Hello! I am currently doing GARP species distribution models. However, I can't find a clear paper about the model's assumptions on what the input data should be or how should they behave.
For example, is it necessary that environmental data are normally distributed? Or that data should follow a certain function (e.g. logistic or linear)?
Thank you for your answers!
Xinhai Li David Eugene Booth Thanks to both of you!
I'm really wondering about this since most GARP/Maxent studies I've read make use of Pearson correlation to test for multicollinearity among explanatory variables. Pearson assumes normality in the variables to be tested, which led me to think that maybe normality is required for the model as well...?
I mean, how were they able to use Pearson correlation coefficient if the variables are non-parametric?
Pearson correlation does not require normality for the correlation coefficients calculations but only for Statisical inference. Check the attachment and download the book from the z-library. Best wishes David Booth
By the way correlations coefficient is a very poor way to test multicollinearity. VIF is much preferred. See the attachment. Best wishes, David Booth
https://www.garp.org/membership/chapters/meetings/time-series-analysis-and-forecasting,kindly check this link.
https://www.garp.org/membership/chapters/meetings/time-series-analysis-and-forecasting,u can follow this link.
https://onlinelibrary.wiley.com/doi/full/10.1111/ecog.05642,this link may be useful.
GARP is classified as a machine learning algorithm, and it is like a nonparametric model. It does not need the normality of explanatory variables, nor the linear or logistic X-Y relationship. It uses the same format of data as Maxent.
- Badges
- Science topic