The ARX companion object provides factory methods.
Attributes
Members list
Value members
Concrete methods
Create an ARX object from a response vector. The input/data matrix x is formed from the lagged y vectors as columns in matrix x.
Create an ARX object from a response vector. The input/data matrix x is formed from the lagged y vectors as columns in matrix x.
Value parameters
- hparam
-
the hyper-parameters (use Regression.hp for default)
- lags
-
the maximum lag included (inclusive)
- y
-
the original un-expanded output/response vector
Attributes
Create an ARX object from a response vector. The input/data matrix x is formed from the lagged y vectors as columns in matrix x. In addition, lagged exogenous variables are added.
Create an ARX object from a response vector. The input/data matrix x is formed from the lagged y vectors as columns in matrix x. In addition, lagged exogenous variables are added.
Value parameters
- elag1
-
the minimum exo lag included (inclusive)
- elag2
-
the maximum exo lag included (inclusive)
- hparam
-
the hyper-parameters (use Regression.hp for default)
- lags
-
the maximum lag included (inclusive)
- y
-
the original un-expanded output/response vector
Attributes
Make a matrix whose columns are lagged exogenous variables to be added to a data matrix.
Make a matrix whose columns are lagged exogenous variables to be added to a data matrix.
Value parameters
- elag1
-
the minimum exo lag included (inclusive)
- elag2
-
the maximum exo lag included (inclusive)
- ex
-
the matrix of data for the exogenous variables
- lags
-
the maximum lag included (inclusive) for checking purposes
Attributes
Use rolling-validation to compute test Quality of Fit (QoF) measures by dividing the dataset into a TESTING SET (tr) and a TRAINING SET (te) as follows: [ <-- tr_size --> | <-- te_size --> ] This version calls predict for one-step ahead out-of-sample forecasts.
Use rolling-validation to compute test Quality of Fit (QoF) measures by dividing the dataset into a TESTING SET (tr) and a TRAINING SET (te) as follows: [ <-- tr_size --> | <-- te_size --> ] This version calls predict for one-step ahead out-of-sample forecasts.
Value parameters
- mod
-
the forecasting model being used (e.g.,
ARX) - rc
-
the retraining cycle (number of forecasts until retraining occurs)
Attributes
- See also
-
RollingValidation
Set whether to include a simple linear (in time) trend.
Set whether to include a simple linear (in time) trend.
Value parameters
- trend
-
flag indicating whether to include a trend
Attributes
Split the x matrix and y vector into training and testing sets.
Split the x matrix and y vector into training and testing sets.
Value parameters
- ratio
-
the ratio of the TESTING set to the full dataset (most common 70-30, 80-20)
- x
-
the x data/input matrix
- y
-
the y response/output vector