The tool supports interface of Foresight Analytics Platform 9 or earlier.
Each equation of a vector error correction model is a multiple regression equation not connected to other equations and a linear combination of endogenous variables named a correction component. That is why unknown values are estimated using the least squares method separately for each equation. Summary statistics of regression equations and summary statistics of coefficients (standard error, t-statistics and probability) are calculated using the standard method. The user should also calculate four statistics describing the ECM model. These values can be used to make a better choice for the model lag and determine model quality.
The Vector Error Correction Model dialog box looks as follows:
The dialog box includes the panels:
And also the panels that are identical to the panels of a standard model:
NOTE. Working with the Vector Error Correction Model model is available in the following cases:
• If a modeling container includes modeling variables that are separate repository objects.
• If a modeling container uses a time series database as a data source.
See also:
The Model Object | Calculation of Vector Error Correction Model