Skip to main content
Metabolomics Society Forum
Topic: Dealing with outliers...
(Read 48 times)
Joined: 10 July, 2018
Phone number: 4789972299
Dealing with outliers...
July 10, 2018, 09:52:33 PM
I was checking my data quality before running PCA/PLS, but am confused by different articles I've read concerning this. Basically they say that Hotelling's T
identifies severe outliers, and DModX identifies moderate outliers.
What I am seeing in my data:
-My QC's all cluster to the center of a PCA
- I have some samples located outside the Hotelling's T
- Depending on how many PCA components I include in the DModX plot, I get different samples that are larger than the D-Crit value.
- How should I decide on how many PCA components to include in the DModX?
- Should I remove all outliers detected by the DModX graph and the Hotelling's T
plot from my data set to prevent skewing of my PCA/PLS?
- Is it possible that the outliers could be of interest and I should leave them in further analysis?
I really appreciate any and all advice!!!!
Washington State University Institute of Biological Sciences
powered by ElkArte 1.0.7
SimplePortal 1.0.0 Beta 1 © 2008-2014