Advertisement

Regression and Model Fitting with Collinearity

  • Scott Pardo
Chapter
  • 73 Downloads

Abstract

Ordinary least squares does not work when there are more regressors than observations. Several methods can be used to build a (linear) predictive model when there are too few observations or when regressors are correlated with each other.

Keywords

Ordinary least squares Partial least squares Ridge regression LASSO 

Reference

  1. Strang G (1980) Linear algebra and its applications, 2nd. edn. Academic Press, New YorkzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Scott Pardo
    • 1
  1. 1.Global Medical & Clinical AffairsAscensia Diabetes CareValhallaUSA

Personalised recommendations