Fitting of Pearson Type III in R using fitdist

Question

I have fitted many distributions to my data but I am facing difficulty in fitting Pearson type III distribution to the data. I also used plotdist function to find starting or initial values in order to fit the distribution using iterative method.The plots obtained from plotdist shows that the plot is a good fit to data at the given starting values But fitdist function does not work and give error code of 100. I also studied the problems and answers available on stack overflow regarding fitting of log Pearson Type III distribution and applied the code but then again I am facing problem in running fitdist function and getting error code of 100 again. The data may be downloaded from the following link.

Lheadway <- pvr$headway+0.0000001

m <- mean(Lheadway)
v <- var(Lheadway)
s <- sd(Lheadway)
g <- e1071::skewness(Lheadway, type=1)

n <- length(Lheadway)
g <- g*(sqrt(n*(n-1))/(n-2))*(1+8.5/n)


my.shape <- (2/g)^2
#my.scale <- sqrt(v)/sqrt(my.shape)*sign(g) # modified as recommended by Carl Schwarz
my.scale <- sqrt(v)/sqrt(my.shape)*sign(g)
my.location <- m-sqrt(v * my.shape)

my.param <- list(shape=my.shape, scale=my.scale, location=my.location)


dPIII<-function(x, shape, location, scale) PearsonDS::dpearsonIII(x, shape, location, scale, log=FALSE)
pPIII<-function(q, shape, location, scale) PearsonDS::ppearsonIII(q, shape, location, scale, lower.tail = TRUE, log.p = FALSE)
qPIII<-function(p, shape, location, scale) PearsonDS::qpearsonIII(p, shape, location, scale, lower.tail = TRUE, log.p = FALSE)

fitPIII <- fitdistrplus::fitdist(Lheadway, distr="PIII", method="mle", start=my.param)

plot(fitPIII)

https://ptagovsa-my.sharepoint.com/:x:/g/personal/kkhan_tga_gov_sa/EfzCE5h0jexCkVw0Ak2S2_MBWf3WUywMd1izw41r0EsLeQ?e=EiqWDc

data is available at

Answer 1

The function works just by changing the method from mle to mse or mge and removing param argument from the code.