Packages

object ARIMA

Companion object for class ARIMA. Includes features related to differencing and automated order selection.

See also

www.jstatsoft.org/article/view/v027i03/v27i03.pdf

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. ARIMA
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Value Members

  1. def difference(y: VectoD, d: Int): VectoD

    Return the 'd'th difference of the time-series for 'd' in {0, 1, 2, 3}.

    Return the 'd'th difference of the time-series for 'd' in {0, 1, 2, 3}. A new vector is returned even when there is no difference taken ('d = 0'), to ensure the original is preserved.

    y

    the original time-series to be differenced

    d

    the order of simple differencing

  2. def transformBack(yp: VectoD, y: VectoD, d: Int): VectoD

    Transform the fitted values on the training data of a differenced time series back to the original scale.

    Transform the fitted values on the training data of a differenced time series back to the original scale. Undo trend differencing only.

    yp

    the vector of predicted/fitted values

    y

    the original time-series vector

    d

    the order of simple differencing

    See also

    stats.stackexchange.com/questions/32634/difference-time-series-before-arima-or-within-arima

  3. def transformBackF(yf: VectoD, y: VectoD, d: Int, t: Int): VectoD

    Transform the forecast values of a differenced time series back to the original scale.

    Transform the forecast values of a differenced time series back to the original scale.

    yf

    the vector of forecasted values

    y

    the original time series

    d

    the order of simple differencing

    t

    the time point being forecasted (@see the 'forecast' method)

    See also

    stats.stackexchange.com/questions/32634/difference-time-series-before-arima-or-within-arima

  4. def transformBack_allH(ypa: MatriD, y: VectoD, d: Int): MatriD

    Transform the forecasted values of a differenced time series back to the original for all horizons scale.

    Transform the forecasted values of a differenced time series back to the original for all horizons scale.

    ypa

    the matrix of all multi-horizon forecasted values

    y

    the original time-series vector

    d

    the order of simple differencing

    See also

    stats.stackexchange.com/questions/32634/difference-time-series-before-arima-or-within-arima