Fitting a student t distribution in R using fitdistr() yields error “non-finite finite-difference value” -
reproducable example give mentioned error code every time is: (note without set.seed, error comes every time)
library(mass) set.seed(seed = 1) data<-rnorm(n = 10000,mean = 0.0002,sd = 0.001) fitdistr(x = data,densfun = "t")
the error message is:
error in stats::optim(x = c(-0.000426453810742332, 0.000383643324222082, : non-finite finite-difference value [2] in addition: warning message: in log(s) : nans produced
the problem "non-finite finite-difference value". fitdistr not give me result.
my knowledge: researched , apparently mean parameter negative during iteration. , solution provide better or @ least different starting value. not figure out how , not sure if issue.
my question: a) why error message , b)how can fix in r, can fit student-t distribution distributed data?
Comments
Post a Comment