I am fitting a model using zeroinfl() and it runs without errors,
returning results that are generally consistent with my hypotheses.
One of my variables is percent black (pblack). This variable was highly
significant in some of the other count models I ran on the way to my
current formulation. It is not significant in this model. As such I
decided to try adding pblack^2 to the model to see whether the issue
might captured there (if it matters I created a new variable in my data
frame called pblacksqared and added that to the count portion of the
model only).
zeroinfl() runs just fine and pblack becomes significant and moves in
the appropriate direction once the new variable is added to the model.
However, pblacksquared is not significant, and while a coefficient is
generated, I get NA values for Std. Error, z value and Pr(>|z|). pblack
and pblacksquared are both positive and continuous with no missing values.
I can't find anything in the documentation about returning an NA value
here. Any suggestions as to where it comes from and how I might
interpret/remedy it?
Thanks,
Chris
