Hello everybody. I'm performing uncertainties analysis on my species distribution models. It accounts for Generalized Circular Models (GCMs), Representative Concentration Pathways (RCP) and algorithms. Some methods used on literature are ANOVA and GLM. However my data is not normal and is zero-inflated. I also need to map them, so I'm looking for sum of squares or deviance explained. I've been digging for solutions, but I hadn't much lucky. Any suggestions ??
If you have zero inflated data and your outcome is a count then you could make use of zero inflated poisson or negative binomial models.
Thanks a lot for your answer Mehmet.
I'm testing right now if my data fit negative binomial distribution. It seems so by the graphs, but the kolmogorov test is a bit uncertain because my data has some ties.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA