Abstract
The k points in p-space corresponding to a specified set of k ( k < p) linearly independent endmember estimates associated with a p-variate ( n × p) compositional dataset X, define the vertices of a ( k − 1) dimensional simplex H. The n estimated mixtures Y ( n × p) which together account for the systematic variation in the dataset X, each should be convex combinations of the k fixed endmember estimates. Accordingly, the n points in p-space which represent these mixtures should be interior points of the simplex H. This paper sets out a FORTRAN algorithm for expanding H by moving nonextreme vertices outwards in the situation that not all the points which represent the mixtures are interior points of H, as required.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call