On Wed, 12 Mar 2014, Tim Marcella wrote:
Hi,
My data is characterized by many zeros (82%) and overdispersion. I have
chosen to model with hurdle regression (pscl package) with a negative
binomial distribution for the count data. In an effort to validate the
model I would like to calculate the R
Dear Tim,
I think that in this paper you would find a suite of different metrics
to evaluate your hurdle model:
Potts, Joanne M., and Jane Elith. "Comparing species abundance models."
Ecological Modelling 199.2 (2006): 153-163.
Best regards,
David March
El 12/03/2014 18:55, Tim Marcella escr
Hi,
My data is characterized by many zeros (82%) and overdispersion. I have
chosen to model with hurdle regression (pscl package) with a negative
binomial distribution for the count data. In an effort to validate the
model I would like to calculate the RMSE of the predicted vs. the observed
values
3 matches
Mail list logo