mixpp: bdm::ARXg Class Reference
bdm::ARXg

bdm::ARXg Class Reference

Non-linear transformation + Gaussian noise. More...

#include <arx_ext.h>

Inheritance diagram for bdm::ARXg:

bdm::ARX bdm::BMEF bdm::BM bdm::root List of all members.

Public Member Functions

void from_setting (const Setting &set)
void validate ()
void to_setting (Setting &set) const
Constructors
 ARXg (const ARXg &A0)
ARXg * _copy () const
Mathematical operations
void bayes_weighted (const vec &yt, const vec &cond=empty_vec, const double w=1.0)
 Weighted Bayes $ dt = [y_t psi_t] $.

Protected Attributes

shared_ptr< fnc > g
 function g

Detailed Description

Non-linear transformation + Gaussian noise.

Regression of the following kind:

\[ y_t = g(\psi_t ) + r e_t \]

where unknown parameters rv are $[r]$, regression vector $\psi_t=\psi(y_{1:t},u_{1:t})$ is propagated through a known function g. Distrubances $e_t$ are supposed to be normally distributed:

\[ e_t \sim \mathcal{N}(0,1). \]

Member Function Documentation

void bdm::ARXg::from_setting ( const Setting &  set  )  [inline, virtual]

UI for ARXg estimator

    class = 'ARXg';
    yrv   = RV({names_of_dt} )                 // description of output variables
    rgr   = RV({names_of_regressors}, [-1,-2]} // description of regressor variables
    constant = 1;                              // 0/1 switch if the constant term is modelled or not
    g     = {class='my_function',...}          // function transforming regressor
    --- optional ---
    prior = {class='egiw',...};                // Prior density, when given default is used instead
    alternative = {class='egiw',...};          // Alternative density in stabilized estimation, when not given prior is used
    frg   = 1.0;                               // forgetting, default frg=1.0
    rv    = RV({names_of_parameters}}          // description of parametetr names

Reimplemented from bdm::ARX.

The documentation for this class was generated from the following file:
Generated on 2 Dec 2013 for mixpp by  doxygen 1.4.7