Encyclopedic Dictionary of Polymers

2011 Edition
| Editors: Jan W. Gooch

Regression Analysis

  • Jan W. Gooch
Reference work entry
DOI: https://doi.org/10.1007/978-1-4419-6247-8_9880

n (method of least squares) A family of statistical techniques for fitting equations to data based on the principle that the best-fitting parameters are those that minimize the sum of squares of the differences between the original observations and the corresponding equation values. A simple case is fitting a straight line to a set of data (xi, yi) to obtain the equation ŷ = a + bċx. Multiple linear regression includes the application of the least-squares principle to any form of relationship between a dependent variable y and several “independent” Factors x1i, x2i,…xki, or explicit functions of the xji, that is “linear with respect to the constants to be fitted.” Nonlinear regression, which requires one or another iterative-search method, deals with relationships that are not linear in the constants sought. Powerful programs for all these techniques are now available for personal computers. Regression equations provide the vehicle for estimating the outcomes of future experiments in...

This is a preview of subscription content, log in to check access.

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Jan W. Gooch
    • 1
  1. 1.AtlantaUSA