Centroid estimation in discrete high-dimensional spaces with applications in biology

1. 

   View larger version:

   • In this window
   • In a new window

   • Download as PowerPoint Slide

   Fig. 1.

   Simple probability space and two different estimators: black point L(1, 1, 1) has probability p ₁ and is the ML estimate; gray points have probability p ₂ as labeled, with p ₂ < p ₁ < 2p ₂, including C(0, 0, 0), and white, unshaded points have zero probability.

   
   
2. 

   View larger version:

   • In this window
   • In a new window

   • Download as PowerPoint Slide

   Fig. 2.

   Multidimensional scaled distribution (A) and histogram of distances to cluster 2 centroid (B) derived from 1,000 representative samples from Sfold for the secondary structure of Dermocarpa sp. ribonuclease P RNA.