Hi! I have a sample size (n=45). I want to perform principal component analysis to group related data and have already done the required test for this analysis, the Bartlett test of Sphericity and KMO. The problem is KMO=~0.4 while the Bartlett test of Sphericity was significant (p<0.05). The data was about C content under land-use effects. I know that KMO needs to be more than 0.5, and closer to 1 is the best, but my question is, why Sphericity was significant for this data while KMO was not? I tried to exclude some data under specific factor effects (e.g., fertilizers) to see any differences in KMO value, but still KMO lower than 0.5! I tried to see the PCA results and already showed a clear cluster within each PC with an eigenvalue value (>0.7). Is the PCA valid for this type of data or not?
Thanks in advance!
This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.
If you have a query related to it or one of the replies, start a new topic and refer back with a link.