Multiblocks PCA

Aline_A16 — Thu, 22 Jun 2023 12:55:47 GMT

Hello,

I have 3 biofluids for which a group of fatty acids (almost the same in each biological matrice) have been measured, and i would like to use a reduction dimension method taking into account that variables are coming from 3 differents blocks (=biofluids). I already performed a simple PCA but i am trying to find a method that is more appropriate considering the 3 blocks aspect. I looked to the paper "A framework for sequential multiblock component methods" https://doi.org/10.1002/cem.811 but i am not able to fully understand the differences between each method and which one could suit my problematic. I would be grateful if someone could clarify this to me.

My main question : is there a method identical or closely similar to simple PCA but including the multiblocks concept ?

Thanks in advance.

Aline

Re: Multiblocks PCA

PaigeMiller — Thu, 22 Jun 2023 16:32:05 GMT

PROC CALIS may do this, but it is not something I could help with. Also, within the Partial Least Squares methodology, there are indeed multi-block models, I would imagine that this could be extended from multi-block PLS to multi-block PCA.

I know the lead author Age Smilde has done a lot of work in this area, maybe you should contact him directly.

topic Multiblocks PCA in Statistical Procedures

Multiblocks PCA

Re: Multiblocks PCA