Many methods in chemometrics rely on projection onto a subspace - they are also called bilinear or latent variable methods. A very interesting article on this ropic appeared in Journal of Chemometrics . Written by experienced chemometricians, this paper presents principal components analysis (PCA), partial least squares (PLS), hierarchical PCA and PLS, PLS-discriminant analysis, Orthogonal projection to latent structures (OPLS), OPLS-discriminant analysis and more, from a special and unusual point of view. Must read for every chemometrician!
- L. Eriksson, J. Trygg, and S. Wold, "A chemometrics toolbox based on projections and latent variables", Journal of Chemometrics, vol. 28, pp. 332-346, 2014. http://dx.doi.org/10.1002/cem.2581