Click here to start

Table of contents

Slide 1

Basic Concepts

Basic Concepts (cont.)

Issues in diversity

Types of structural diversity

Small (< ca. 500) datasets of practical interest

Other small datasets

Questions of a structural diversity measure

Questions for a given dataset

Possibilities for quantitation

Some proposed database diversity measures


Diversity measures and modal fingerprints

Extend threshold analysis

Relative vs. absolute

Other measures derived from bits or similarities

Slide 17

Slide 18

Slide 19

Slide 20

Principal Components (n = 23, k = 18)

Rotated Factor Pattern (dissimilarities and ln)

Datasets Plotted vs. First Two Rotated Factors

Datasets plotted vs. mean modal dissimilarity (t=0.5) and average # bits


mean centr_dist



Conclusions to date


Correlations among diversity measures (n = 23)

Correlations (cont.)

Datasets plotted vs. mean pairwise dissimilarity and average # bits

Datasets plotted vs. mean centroid distance and average # bits

Slide 35

Best viewed with