Continuing the discussion from Evident: Effect size and power calculations for microbiome community data:
@gibsramen and others, I am hoping you can help me with an error I can't resolve when trying to use Evident. My issue is similar to a previous issue (q2-evident: repeated measures).
I am trying to conduct a power analysis based on previously collected data. I receive the same error whether I am trying to run the multivariate analysis or univariate analysis, so it is not an issue unique to the command I am running. Though I have tried many iterations, the most recent command I am using is:
qiime evident multivariate-power-analysis
--i-data 06_core-metrics/9204-sepp-core-metrics2/generalized-unifrac05-distance-matrix.qza
--m-sample-metadata-file 03_metadata/metadata_all-samples-good-poweranalysis.txt
--p-group-column event_room
--p-alpha 0.01 0.05 0.1
--p-total-observations $(seq 10 10 300)
--o-power-analysis-results power_room_unifrac05_time.qza
This gives me an error:
Plugin error from evident:
'event_room'
This error was previously seen in the forum post I referenced above, with the solution being that the evident package does not work on numeric data. However, the event_room data column I have included is categorical, so that is a different issue than the previous solution. I have tried several different metadata columns just in case, but I receive the same error regardless. I have also tried using this under several versions of QIIME2, including 2022.11 as suggested on the Github
Can you offer me any potential solutions? Also, since it has been 2 years since the previous post, is there any update on using this tool for numerical data?
Thanks!!!