Skip to main content

Clustering and Classification methods for Biologists

---

Discriminant Analysis

• Contents
• Analyses
• Resources
• Sponsors
• Accessibility
• Legal Notice
• Comments
• Contact me

Page Outline

• PCA
• Discriminant Analysis
• DA SAQ
• Home

 

Search

options

Iris Data : Discriminant Analysis 3 (PC pedictors)

PCA of the 4 predictors

Total Variance Explained

	Initial Eigenvalues			Extraction Sums of Squared Loadings
Component	Total	% Variance	Cumulative %	Total	% Variance	Cumulative %
1	2.918	72.962	72.962	2.918	72.962	72.962
2	0.914	22.851	95.813	0.914	22.851	95.813
3	0.147	3.669	99.482
4	0.021	.518	100.000

 

Component Matrix

	Component
	1	2
SEPAL_L	0.890	0.361
SEPAL_W	-0.460	0.883
PETAL_L	0.992	0.023
PETAL_W	0.965	0.064

 

top

---

Discriminant Analysis using the PCA scores

Summary of Canonical Discriminant Functions

Eigenvalues

Function	Eigenvalue	% of Variance	Cumulative %	Canonical Correlation
1	17.562	99.0	99.0	0.973
2	0.182	1.0	100.0	0.393

Wilks' Lambda

Test of Function(s)	Wilks' Lambda	Chi-square	df	Sig.
1 through 2	0.046	452.482	4	0.000
2	0.846	24.536	1	0.000

 

Standardized Canonical Discriminant Function Coefficients

	Function
	1	2
PC1	1.094	0.034
PC2	-0.474	0.986

 

Structure Matrix

	Function
	1	2
PC1	0.901	0.434
PC2	-0.031	1.000

 

Functions at Group Centroids

	Function
SPECIES	1	2
I.setosa	-5.669	0.154
I.versicolor	1.526	-0.577
I.virginica	4.143	0.423

 

Classification Statistics

Classification Results

			Predicted Group Membership			Total
		SPECIES	I.setosa	I.versicolor	I.virginica
Original	Count	I.setosa	50	0	0	50
		I.versicolor	0	45	5	50
		I.virginica	0	5	45	50
	%	I.setosa	100.0	.0	.0	100
		I.versicolor	.0	90.0	10.0	100
		I.virginica	.0	10.0	90.0	100
Cross-validated	Count	I.setosa	50	0	0	50
		I.versicolor	0	44	6	50
		I.virginica	0	5	45	50
	%	I.setosa	100.0	.0	.0	100
		I.versicolor	.0	88.0	12.0	100
		I.virginica	.0	10.0	90.0	100

top

---