We have a poolof hairs (around 10 for each reference sample coming from one individual) representing 15 individuals (e.g.).
We can characterize each of them by microscopy for several morphological characters, and by microspectrophotometry for colours informations.
These methods results for each hair in one set of discontinuous/qualitative data (morphological characters) and for the same hair in one set of continuous/quantitative data (colours informations). We can analyze them separately. That is not a problem.
But how can we analyse the two sets in a pooled matrix (combining qualitative and quantitative data) following a standardized protocol (that could be reused latter, like that)?
The questions we need to answer are :
- to test if all hairs coming from the same people cluster in the same group;
- for an unknown sample (of one hair at minimum), to search the group from which is the closest;
- and of course, to have a statistical estimation of the validity of the clusters or the similarity between unknown hairs and the closest clusters.
What is the best way to do that and the best software easy to use? (like XlStat?)
Thank you for your suggestions and ideas.
Hi all,
After searching and some testing it seems to me that the protocol should include first a multiple factor analysis of mixed data followed by some kind of clustering (but which will be the best?). This should solve the first question and probably also the last one.
But how to attribute one new samples to the cluster previously defined?
Hi all,
After some tests and research, it seems that the Factorial Analysis of Mixed Data ("Analyse Factorielle des Données Mixtes") could answer to my question.
See here http://data-mining-tutorials.blogspot.com/2013/03/factor-analysis-for-mixed-data.html and (in french) here http://www.agro-montpellier.fr/sfds/CD/textes/pages1.pdf
Several softs and program could run that but one very useful for exploration of data is TANAGRA. It propose also a tutorial for an automatic classification on mixed data which allow the subsequent classification of a new sample. And this works rather fine :-)
May be you could have some other idea. Feel free to share them. On my side, I will close this question for the moment.
I think the Taguchi-Maharanobis strategy is proper for your inquiry.
We consider each reference samples as each classes and one individual as the other class. This is the same as one-class SVM.
I developed the optimal LDF on the minimum number of misclassisications (MNM).
We discriminate the data consists of reference samples with one individual.
We evaluate the discriminant scores by obtained LDFs and choose reference calass with the most biggest t-value.
I am willing to co-work.
- Badges
- Science topic