ForecasterX
The ForecasterX trait provides a common framework for several forecasting models that use 1 ENDOGENOUS variable y and 0 or more EXOGENOUS variables xj. It provides methods for multi-horizon (1 to h) forecasting using the RECURSIVE technique. Forecasted values are produced only for the endogenous variable y. Lower case indicates actual values, while upper case is for forecasted values.
Y_t+1 = f(y_t, y_t-1, ... y_t-p+1, x0_t, x0_t-1, ... x0_t-p+1, x1_t, ...) Y_t+2 = f(Y_t+1, y_t, ... y_t-p+2, x0_t, x0_t-1, ... x0_t-p+1, x1_t, ...) ... Y_t+h = f(Y_t+1, y_t, ... y_t-p+2, x0_t, x0_t-1, ... x0_t-p+1, x1_t, ...)
Value parameters
- lags
-
the lags (p) used for endogenous variable (e.g., 10 => use lags 1 to 10)
Attributes
- See also
-
Forecaster - when there are no exogenous variables
- Graph
-
- Supertypes
-
class Objecttrait Matchableclass Any
- Known subtypes
Members list
Value members
Abstract methods
Produce a vector of size h, of 1 through h-steps ahead forecasts for the model. forecast the following time points: t+1, ..., t+h. Note, must create the yf matrix before calling the forecast method. Intended to work with rolling validation (analog of predict method)
Produce a vector of size h, of 1 through h-steps ahead forecasts for the model. forecast the following time points: t+1, ..., t+h. Note, must create the yf matrix before calling the forecast method. Intended to work with rolling validation (analog of predict method)
Value parameters
- h
-
the forecasting horizon, number of steps ahead to produce forecasts
- t
-
the time point from which to make forecasts
- yf
-
the forecasting matrix for the endogenous variable y (time x horizons)
Attributes
Forecast values for all y_.dim time points at horizon h (h-steps ahead). Assign into forecasting matrix and return the h-steps ahead forecast.
Forecast values for all y_.dim time points at horizon h (h-steps ahead). Assign into forecasting matrix and return the h-steps ahead forecast.
Value parameters
- h
-
the forecasting horizon, number of steps ahead to produce forecasts
- yf
-
the forecasting matrix for the endogenous variable y (time x horizons)
- yx
-
the matrix of endogenous y and exogenous x values
Attributes
Test FORECASTS at horizon h of a forecasting model y_ = f(lags (y_), x) + e and RETURN (1) aligned actual values, (2) the forecasts and (3) QoF vector. Testing may be in-sample (on the training set) or out-of-sample (on the testing set) as determined by the parameters passed in. Note: must call train and forecastAll before testF.
Test FORECASTS at horizon h of a forecasting model y_ = f(lags (y_), x) + e and RETURN (1) aligned actual values, (2) the forecasts and (3) QoF vector. Testing may be in-sample (on the training set) or out-of-sample (on the testing set) as determined by the parameters passed in. Note: must call train and forecastAll before testF.
Value parameters
- h
-
the forecasting horizon, number of steps ahead to produce forecasts
- y_
-
the testing/full response/output vector
- yx
-
the matrix of endogenous y and exogenous x values
Attributes
Concrete methods
Forecast values for all y_.dim time points and all horizons (1 through h-steps ahead). Record these in the yf matrix, where yf(t, k) = k-steps ahead forecast for y_t Note, column 0, yf(?, 0), is set to y (the actual time-series values). Forecast recursively down diagonals in the yf forecasting matrix. The top right and bottom left triangles in yf matrix are not forecastable.
Forecast values for all y_.dim time points and all horizons (1 through h-steps ahead). Record these in the yf matrix, where yf(t, k) = k-steps ahead forecast for y_t Note, column 0, yf(?, 0), is set to y (the actual time-series values). Forecast recursively down diagonals in the yf forecasting matrix. The top right and bottom left triangles in yf matrix are not forecastable.
Value parameters
- h
-
the maximum forecasting horizon, number of steps ahead to produce forecasts
- y_
-
the actual values to use in making forecasts
- yx
-
the matrix of endogenous y and exogenous x values
Attributes
Test FORECASTS over horizons 1 to h of a forecasting model y_ = f(lags (y_), x) + e and return its forecasts and QoF vector. Testing may be in-sample (on the training set) or out-of-sample (on the testing set) as determined by the parameters passed in. Note: must call train and forecastAll before testHorizons.
Test FORECASTS over horizons 1 to h of a forecasting model y_ = f(lags (y_), x) + e and return its forecasts and QoF vector. Testing may be in-sample (on the training set) or out-of-sample (on the testing set) as determined by the parameters passed in. Note: must call train and forecastAll before testHorizons.
Value parameters
- h
-
the forecasting horizon, number of steps ahead to produce forecasts
- y_
-
the testing/full response/output vector
- yx
-
the matrix of endogenous y and exogenous x values
Attributes
Set up testing by making h-steps ahead FORECASTS, and then aligning actual and forecasted values. Helper method for implementations of testF method. DROP the first h elements.
Set up testing by making h-steps ahead FORECASTS, and then aligning actual and forecasted values. Helper method for implementations of testF method. DROP the first h elements.
Value parameters
- doPlot
-
whether to plot predicted and actual values vs. time t
- h
-
the forecasting horizon, number of steps ahead to produce forecasts
- y_
-
the testing/full response/output vector
- yx
-
the matrix of endogenous y and exogenous x values