parmfrailty: Fitting a parametric multivariate mixed-Poisson model

In joolee0918/Mfrailty: Dependence multivariate random effects model via gaussian copula functions

Description

Fitting a parametric multivariate mixed-Poisson model via a Gaussian copula with a log-normal marginal distribution of random effects

Usage

parmfrailty(formula, data, frailty = NULL, dist = "weibull",
  margins = "lnorm", ntype, model = FALSE, model.matrix = FALSE,
  control = list(), init = list(), eventnames = NULL,
  parallel = FALSE, ncore = NULL, ...)

Arguments

formula	a formula object with an obect of the type Surv on the left side and the terms on the right side. Note that +strata() is not supported.
data	a 'data.frame' which has variables in 'formula'
frailty	a charhacter string specifying a group
dist	a vector of character strings specifying a distribution for the baseline for each type of events. If it is a character string, it applies to all types of events. Default is "weibull". Other options are "ev", "loglogistic", and "lognormal". See phreg.
ntype	the number of types of events.
model	logical value: if TRUE, the model frame is returned.
model.matrix	logical value: if TRUE, the x matirx is returned.
control	an object of class specifying control options created by controlList.
init	a list specifying inital values of a vector of variances of random effects and dependence parameters. Default initial value for a variance of random effect is 1 and 0 for the dependence parameter.
eventnames	a vector of character string speficying event names
parallel	logical value: if TRUE, it supports parallel execution.
ncore	the number of cores if parallel = TRUE.

Value

an object of class parmfrailty representing the fit.

beta.coefficients	a list of each types of events of the estimated regressoin coefficients.
logalpha.coefficients	a list of each types of events of the estimated log of baseline parameters.
sig2	a vector of the estimated variances of random effects.
rho	a vector of the estimated dependence parameters from a Gaussian copula function.
ktau	a vector of the estimated Kendall's tau from a Gaussian copula function.
logLik	a value of log likelihood at the final values of the parameters.
iter	the number of iterations used.
conv	an integer code for the convergence. See convergence in optim.
var	a variance-covariance matrix of the estimates.
betavar	a list of each type of variances of the regression coefficient estimates.
logalphavar	a list of each type of variances of the log of baseline parameter estimates.
thetavar	a list of each type of variacnes of the regression coefficients and the log of baseline parameter estimates.
sig2var	a vector of the variances of random effects variances estimates.
rhovar	a vector of the dependence parameter estimates.
varnames	a list of event names and variable names.
control	a list of control arguments used.
n	the number of sample size.
nevent	a vector of the number of each types of events.
neventtype	the number of types of events.
nknot	the number nodes used in Gaussian-quadrature.
margins	a vector of character strings specyting marginal distributions of random effects.

The object will also contain the following: dist, copula, model, call, optionally x, and model.

joolee0918/Mfrailty documentation built on May 7, 2019, 6:58 p.m.