init.ordi {LCAextend} | R Documentation |
computes the initial values for EM algorithm in the case of ordinal measurements
Description
computes the initial values of cumulative logistic coefficients alpha for the EM algorithm in the case of ordinal measurements and a product multinomial model.
Usage
init.ordi(y, K, x = NULL, var.list = NULL)
Arguments
y |
a |
K |
number of latent classes of the model, |
x |
a matrix of covariates if any, default is |
var.list |
list of integers indicating which covariates (taken from |
Details
The function allocates every individual to a class and evaluates the cumulative logistic coefficients for each measurement and each class. Regression coefficients for the covariates are set to 0.
Value
The function returns a list of one element alpha
which is a list of d
elements, each element alpha[[j]]
is a K
times
S-1
matrix, where S
is the number of values of the measurement y[,j]
, a row alpha[[j]][k,]
gives the the cumulative logistic
coefficients of class k
and measurement j
using alpha.compute
.
See Also
Examples
#data
data(ped.ordi)
status <- ped.ordi[,6]
y <- ped.ordi[,7:ncol(ped.ordi)]
#the function
init.ordi(y[status==2,],K=3)