2

I would like to know whether it is possible to know what feature of a data set mostly contribute to the classification performed by linear discriminant analyses.

To make my question clearer, let’s take the example available in Matlab: the Fisher’s iris data.

Each row of the data set fisheriris contains a sample of an iris flower and the columns a value for: Sepal length, Sepal width, Petal length, Petal width.

I would like to know which feature (Sepal length or width or petal length) the most contribute in the classification of a sample of iris as setosa or virginica.

Can I obtain this information using classify or fitcdiscr?

I hope that my question is clear.

Thank you for your help,

ttnphns
  • 51,648
  • 40
  • 253
  • 462
Andesa
  • 21
  • 2
  • [Here is](https://stats.stackexchange.com/a/83114/3277) discriminant analysis of iris data. [Here is](https://stats.stackexchange.com/a/48859/3277) the algebra of linear DA. Discriminant analysis classifies by the discriminants it extracts from the data. Discriminants are linear combinations the variables. There are two types of coefficients which relate the discriminants and the variables: the discr. coefficients and the correlations. Both coefficients convey information of how "important" a variable in discriminating the groups (and hence, in classifying). – ttnphns Nov 08 '17 at 15:22
  • @ttnphns, thank you for the links. But how do I obtain this information in Matlab when I use classify or fitdiscr? – Andesa Nov 08 '17 at 15:48
  • Program-specific questions (how to ask for this or that output or how to code) are off-topic on CV. – ttnphns Nov 08 '17 at 17:04

0 Answers0