Gaomeng
2012-May-24 08:49 UTC
[R] Mistake:number of cluster centres must lie between 1 and nrow(x)
Dear List:
I write codes to get"Mean and standard deviations (Std.) for EM
estimates—500 samples from the FM-ST model"(R package mixsmsn).It has a
mistake:"number of cluster centres must lie between 1 and nrow(x) ".
my
codes below:
mu1 <- c(2,2)
Sigma1 <- matrix(c(1.5,0,0,1.5), 2,2)
shape1 <-c(-5,10)
nu1 <- 4
mu2 <- c(-2,-1)
Sigma2 <- matrix(c(1.5,0,0,1.5), 2,2)
shape2 <-c(-5,10)
nu2 <- 4
pii<-c(0.6,0.4)
arg1 = list(mu=mu1, Sigma=Sigma1, shape=shape1, nu=nu1)
arg2 = list(mu=mu2, Sigma=Sigma2, shape=shape2, nu=nu2)
y <- rmmix(n=500, p = pii, "Skew.t", list(arg1,arg2))
St.analysis <- smsn.mmix(y, nu=3, g=2, get.init = TRUE, criteria = TRUE,
group = TRUE, family = "Skew.t",calc.im=TRUE)
St.analysis
##skew t fit giving intial values
for(i in 1:500){
mu1 <- c(0,0)
Sigma1 <- matrix(c(1,0,0,1), 2,2)
shape1 <-c(-1,5)
nu1 <- 10
mu2 <- c(0,0)
Sigma2 <- matrix(c(1,0,0,1), 2,2)
shape2 <-c(-1,5)
nu2 <- 10
pii<-c(0.5,0.5)
mu<-list(mu1,mu2)
#nu<-list(nu1,nu2)
Sigma<-list(Sigma1,Sigma2)
shape<-list(shape1,shape2)
St.analysis[i] <- smsn.mix(y[i,],g=2,nu=10,mu=mu,shape=shape,pii pii,get.init
= TRUE, criteria = TRUE,group = TRUE, family "Skew.t",calc.im=TRUE)
print(St.analysis[i])
}
--
View this message in context:
http://r.789695.n4.nabble.com/Mistake-number-of-cluster-centres-must-lie-between-1-and-nrow-x-tp4631177.html
Sent from the R help mailing list archive at Nabble.com.
[[alternative HTML version deleted]]