It estimates marginal regression models to datasets consisting of a categorical response and one or more covariates by a Fisher-scoring algorithm; this is an internal function that also works with response variables having a different number of response categories.
est_multi_glob_genZ(Y, X, model = c("m","l","g"), ind = 1:nrow(Y), de = NULL,
Z = NULL, z = NULL, Dis = NULL, dis = NULL, disp=FALSE,
only_sc = FALSE, Int = NULL, der_single = FALSE, maxit = 10)matrix of response configurations
array of all distinct covariate configurations
type of logit (m = multinomial, l = local, g = global)
vector to link responses to covariates
initial vector of regression coefficients
design matrix
intercept associated with the design matrix
matrix for inequality constraints on de
vector for inequality constraints on de
to display partial output
to exit giving only the score
matrix of the fixed intercepts
to require single derivatives
maximum number of iterations
estimated vector of regression coefficients
log-likelihood at convergence
matrix of the probabilities for each distinct covariate configuration
matrix of the probabilities for each covariate configuration
score for the vector of regression coefficients
Fisher information matrix
estimated vector of (free) regression coefficients
score for the vector of (free) regression coefficients
Fisher information matrix for the vector of (free) regression coefficients
matrix of individual scores for the vector of regression coefficients (if der_single=TRUE)
matrix of individual scores for the vector of (free) regression coefficients (if der_single=TRUE)
Colombi, R. and Forcina, A. (2001), Marginal regression models for the analysis of positive association of ordinal response variables, Biometrika, 88, 1007-1019.
Glonek, G. F. V. and McCullagh, P. (1995), Multivariate logistic models, Journal of the Royal Statistical Society, Series B, 57, 533-546.