-
Notifications
You must be signed in to change notification settings - Fork 97
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Missing (or NA) data for PERMANOVA #319
Comments
It seems The Alternatively, you can have listwise deletion of missing values using library(vegan)
data(dune, dune.env)
z <- dune.env
z[12,5] <- NA # one missing value
k <- complete.cases(z) # FALSE for rows with NA
adonis(dune[k,] ~ ., z[k,]) # use complete.cases as row selector |
The documented behaviour was accidentally and silently changed to always making pairwise deletion of missing values with internal speed up of C code (commit 3aeeb1d 2016-09-06, released in vegan 2.4-2 2017-01-17). Now we stop with error (like documented). See also my comment in GitHub issue #319. (cherry picked from commit 2e9969a)
For the record: commit messages 2e9969a (and cherry-picked f4d5cae) suggest that |
I've searched around the threads on here and am not sure I am able to find what I'm looking for. I am hoping to use PERMANOVA to run my analysis, but I do have missing values. I don't seem to be able to run vegdist, adonis, or other related functions with blanks or NA. Is there any way around this?
The text was updated successfully, but these errors were encountered: