Results (
Vietnamese) 1:
[Copy]Copied!
One possible reason could be the relatively low number of presence points (from 13 to 26, Fig.4) in this work compared to previous studies. As a consequence of the reduced number of presence points, the models were highly sensitive to the training sample selection procedure, and hence the calculated AUC and Kappa values were highly variable (see error bars, Fig.3). This high variability was the most probable cause for the lack of any significant difference. Although the differences between both models were not significant, both statistics showed higher values for MAXENT for all four species studied and the correlation between MAXENT and the presence–absence models were always higher than with ENFA.
Being translated, please wait..