Message Boards Message Boards

Model selection for Time Series II

Posted 10 years ago

Time series can be defined as a collection of observations that occur sequentially through time. Examples of time series are virtually endless and occur in almost every part of our activity. The purpose of time series is to (i) describe, (ii) explain, (iii) predict and (iv) control factors that create particular series. The special characteristic of time-series is the fact that successive observations are usually not independent and that therefore the analysis must take into account the time sequence of the observations. Most time series are stochastic and therefore future is only partly determined by past values, so exact predictions are impossible and must be replaced by the probabilistic model which is conditioned by a knowledge of past values.

From historical data to the fitted model

Attachments:
POSTED BY: Igor Hlivka

Igor

Is it possible to get the notebook behind this and the other PDF files?

Thank you Michael

POSTED BY: Michael Kelly
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract