Class ColtBinomialSelector

  • All Implemented Interfaces:
    java.lang.Cloneable, Actor, Executable, FiringsRecordable, Initializable, TypedActor, Changeable, Debuggable, DebugListener, Derivable, Instantiable, ModelErrorHandler, MoMLExportable, Moveable, Nameable

    public class ColtBinomialSelector
    extends ColtRandomSource
    Assign trials from several populations using a conditional Binomial selection process. For example, if a vector of P populations are presented (as P input channels) and N trials is specified, then this algorithm will distribute the N trials based on the proportions represented in the P populations. This is done by performing a progressively conditional Binomial selection in which n and p change after each trial assignment step. The Binomial trials (n) is decremented after each assignment step to represent the remaining trials, and the new Binomial probability (p) is calculated based on the populations that remain eligible for selection.

    A new set of trial assignments is produced for each iteration and will not change until the next iteration. The values that are generated are independent and the expected values of the assignments will have expected values that are representative of the population proportions.

    Since:
    Ptolemy II 6.0
    Version:
    $Id$
    Author:
    Raymond A. Cardillo, Matthew J. Robbins, Contributors: Jason Smith and Brian Hudson
    See Also:
    ColtBinomial, Binomial
    Pt.AcceptedRating:
    Red (cxh)
    Pt.ProposedRating:
    Red (cxh)