Cokriging-Based, Gaussian Cdf Estimator

Gaussian_cdf_coKestimator<covariance_set,kriging_constraints,matrix_lib>

This cdf estimator assumes the cdf of variable Z is Gaussian, and does account for secondary variables. The mean and variance of the Gaussian cdf are estimated by cokriging.

Where Defined

In header file <cdf_estimators.h>

Template Parameters

covariance_set		is a model of Covariance Set
kriging_constraints		is model of Kriging Constraint. It is set by default to OK_constraints<tnt_lib>
matrix_lib		defines the library of linear algebra to be used. The default value is tnt_lib, the TNT library.

Model of

Multiple Variable Cdf Estimator

Members

The leading Gaussian_cdf_coKestimator:: is omitted in the list of member functions.

• Gaussian_cdf_coKestimator(const covariance_set& cov_set,
                            const kriging_constraints& Kconstraints)
  
  Constructs a Gaussian_cdf_coKestimator. Covariance set cov_set gives the covariances C_{i, j}($\bf u_{i}^{}$,$\bf u_{j}^{}$) between variables Z($\bf u_{i}^{}$) and Z($\bf u_{j}^{}$).

• template<class Location, class InputIterator, class GaussianCdf> 
  int operator()(const Location& u,
               InputIterator first_neigh, InputIterator last_neigh,
               GaussianCdf& ccdf)
               
  
  Function call operator. It estimates the gaussian cdf parameters and modifies ccdf accordingly. location is a model of Location, and [first_neigh,last_neigh) is a range of models of Neighborhood.

  u is the location at which the Gaussian conditional cdf is estimated. The function returns 0 if no problem occurred.