sufficientStatistics_Weighted.CatDP: Weighted sufficient statistics of a "CatDP" object

In bbricks: Bayesian Methods and Graphical Model Structures for Statistical Modeling

Description

For following model structure:

pi|alpha \sim DP(alpha,U)

x|pi \sim Categorical(pi)

where DP(alpha,U) is a Dirichlet Process on positive integers, alpha is the "concentration parameter" of the Dirichlet Process, U is the "base measure" of this Dirichlet process, it is an uniform distribution on all positive integers.Categorical() is the Categorical distribution. See dCategorical for the definition of the Categorical distribution.
In the case of CatDP, x can only be positive integers.
The model structure and prior parameters are stored in a "CatDP" object.
The sufficient statistics of a set of samples x is:

• unique positive integer values

• effective counts of the unique positive integers

Usage

## S3 method for class 'CatDP'
sufficientStatistics_Weighted(obj, x, w, foreach = FALSE, ...)

Arguments

obj	A "CatDP" object.
x	integer, the elements of the vector must all greater than 0, the samples of a Categorical distribution.
w	numeric, sample weights
foreach	logical, specifying whether to return the sufficient statistics for each observation. Default FALSE.
...	Additional arguments to be passed to other inherited types.

Value

An object of class "ssCatDP", the sufficient statistics of a set of categorical samples. Or an integer vector same as x if foreach=TRUE.

References

Teh, Yee W., et al. "Sharing clusters among related groups: Hierarchical Dirichlet processes." Advances in neural information processing systems. 2005.

See Also

CatDP, sufficientStatistics.CatDP

Examples

x <- sample(1L:10L,size = 4,replace = TRUE)
obj <- CatDP()
w <- runif(4)
## return an object of class "ssCatDP" contains the weighted counts of each unique integer
sufficientStatistics_Weighted(obj=obj,x=x,w=w)
## return x itself, no matter what w is
sufficientStatistics_Weighted(obj=obj,x=x,w=w,foreach = TRUE)

bbricks documentation built on July 8, 2020, 7:29 p.m.