In discriminant analysis you use a group of quantitative variables to discriminate experimental units in two groups (or more than 2 in Canonical Discriminant Analysis).
Is this the kind of help you were looking for?
Discriminant function analysis is a statistical analysis to predict a categorical dependent variable (called a grouping variable) by one or more continuous or binary independent variables (called predictor variables). Discriminant analysis is used when groups are known beforhand. Each case must have a score on one or more quantitative predictor measures, and a score on a group measure. In simple terms, discriminant function analysis is classification - the act of distributing things into groups, classes or categories of the same type
Please, find hereafter one of my papers, published into CSBIGS that could be used as an introduction to discriminant analysis.
http://www.bentley.edu/centers/sites/www.bentley.edu.centers/files/csbigs/Desbois.pdf
You can find on page 68 the way discriminant scores are computed and their interpretation.
In this paper, the discriminant analysis is processed under the SPSS package but you can find similar functions in any other good statistical package, including other professional ones (e.g. SAS), or academic ones (e.g. R).
This paper encompass a comparison with logistic regression, performed by the means of ROC curves.
Beware that several types of discriminant analysis can be used : linear, quadratic, bayesian, etc. Each of them achieves a specific purpose of discrimination.
Hereafter, please find an example of using Linear Discriminant Analysis function (lda) with the MASS library in R:
> library("MASS") # load the MASS library
> wine.lda
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics