To increase transparency, PeerJ operates a system of 'optional signed reviews and history'. This takes two forms: (1) peer reviewers are encouraged, but not required, to provide their names (if they do so, then their profile page records the articles they have reviewed), and (2) authors are given the option of reproducing their entire peer review history alongside their published article (in which case the complete peer review process is provided, including revisions, rebuttal letters and editor decision letters).
Thank you for attending to these changes quickly.
As you can see, both my reviewers like your paper and so do I. Please fix these minor problems and return the revision as soon as you can.
When PeerJ accepts a paper it gets published "as it is" (i.e. without further copyediting). I recommend that you use a programme such as Grammarly to check your English to ensure that it's the best it can be.
This article is well written and answers an very important question. The structure is clear and figures are relevant.
This study has a very good design. It carried out model evaluation with different measures and with two independent test datasets. So the comparison of models is legitimate. However, there are still some parts that the authors need to address. For the 21 variables that were selected to build models, you need to show if high correlation exists between some variables. The collinearity will influence the validity of your models. For the validation, please report detail number, percentage on how many test data are correctly predicted.
The data and methods used in the study are appropriate and valid.
I recommend to accept this paper with minor revisions. This paper answers a good question with a careful design.
The manuscript requires to be looked over and edited throughout for better english.
Line 158: Some additional information on how variables were reduced is necessary. Was there clear evidence that variables were not autocorrelated prior to running the models?
Line 177; also lines 213-214: A check to see if the pseudo-replicated points did not overlap with points obtained with satellite tracking will be important.
I like how the authors have included both the strengths and the shortcomings of their methods ensuring that the findings have high value for conservationists wishing to use the statistical methods described.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.