[R] Finite mixture model: truncated normal and a normal distribution

David Winsemius dwinsemius at comcast.net
Fri Jun 5 04:56:18 CEST 2015


On Jun 4, 2015, at 5:38 PM, John Sorkin wrote:

> I am looking for software that will take data what appears to come from a series of low numbers coming from a left-truncated normal distribution and a series of higher numbers coming from a normal distribution and produce the mean, SD, and mixing proportion of the two source distributions. I have looked at mixtoolsmixtools but it is not exactly what I am looking for as it models two-normal distributions (i.e. the lower of the two distributions is NOT truncated).
> 
> Any suggestions for a package, or an analysis plan would be appreciated.

Perhaps posting some data?

> 
> John David Sorkin M.D., Ph.D.


-- 
David Winsemius, MD
Alameda, CA, USA



More information about the R-help mailing list