-basic_Init_Parameters = function(n,p,m,k){
+#-----------------------------------------------------------------------
+#' Initialize the parameters in a basic way (zero for the conditional mean,
+#' uniform for weights, identity for covariance matrices, and uniformly distributed forthe clustering)
+#' @param n sample size
+#' @param p number of covariates
+#' @param m size of the response
+#' @param k number of clusters
+#' @return list with phiInit, rhoInit,piInit,gamInit
+#' @export
+#-----------------------------------------------------------------------
+basic_Init_Parameters = function(n,p,m,k)
+{
phiInit = array(0, dim=c(p,m,k))
- piInit = (1.0/k)*rep.int(1,k)
+ piInit = (1./k)*rep.int(1,k)
rhoInit = array(0, dim=c(m,m,k))
-
- for(i in 1:k){
+ for(i in 1:k)
rhoInit[,,i] = diag(m)
- }
gamInit = 0.1*array(1, dim=c(n,k))
-
- R = sample(1:k,n, replace= TRUE)
-
- for(i in 1:n){
+ R = sample(1:k,n, replace=TRUE)
+ for(i in 1:n)
gamInit[i,R[i]] = 0.9
- }
gamInit = gamInit/sum(gamInit[1,])
-
- return(list(phiInit, rhoInit, piInit, gamInit))
+ return (data = list(phiInit = phiInit, rhoInit = rhoInit, piInit = piInit, gamInit = gamInit))
}