bayesHistogram.help: Helping function for Bayesian smoothing of (bi)-variate...

In bayesSurv: Bayesian Survival Regression with Flexible Error and Random Effects Distributions

Helping function for Bayesian smoothing of (bi)-variate densities based on possibly censored data

Description

These functions are not to be called by ordinary users.

These are just sub-parts of ‘bayesHistogram’ function to make it more readable for the programmer.

Usage

bayesHistogram.design(y1, y2)

bayesHistogram.checkStore(store)

bayesHistogram.priorInit(prior, init, mcmc.par, design)

bayesHistogram.writeHeaders(dir, design, prior.init, store)

Arguments

y1	response for the first dimension. This should be a~survival object created by Surv
y2	response object for the second dimension (if bivariate density is to be smoothed). This should be a~survival object created by Surv. Further, it must be consistent with y1, i.e. it has to have the same number of rows.
store	a~list with appropriate components
prior	a~list as required by prior argument of function bayesHistogram
init	a~list as required by init argument of function bayesHistogram
mcmc.par	a~list as required by mcmc.par argument of function bayesHistogram
design	a~list with the design information as returned by the function bayesHistogram.design. The list is assumed to have the following components: y.left ... y.right ... status ... dim ...
dir	string giving a~directory where to store sampled files
prior.init	an~object as returned by bayesHistogram.priorInit

Value

Some lists.

Value for bayesHistogram.design

A~list with the following components:

y.left

vector or matrix with either observed, right or left censored observations or with the lower limits of interval censored observations. It is a vector if dim == 1 and it is a matrix with 2 rows and n columns if dim == 2, where n is a~sample size. In that case, the first row of the matrix are responses for the first dimension and the second row of the matrix are responses for the second dimension.

y.right

vector or matrix with entries equal to 1 for observed, right or left censored observations and entries equal to the upper limits of interval censored observations. The structure is the same as that of y.left.

status

a~vector or matrix with censoring indicators (1 = exactly observed, 0 = right censored, 2 = left censored, 3 = interval censored). The structure is the same as that of y.left.

dim

dimension of the response, i.e. 1 (univariate smoothing) or 2 (bivariate smoothing)

Value for bayesHistogram.priorInit

A~list with the following components:

Gparmi

integer parameters for the G-spline constructor in the C++ code

Gparmd

double parameters for the G-spline constructor in the C++ code

iter

index of the nullth iteration

y

vector of initial values for the response, sorted as y_1[1], y_1[2], \dots, y_n[1], y_n[2] in the case of bivariate response with sample size equal to n

r

initial component labels (vector of size n) taking values from 1 to the total length of the G-spline

specification

specification of the G-spline model (1 or 2), see bayesHistogram for more detail

and the following attributes:

init

prior

mcmc.par

Author(s)

Arnošt Komárek [e-mail]

bayesSurv documentation built on May 29, 2024, 8:32 a.m.