TS_P1 - INTRODUCTION TO TIME SERIES ANALYSIS A time series...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1 INTRODUCTION TO TIME SERIES ANALYSIS A time series is a series of observations generated sequentially over time or space Example: Day (t) Return (y t ) 1 2.0 2 2.5 3 2.6 4 2.9 5 3.0 Underlying stochastic process {Y t } = {Y 1 , Y 2 ,... } Time series analysis = methods for analyzing time series.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Goals of time series analysis Describe (model) systems accurately Explain or give reasons for the patterns observed Predict the behavior of systems Control the behavior of systems Plan and carry out activities efficiently and effectively = !
Background image of page 2
3 Time domain and Frequency domain analyses Time domain analysis = analysis based on actual data {Y t } main tool of analysis = Auto-correlation function Frequency domain analysis = analysis based on data that has been transformed to complex numbers { j = A j +iB j =R j e ij ± } main tool of analysis = spectrum (periodogram)
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 Modeling time series Model = verbal/mathematical/statistical description of a system’s movements Types Models: Deterministic = one whose trajectory is completely determined by initial (boundary) conditions [not subject to error] X t =X 0 e 2t X t = 5 +2t + 10cos(2 ± t/12) Stochastic [Probabilistic] = one whose trajectory depends on chance [subject to error] X t = X 0 e 2Wt where W t is the value of a (normal) random at time t, [e.g. value of a government security such as a bond].
Background image of page 4
5 Main types of variation/components of a time series Trend (T t ) = a systematic short or long term movement/variation [a] deterministic trend e.g. (t) = 5+2t [b] stochastic trend e.g. Y t = Y t-1 + e t Seasonal [periodic] (S t ) = recurs with a fixed frequency i.e. at regular intervals of time e.g. such as mean monthly rainfall, mean monthly temperature, weekly sales of a company S t
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 21

TS_P1 - INTRODUCTION TO TIME SERIES ANALYSIS A time series...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online