Module net.finmath.lib
Package net.finmath.timeseries.models.parametric

Class GARCH

java.lang.Object
net.finmath.timeseries.models.parametric.GARCH
All Implemented Interfaces:
HistoricalSimulationModel
public class GARCH extends Object implements HistoricalSimulationModel
Log-normal process with GARCH(1,1) volatility. This class estimate the process \[ \mathrm{d} \log(X) = \sigma(t) \mathrm{d}W(t) \] where \( \sigma \) is given by a GARCH(1,1) process from time discrete realizations \( X_{i} \). That is, given a time series of values \( X_{i} \) the GARCH(1,1) volatility of the log-returns \( \log(X_{i+1}/X_{i}) \) is estimated.
Version:
1.0
Author:
Christian Fries

  • Constructor Details

    • GARCH

      public GARCH(double[] values)
      Create GARCH model estimated form the given time series of values.
      Parameters:
      values - Given set of values.

    • GARCH

      public GARCH(double[] values, int windowIndexStart, int windowIndexEnd)
      Create GARCH model estimated form the given time series of values.
      Parameters:
      values - Given set of values.
      windowIndexStart - First index to consider in the given set of values.
      windowIndexEnd - Last index to consider in the given set of values.

  • Method Details

    • getCloneWithWindow

      public GARCH getCloneWithWindow(int windowIndexStart, int windowIndexEnd)
      Description copied from interface: HistoricalSimulationModel
      Create a new model, using only a window of the times series.
      Specified by:
      getCloneWithWindow in interface HistoricalSimulationModel
      Parameters:
      windowIndexStart - Index of the first element to be part of the new time series.
      windowIndexEnd - Index of the last element to be part of the new time series.
      Returns:
      A new historical simulation using a different data window.

    • getLogLikelihoodForParameters

      public double getLogLikelihoodForParameters(double omega, double alpha, double beta)
      Get log likelihood of the sample time series for given model parameters.
      Parameters:
      omega - The parameter ω of the GARCH model.
      alpha - The parameter α of the GARCH model.
      beta - The parameter β of the GARCH model.
      Returns:
      The log likelihood of the times series under the specified GARCH model.

    • getLastResidualForParameters

      public double getLastResidualForParameters(double omega, double alpha, double beta)
      Returns the last estimate of the time series volatility.
      Parameters:
      omega - The parameter ω of the GARCH model.
      alpha - The parameter α of the GARCH model.
      beta - The parameter β of the GARCH model.
      Returns:
      Last residual, i.e., σ

    • getSzenarios

      public double[] getSzenarios(double omega, double alpha, double beta)

    • getQuantilPredictionsForParameters

      public double[] getQuantilPredictionsForParameters(double omega, double alpha, double beta, double[] quantiles)

    • getBestParameters

      public Map<String,Object> getBestParameters()
      Description copied from interface: HistoricalSimulationModel
      Returns the parameters estimated for the given time series.
      Specified by:
      getBestParameters in interface HistoricalSimulationModel
      Returns:
      The parameters estimated for the given time series.

    • getBestParameters

      public Map<String,Object> getBestParameters(Map<String,Object> guess)
      Description copied from interface: HistoricalSimulationModel
      Returns the parameters estimated for the given time series, using a parameter guess.
      Specified by:
      getBestParameters in interface HistoricalSimulationModel
      Parameters:
      guess - A parameter guess.
      Returns:
      The parameters estimated for the given time series.