[R] Zero Inflated Distributions

[vioravis]

Thanks, Thierry.  

Has anyone used the "bayescount" for estimating zero inflated distributions?
It states that it is a "crude function". Does that mean the estimates are
only approximate???

The example they have given seems to work only with Gamma Poisson.

data <- rpois(100, rgamma(100, shape=1, scale=8))
data[1:15] <- 0
maximise.likelihood(data, "ZIGP")

However, when I tried fitting Gamma/LogNormal/Weibull (assuming that data is
continuous), it throws out the following error:


           shape           scale           zi
            9.532           4               21              
                                                         
Error in optim(c(shape, scale, zi), f6, control = list(fnscale = -1)) : 
  function cannot be evaluated at initial parameters

What is this error about???

Moreover, the function seems extremely slow. For the 100 data point example
considered, it takes around 8 seconds for the estimation. 

Please let me know your opinions on this package and alternative packages,
if any.

Thank you.

Ravi

--
View this message in context: http://r.789695.n4.nabble.com/Zero-Inflated-Distributions-tp3334861p3335122.html
Sent from the R help mailing list archive at Nabble.com.