or twenty years into the future.
1.2.3 Some terminologies
Continuous and discrete time series
A time series is said to be continuous when the observations are made continuously with time
and discrete when observations are taken only at specific times usually equally spaced. The latter
is the type that will be considered in this course.
Deterministic and stochastic time series
Deterministic time series is a series that can be predicted exactly. This is the case where future
values may be predicted fully from past observations. However, most time series are stochastic
in that the future is partly determined by past values, so that exact predictions are impossible.
In this course we will consider discrete and stochastic time series.
1.2.4 Objectives of Time Series Analysis
The objectives of analysing a time series include Description, Explanation, Prediction and
Control.
Description
When presented with a time series, the first step in the analysis is usually to plot the data and
obtain simple descriptive measures of the main properties of the series. Features such as trend
and seasonal effects can sometimes be easily seen from such a plot. The graph will also enable
one to look for unusual observations or outliers which do not appear to be consistent with the rest
of the data.
Explanation
When observations are taken on two or more variables, it may be possible to use the variation in
one time series to explain the variation in another time series. This may lead to a deeper
understanding of the process that generates the given time series.
Prediction
Given an observed time series, one may want to forecast the future values of the series. This is a
very important task in sales forecasting and in the analysis of economic and industrial time
series.
Control
When a time series is generated which measures the quality of a manufacturing process, the aim
of the analysis may be to control the process. A stochastic model is fitted to the series, future
values of the series are predicted and the input process variables are adjusted so as to keep the
process on target.
