bblonder
commented
7 years ago Hi Dan - glad you like it. You could consider calculating the mean network degree (for the positive links). However I don't think it is going to be easy to collapse a whole network down to a single number...
Ben
On Tue, Apr 4, 2017 at 2:31 AM, Dan McGlinn notifications@github.com wrote:
Hey @bblonder https://github.com/bblonder thanks for this great package! I'm curious if you have thought much about how to reduce down the information from your analysis to a single number that suggests the degree of species association on average in the community. This would be really useful for comparing communities to see if their degrees of association differ. Traditionally folks have suggested the variance ratio (V = summed covariance / expected variance) which has problems but is nice in that it is a single community wide statistic.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/bblonder/netassoc/issues/1, or mute the thread https://github.com/notifications/unsubscribe-auth/AAnvPyH_f2i_BXxBswzhZ1aK3Dr8K89qks5rsY98gaJpZM4MyQT9 .
-- Benjamin Blonder Environmental Change Institute School of Geography and the Environment University of Oxford
Website + photoblog: http://www.benjaminblonder.org Google Scholar: http://scholar.google.com/citations?user=l3FNoE8AAAAJ University of Arizona Sky School: https://skyschool.arizona.edu/
dmcglinn
Hey @bblonder thanks for this great package! I'm curious if you have thought much about how to reduce down the information from your analysis to a single number that suggests the degree of species association on average in the community. This would be really useful for comparing communities to see if their degrees of association differ. Traditionally folks have suggested the variance ratio (V = summed covariance / expected variance) which has problems but is nice in that it is a single community wide statistic.