An Application of the H-Function to Curve-Fitting and Density Estimation.

Abstract

The H-function is the most general special function, encompassing as specific cases many mathematical functions and nearly every continuous statistical distribution defined over positive x. A general procedure is developed to estimate the parameters of the H-function which gives the best fit to a set of data. The technique creates a system of nonlinear equations from the method of moments and uses Powell's quasi-Newton hybrid algorithm to solve the equations. A computer program, which can accept both raw data or previously calculated moments, implements the general process. Several new theoretical results are also presented. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1983
Accession Number
ADA141045

Entities

People

  • C. D. Bodenschatz
  • R. A. Boedigheimer

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Air Platforms
  • C4I
  • Cyber
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Computational Science
  • Computer Programs
  • Computers
  • Contour Integrals
  • Curve Fitting
  • Distribution Functions
  • Mathematics
  • Maximum Likelihood Estimation
  • Numerical Analysis
  • Probability
  • Probability Density Functions
  • Probability Distributions
  • Random Variables
  • Statistical Analysis
  • Statistical Distributions
  • Statistical Functions

Fields of Study

  • Mathematics

Readers

  • Approximation Theory.
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Operations Research