kjb::MV_normal_on_normal_dependence Class Reference

Represents the dependence between X and Y in p(x | y), where (x,y) is a multivariate normal. More...

#include <prob_conditional_distribution.h>

Public Member Functions
	MV_normal_on_normal_dependence (const MV_normal_distribution &PX, const MV_normal_distribution &PY, const Matrix &covariance_XY)
	Specify this conditional distributon by specifying the marginals and the covariance. More...
	MV_normal_on_normal_dependence (const Matrix &conditional_cov, int dim_y)
	Specify this conditional distributon by specifying the conditional variance, meaning the mean will simply the given value y. This a common thing to do in our lab. More...
	MV_normal_on_normal_dependence (const MV_normal_on_normal_dependence &nond)
MV_normal_on_normal_dependence &	operator= (const MV_normal_on_normal_dependence &nond)
MV_normal_distribution	operator() (const Vector &y) const

Detailed Description

Represents the dependence between X and Y in p(x | y), where (x,y) is a multivariate normal.

We need five parameters to determine a bivariate normal: three elements of the covariance matrix of the joint (var_X, var_Y, * and cov_XY) and the two means (mean_X, mean_Y). From these parameters, we can determine p(x | y) for any value of y.

Additionally, one can provide the conditional variance directly, which means one wants the mean to be simply y.

Constructor & Destructor Documentation

kjb::MV_normal_on_normal_dependence::MV_normal_on_normal_dependence ( const MV_normal_distribution &  PX, const MV_normal_distribution &  PY, const Matrix &  covariance_XY  )

inline

Specify this conditional distributon by specifying the marginals and the covariance.

kjb::MV_normal_on_normal_dependence::MV_normal_on_normal_dependence ( const Matrix &  conditional_cov, int  dim_y  )

inline

Specify this conditional distributon by specifying the conditional variance, meaning the mean will simply the given value y. This a common thing to do in our lab.

kjb::MV_normal_on_normal_dependence::MV_normal_on_normal_dependence ( const MV_normal_on_normal_dependence &  nond )

inline

Member Function Documentation

MV_normal_distribution kjb::MV_normal_on_normal_dependence::operator() ( const Vector &  y ) const

inline

MV_normal_on_normal_dependence& kjb::MV_normal_on_normal_dependence::operator= ( const MV_normal_on_normal_dependence &  nond )

inline

---

The documentation for this class was generated from the following file:

• /work/kobus/src/lib/prob_cpp/prob_conditional_distribution.h