Browse Prior Art Database

Object Oriented Technology to Improve Statistical Process in Process Modeling

IP.com Disclosure Number: IPCOM000114448D
Original Publication Date: 1994-Dec-01
Included in the Prior Art Database: 2005-Mar-28
Document File: 2 page(s) / 34K

Publishing Venue

IBM

Related People

Potok, TE: AUTHOR

Abstract

Disclosed is a method of creating a series of distribution objects for the commonly used distribution, e.g., normal, poisson, bionomial, etc., as a solution to the limited support of statistical distributions, which is a major drawback of using an Object Oriented (OO) language for process modelling. These distribution objects can then be used by any new object created for a process model. By doing this, every new object instance that is created contains distribution information.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 82% of the total text.

Object Oriented Technology to Improve Statistical Process in Process
Modeling

      Disclosed is a method of creating a series of distribution
objects for the commonly used distribution, e.g., normal, poisson,
bionomial, etc., as a solution to the limited support of statistical
distributions, which is a major drawback of using an Object Oriented
(OO) language for process modelling.  These distribution objects can
then be used by any new object created for a process model.  By doing
this, every new object instance that is created contains distribution
information.

      The detailed steps needed to create the distribution objects
and make them part of every new object created are as follows:
  1.  Create an object that can return values based on indices.  This
       type of object is normally thought of as an array or matrix.
  2.  Using a statistical hand book, load the object with probability
       densities at the corresponding distribution parameter values.
       For example, with a normal distribution, the probability
density
       values would form an array that would be indexed by the
       corresponding Z values.
  3.  Name the object according to the distribution that it
represents.
  4.  Create a class variable in the highest class within the
hierarchy
       that is used for process modelling.  This class variable must
       have the following characteristics:
      o  It can represent any...