You should pay close attention to the definitions of the parameters
passed to the various gamma functions.
x <- rgamma(1000, 2, 2)
library(mhsmm)
qsh <- gammafit(x)$shape; qsc <- gammafit(x)$scale
> qsh
x
x 2.009260
> qsc
x
x 0.4827448
On Sep 4, 2009, at 11:59 AM, Petar Milin wrote:
Thank you very much for the answer!
However, instead of x being some uniform values, I have real values.
Hence, if I have dat$V1 of my interest, formula should be like this:
qqmath(~ V1, data=dat, distribution=function(V1) qgamma(V1,
shape=gammafit(dat$V1)$shape, scale=gammafit(dat$V1)$scale))
Is that correct?
(gammafit() from mhsmm package calculates parameters of gamma
function)
Thank you, again. Best,
PM
Duncan Murdoch wrote:
On 9/4/2009 8:36 AM, Petar Milin wrote:
Hello ALL!
Can anyone tell me how to specify qqmath() function with
distribution qgamma?
In help it is bit vague how to pass shape and scale parameters for
gamma.
Take a look at the first example, which passes in the df parameter
for a t distribution. You want something like
x <- runif(1000) # not a gamma, plot should look bad
qqmath(~ x, distribution=function(x) qgamma(x, shape=2, scale=2))
Duncan Murdoch
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
David Winsemius, MD
Heritage Laboratories
West Hartford, CT
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
