Binomial Distribution in in R

Question

I applied this code and I get this error over and over again.

library(mixtools)

simulate <- function(lambda=0.3, mu=c(0, 4), sd=c(1, 1), n.obs=10^5) {
    x1 <- rnorm(n.obs, mu[1], sd[1])
    x2 <- rnorm(n.obs, mu[2], sd[2])    
    return(ifelse(runif(n.obs) < lambda, x1, x2)) 
}

x <- simulate()

model <- normalmixEM(x=x, k=2)

Error: object 'C_normpost' not found

Can anyone help me with this?

If on the other hand someone can think of a way to separate two binomial distributions it would be great.

I can't reproduce the error, it runs smoothly for me. I don't know if the results make sense, but no error. — Yannis Vassiliadis, May 10 '18 at 21:47
Me too, no error. which version of R you are running? `sessionInfo()` ? — Gwang-Jin Kim, May 10 '18 at 21:53

score 1 · Accepted Answer · answered May 10 '18 at 22:15

If you have the mixtools package properly installed there should not be an error. I have version 1.1.0 installed which CRAN tells me is the most recent released version. A .C() call to C_normpost is made in three different places in the body of normalmixEM. After that code I see:

str(model)   # don't type just `model` ... appears to have no print method for it.
List of 9
 $ x         : num [1:100000] 3.33 3.17 -2.04 3.66 5.11 ...
 $ lambda    : num [1:2] 0.299 0.701
 $ mu        : num [1:2] -0.00253 3.9986
 $ sigma     : num [1:2] 0.994 1.001
 $ loglik    : num -197426
 $ posterior : num [1:100000, 1:2] 1.94e-03 3.66e-03 1.00 5.17e-04 1.42e-06 ...
  ..- attr(*, "dimnames")=List of 2
  .. ..$ : NULL
  .. ..$ : chr [1:2] "comp.1" "comp.2"
 $ all.loglik: num [1:39] -427524 -216959 -208812 -204523 -200531 ...
 $ restarts  : num 0
 $ ft        : chr "normalmixEM"
 - attr(*, "class")= chr "mixEM"

summary(model)
summary of normalmixEM object:
           comp 1   comp 2
lambda  0.2992979 0.700702
mu     -0.0025302 3.998599
sigma   0.9935503 1.001362
loglik at estimate:  -197426.2

So it has done a rather good job of estimating the means (0 and 4) as well as a very good job of estimating the variances of those components (1 and 1). You should probably try to reinstall mixtools in a fresh session and rerun the code.

Binomial Distribution in in R

1 Answers1