I'm sorry, I think I misunderstood your request, Mariela.
Mclust will give you the parameters for each mixture model (mean and variance).
Here is what I meant:
library(mclust) # Mclust library for bimodal distributions
set.seed(314)
x - c(rnorm(100), rnorm(100, 10,3))
hist(x, prob=T)
m -
Hi!
I am using normalmixEM to fit a mixture of normal distributions.
I dont see an estimation of the standard deviation of the parameters.
Any idea?
thanks in advance
MAriela
[[alternative HTML version deleted]]
___
R-sig-ecology mailing list
Have you tried taking a look at the mclust package? It's quite flexible,
and obtains these statistics.
Phil
On 5/9/2014 8:30 AM, Mariela Sued wrote:
Hi!
I am using normalmixEM to fit a mixture of normal distributions.
I dont see an estimation of the standard deviation of the parameters.
The output from the normalmixEM function returns mu and sigma, mean and std
dev. of the distributions, a simple boot.se() of these output estimates
will generate the standard error of the mean and stand. dev.
Best,
Jason
Jason G. Romine,