R help - Jul 2013 - percent correctly predicted (PCP) zeros for hurdle model

Hello all,

I am using the hurdle model for fitting my count data using the pscl package
which is working fine. However, I am stuck with the problem of calculating
the percent correctly predicted (PCP) zeros for hurdle model. The method I
am trying to use to achieve this is 'hitmiss' in the pscl package (ref:
http://www.inside-r.org/packages/cran/pscl/docs/hitmiss).

When I do:
> hitmiss(hnegbin1)              #hnegbin is the hurdle model

I get the following error:

Error in UseMethod("hitmiss") :
  no applicable method for 'hitmiss' applied to an object of class
"hurdle"


FYI, equation I used for building hurdle model:

 hurdle(formula = Y ~ X | X, dist = "negbin", zero.dist =
"binomial")


Could someone please let me know what I am doing wrong? Thanks!

	[[alternative HTML version deleted]]