This paper describes some of the deflation problems in multiblock PLS. Deflation of X using block scores leads to inferior prediction of Y . Deflation of X using super scores gives the same predictions as standard PLS with all variables in one large X ‐block, but the information of the separate blocks gets mixed up owing to the deflation of X . If Y is deflated using the super score instead, these problems disappear.
No takes yet. Share an insight, caveat, or question.
Westerhuis et al. (2001) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: