Added functionality for Pareto and GenPareto in Fit_References
Improved functionality for maximum likelihood estimation
Possibility to use reporting thresholds
Allow to consider censored data
Added distributions in function Local_Pareto_Alpha:
Generalized Pareto distribution
Piecewise Pareto distribution
Improved handling of inputs of length zero in vectorized functions
Vectorization of the following functions:
PiecewisePareto_Layer_Mean (only parameters Cover and AttachmentPoint)
PiecewisePareto_Layer_SM (only parameters Cover and AttachmentPoint)
PiecewisePareto_Layer_Var (only parameters Cover and AttachmentPoint)
Added function Fit_PML_Curve which fits a PPP_Model to a PML curve..
Added the option to use weights in Pareto_ML_Estimator_Alpha, PiecewisePareto_ML_Estimator_Alpha and GenPareto_ML_Estimator_Alpha.
Added function Fit_References for the piecewise Pareto distribution. This function fits a PPP model to the expected losses of
given reference layers and excess frequencies
It is now possible to have layers with an expected loss of zero in PiecewisePareto_Match_Layer_Losses
Improved handling of Frequencies and TotalLoss_Frequencies in PiecewisePareto_Match_Layer_Losses
Added functions for the generalized Pareto distribution
Added the class PGP_Model. PGP stands for Panjer & Generalized Pareto. A PGP_Model object contains the information to specify a
collective model with a Panjer distributed claim count and a generalized Pareto distributed severity
The following functions have been replaced by generics for PPP_Models and PGP_Models:
PPP_Model_Exp_Layer_Loss has been replaced by Layer_Mean
PPP_Model_Layer_Var has been replaced by Layer_Var
PPP_Model_Layer_Sd has been replaced by Layer_Sd
PPP_Model_Excess_Frequency has been replaced by Excess_Frequency
PPP_Model_Simulate has been replaced by Simulate_Losses
PiecewisePareto_Match_Layer_Losses now returns a PPP_Model object. PPP stands for Panjer & Piecewise Pareto. The Panjer class contains the
Poisson, the Negative Binomial and the Binomial distribution. A PPP_Model object contains the information required to specify a collective
model with a Panjer distributed claim count and a Piecewise Pareto distributed severity.
The package provides additional functions for PPP_Model objects:
PPP_Model_Exp_Layer_Loss: Calculates the expected loss of a reinsurance layer for a PPP_Model
PPP_Model_Layer_Var: Calculates the variance of the loss in a reinsurance layer for a PPP_Model
PPP_Model_Layer_Sd: Calculates the standard deviation of the loss in a reinsurance layer for a PPP_Model
PPP_Model_Excess_Frequency: Calculates the expected frequency in excess of a threshold for a PPP_Model
PPP_Model_Simulate: Simulates losses of a PPP_Model
PiecewisePareto_Match_Layer_Losses now also works for only one layer
Improved error handling in PiecewisePareto_Match_Layer_Losses
Added maximum likelihood estimation of the alphas of a piecewise Pareto distribution.
Allow for a different reporting threshold for each loss in Pareto_ML_Estimator_Alpha and in rPareto.
Improved fitting algorithm in Pareto_ML_Estimator_Alpha.
Better error handling in in Pareto_Find_Alpha_btw_FQ_Layer.