I have performed chemical analysis on a sample and the resulting data is something like this: "Carbon: 1.2%, Iron: 50%, Vanadium 2.3% ..." and so on.

I have 25 sets of similar data taken from other samples and I need to figure out which of these 25 sets matches the first one the best i.e., which has the closest chemical composition to the sample.

This is probably a very simple problem but I have not studied statistics. I tried to use Pearson correlation but I'm not sure this is the right tool for this specific problem.

  • $\begingroup$ Clustering? or better, graphical methods. Make a plot with the relative percentages? Or look into "compositional methods" which was made for this kind of situation. Or, maybe some kind of correspondence analysis could be used! $\endgroup$ – kjetil b halvorsen Jun 1 '16 at 18:45
  • $\begingroup$ You could also post your data as a table in the original post. Could be interesting to have a look! $\endgroup$ – kjetil b halvorsen Jun 1 '16 at 18:47
  • $\begingroup$ Have a look at: onlinelibrary.wiley.com/doi/10.1002/9781119976462.ch8/summary $\endgroup$ – kjetil b halvorsen Jun 1 '16 at 19:41

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.