liftoneDoptimal_MLM_func: function of liftone for multinomial logit model

In ForLion: 'ForLion' Algorithm to Find D-Optimal Designs for Experiments

function of liftone for multinomial logit model

Description

function of liftone for multinomial logit model

Usage

liftoneDoptimal_MLM_func(
  m,
  p,
  Xi,
  J,
  thetavec,
  link = "continuation",
  reltol = 1e-05,
  maxit = 500,
  p00 = NULL,
  random = FALSE,
  nram = 3
)

Arguments

m	number of design points
p	number of parameters in the multinomial logit model
Xi	model matrix
J	number of response levels in the multinomial logit model
thetavec	model parameter
link	multinomial logit model link function name "baseline", "cumulative", "adjacent", or"continuation", default to be "continuation"
reltol	relative tolerance for convergence, default to 1e-5
maxit	the number of maximum iteration, default to 500
p00	specified initial approximate allocation, default to NULL, if NULL, will generate a random initial approximate allocation
random	TRUE or FALSE, if TRUE then the function will run with additional "nram" number of initial allocation p00, default to be TRUE
nram	when random == TRUE, the function will generate nram number of initial points, default is 3

Value

p reported D-optimal approximate allocation

p0 the initial approximate allocation that derived the reported D-optimal design

Maximum the maximum of the determinant of the Fisher information matrix

Convergence TRUE or FALSE, whether the algorithm converges

itmax, maximum iterations

Examples

m=5
p=10
J=5
factor_x = matrix(c(-1,-25,199.96,-150,-100,16,1,23.14,196.35,0,-100,
16,1,-24.99,199.99,-150,0,16,-1,25,-200,0,0,16,-1,-25,-200,-150,0,16),ncol=6,byrow=TRUE)
Xi=rep(0,J*p*m); dim(Xi)=c(J,p,m)
hfunc.temp = function(y){
if(length(y) != 6){stop("Input should have length 6");}
 model.mat = matrix(NA, nrow=5, ncol=10, byrow=TRUE)
 model.mat[5,]=0
 model.mat[1:4,1:4] = diag(4)
 model.mat[1:4, 5] =((-1)*y[6])
 model.mat[1:4, 6:10] = matrix(((-1)*y[1:5]), nrow=4, ncol=5, byrow=TRUE)
 return(model.mat)
 }
for(i in 1:m) {
Xi[,,i]=hfunc.temp(factor_x[i,])
}
thetavec=c(-1.77994301, -0.05287782,  1.86852211, 2.76330779, -0.94437464, 0.18504420,
-0.01638597, -0.03543202, -0.07060306, 0.10347917)
liftoneDoptimal_MLM_func(m=m,p=p,Xi=Xi,J=J,thetavec=thetavec,
link="cumulative",p00=rep(1/5,5), random=FALSE)

ForLion documentation built on April 11, 2025, 5:38 p.m.