I run the following:
library(actuar)
x <- seq(0, 22, 0.5)
fl <- discretize(plnorm(x, 2.1), from = 0, to = 22, step = 0.5, method
="lower")
Fs <- aggregateDist("recursive", model.freq =
"poisson",model.sev = fl,
lambda = 10, x.scale = 0.5)
Warning message:
In panjer(fx = model.sev, dist = dist, p0 = p0, x.scale = x.scale, :
maximum number of recursions reached before the probability distribution
was complete
# Should i be worried about the warning message.
# How do i choose the domain of the x function bearing in mind that the
original severity data was running in the interval(9 to 17). I had
achieved this interval by applying the natural log transformation on the
original severity data.
# i had obtained the parameters meanlog = 11.69 and sdlog=2.1. How do these
parameters feature when discretizing the log normal so as to apply it in
the aggregate disrtibution
# I also run following for the aggregate distribution as i had fitted the
negative binomial for the frequency distribution.
library(actuar)
x <- seq(0, 22, 0.5)
fl <- discretize(plnorm(x, 2.1), from = 0, to = 22, step = 0.5, method
="lower")
Fs <- aggregateDist("recursive", model.freq = "negative
binomial",model.sev
= fl, mu= 10, x.scale = 0.5)
Error in panjer(fx = model.sev, dist = dist, p0 = p0, x.scale = x.scale, :
value of 'prob' or 'size' missing
I also run the following as i wanted to use the convolution method for the
aggregate distribution:
library(actuar)
x <- seq(0, 22, 0.5)
fl <- discretize(plnorm(x, 2.1), from = 0, to = 22, step = 0.5, method
="lower")
Fs <- aggregateDist("convolution", model.freq = "negative
binomial",model.sev = fl, mu= 10, x.scale = 0.5)
Error in aggregateDist("convolution", model.freq = "negative
binomial", :
'model.freq' must be a vector of probabilities
Finally how do i deal with the natural log transformation i had applied
to the severity distribution when fitting the aggregate distribution noting
that the frequency distribution was fitted without the natural log
transformation.
Kindly assist.
Charles.
[[alternative HTML version deleted]]
