 |
The term 'time series' usually refers to a sequence of observations following each other in time - they are common in many fields such as economics, engineering, and meteorology, to name just a few. What is specific to time series is that adjacent observations are somewhat dependent. This characteristic is at the core of the techniques for time series analysis.
Various models can be constructed with this dependence structure in mind: autoregressive (AR), moving average (MA), ARMA, ARIMA, etc. These models are then used to simulate new data as well as to forecast future values based on past observations. In this talk we look at some tools for time series analysis new to Mathematica.
(video, see link below)
|
|
For the newest resources, visit Wolfram Repositories and Archives »
