Partial Least Squares advice needed PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Dr Christopher JL Silwood posted on Wednesday, October 11, 2006 - 4:09 pm
I use spectroscopy to analyse chemical compounds generated from cooking oils. My data set comprises 6 oils, 5 material treatments, 3 timepoints. There would appear to be a range of tests here:
(a) correlation of membership category (X matrix) with either the spectra themselves or spectra-derived compound concentrations (Y matrix; I assume that this sort of category description is not appropriate for PLS-DA whereby membership constitutes the Y matrix instead), i.e. this would be an inverse regression; what contrast coefficients should I use for matrices combining time and material or time, material and oil; do I in fact exclude one set of category membership dummy variable columns as in more typical regression analyses? Is the use of Q2 and R2 and 70/30 training/validation sets appropriate here?);
(b) spectra (X) versus %fatty acid distribution or generated compound concentrations (Y, both are easily obtained from spectra for the calibration set) whereby I could compare PLS1 levels obtained from individual levels with those derived simultaneously (PLS2) from the whole lot;
(c) a PLS-DA analysis of spectral data (X) versus class membership based on, e.g. acceptable compound ingestible levels (Y), i.e. toxic (“1”) or non-toxic (“0”), again do I exclude one of these category membership columns?).
 Bengt O. Muthen posted on Wednesday, October 11, 2006 - 5:44 pm
I'm sorry but it sounds like this message ended up in the wrong discussion group. Mplus does not do "PLS-DA", and I don't understand spectroscopy in order to give suggestions.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: