Difference between revisions of "Orange: VAR Model"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) |
Onnowpurbo (talk | contribs) |
||
| Line 4: | Line 4: | ||
Model the time series using vector autoregression (VAR) model. | Model the time series using vector autoregression (VAR) model. | ||
| − | + | ==Input== | |
| − | + | Time series: Time series as output by As Timeseries widget. | |
| − | + | ==Output== | |
| − | + | Time series model: The VAR model fitted to input time series. | |
| − | + | Forecast: The forecast time series. | |
| − | + | Fitted values: The values that the model was actually fitted to, equals to original values - residuals. | |
| − | + | Residuals: The errors the model made at each step. | |
Using this widget, you can model the time series using VAR model. | Using this widget, you can model the time series using VAR model. | ||
| Line 19: | Line 19: | ||
[[File:Var-model-stamped.png|center|200px|thumb]] | [[File:Var-model-stamped.png|center|200px|thumb]] | ||
| − | + | * Model’s name. By default, the name is derived from the model and its parameters. | |
| − | + | * Desired model order (number of parameters). | |
| − | + | * If other than None, optimize the number of model parameters (up to the value selected in (2)) with the selected information criterion (one of: AIC, BIC, HQIC, FPE, or a mix thereof). | |
| − | + | * Choose this option to add additional “trend” columns to the data: | |
| − | + | ** Constant: a single column of ones is added | |
| − | + | ** Constant and linear: a column of ones and a column of linearly increasing numbers are added | |
| − | + | ** Constant, linear and quadratic: an additional column of quadratics is added | |
| − | + | * Number of forecast steps the model should output, along with the desired confidence intervals values at each step. | |
==Contoh== | ==Contoh== | ||
Revision as of 06:26, 30 January 2020
Sumber: https://orange.biolab.si/widget-catalog/time-series/var/
Model the time series using vector autoregression (VAR) model.
Input
Time series: Time series as output by As Timeseries widget.
Output
Time series model: The VAR model fitted to input time series. Forecast: The forecast time series. Fitted values: The values that the model was actually fitted to, equals to original values - residuals. Residuals: The errors the model made at each step.
Using this widget, you can model the time series using VAR model.
- Model’s name. By default, the name is derived from the model and its parameters.
- Desired model order (number of parameters).
- If other than None, optimize the number of model parameters (up to the value selected in (2)) with the selected information criterion (one of: AIC, BIC, HQIC, FPE, or a mix thereof).
- Choose this option to add additional “trend” columns to the data:
- Constant: a single column of ones is added
- Constant and linear: a column of ones and a column of linearly increasing numbers are added
- Constant, linear and quadratic: an additional column of quadratics is added
- Number of forecast steps the model should output, along with the desired confidence intervals values at each step.
Contoh
See also
ARIMA Model, Model Evaluation