rriskFitdist.cont(data, distr, method = c("mle", "mme"), start, chisqbreaks, meancount, ...)
name
naming a distribution for which the corresponding
density function dname
, the corresponding distribution function
pname
and the corresponding quantile function must be defined, or
directly the density function.method = "mme"
,
and may be omitted for some distributions for which reasonable starting values
are computed if method = "mle"
.meancount
, or slightly more if
there are some ties.rriskMLEdist
, in order to control the optimization method.rriskFitdist.cont
returns a list containing 19 items with following fitting results:
estimate
method
sd
NULL
in case of the "mme" method.cor
NULL
in case of the "mme" method.loglik
NULL
in case of the "mme" method.aic
NULL
in case of the "mme" method.bic
NULL
in case of the "mme" method.n
data
distname
chisq
NULL
, if not computed.chisqbreaks
chisqpvalue
NULL
, if not computed.chisqdf
NULL
, if not computed.chisqtable
ad
NULL
, if not computed.adtest
NULL
, if not computed.ks
NULL
, if not computed.kstest
NULL
, if not computed.fitdist
from the package
fitdistrplus (Version 0.1-2). The original function was extended to
fitting additional distributions. The following continuous distributions can
be fitted by this function: normal, lognormal, logistic, exponential, F,
Student's t, Beta, Cauchy, Weibull, Gamma.
For more details see the assistance page of the function
fitdist
from the package fitdistrplus.
This function is not intended to be called directly but is internally
called in useFitdist
.
set.seed(1)
x <- stats::rnorm(5000, mean = 10, sd = 5)
rriskFitdist.cont(x, "norm")
rriskFitdist.cont(x, "t")
Run the code above in your browser using DataLab