A Multivariable Regression Algorithm

Abstract

A BASIC algorithm has been developed that is capable of fitting a user-defined regression equation to a set of data. This best-fit-curve algorithm is unique in that it allows multiple variables and multiple forms (exponential, trigonometric, logarithmic, etc.) to be present in a single regression equation. The least-squares regression performed determines the constants for each of the regression equation terms to provide a best-fit curve. Other programs within the algorithm set allow for data entry, editing and print-out, and plotting of the raw data and their best-fit regression curve.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1983
Accession Number
ADA136630

Entities

People

  • George L. Blaisdell
  • Todd Carpenter

Organizations

  • Cold Regions Research and Engineering Laboratory

Tags

Communities of Interest

  • Energy and Power Technologies
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Computer Programming
  • Computer Programs
  • Computers
  • Curve Fitting
  • Data Analysis
  • Equations
  • Experimental Data
  • Hard Copy
  • Heat Flux
  • Heat Transfer
  • Least Squares Method
  • Mass Storage
  • Plotting
  • Polynomials
  • Simultaneous Equations
  • Thermal Conductivity

Readers

  • Approximation Theory.
  • Computer Science.