CUB (version 0.1)

cubforsim: Simulation routine for CUB models without covariates

Description

Fit CUB models without covariates to given ordinal data. It is useful for simulation experiments since it performs the same steps as CUB function of the package, but with no printed output.

Usage

cubforsim(m, ordinal, maxiter = 500, toler = 1e-06)

Arguments

m

Number of ordinal categories

ordinal

Vector of ordinal responses

maxiter

Maximum number of iterations allowed for running the optimization algorithm (defaul: maxiter = 500)

toler

Fixed error tolerance for final estimates (default: toler = 1e-6)

Value

An object of the class "CUB", with null output for $BIC since the routine is only for simulation purposes

See Also

CUB, loglikCUB

Examples

data(relgoods)
m<-10
ordinal<-na.omit(relgoods[,37])
simul<-cubforsim(m,ordinal,maxiter=500,toler=1e-6)
simul$estimates      # Estimated parameters vector (pai,csi)
###############
data(univer)
m<-7
ordinal<-univer[,12]
simul<-cubforsim(m,ordinal)
param<-simul$estimates   # Estimated parameters vector (pai,csi)
###############
m<-9; n<-500
pai<-0.7
csi<-0.4
ordinal<-simcub(n,m,pai,csi)
simul<-cubforsim(m,ordinal)
param<-simul$estimates
maxlik<-simul$loglik
niter<-simul$niter
varmat<-simul$varmat