Overcoming Multicollinearity in Near Infrared Analysis for Lycopene Content Estimation in Tomatoes by Using Ridge Regression

H. Pasternak, Z. Schmilovitch, E. Fallik, Y. Edan

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

High intercorrelation between absorbance at different wavelengths is common in near infrared analysis and was observed in an experiment to determine lycopene in tomatoes. Simulation analysis and experiments were conducted to estimate the effects of this problem on the estimators and on the predictive ability of linear regression and ridge regression. Applying linear regression to the experimental data resulted in very large parameter values, implying poor predictive ability. When linear regression gives very large parameter values, the estimated parameters are practically random numbers and are not correlated to the true ones. Ridge regression yielded estimators with normal values, but which are still poorly correlated with the true parameters. However, the predictive ability of the derived equation is good and may be used in practice to determine lycopene content in tomatoes since it is relatively easy to update.

Original languageEnglish
Pages (from-to)60-66
Number of pages7
JournalJournal of Testing and Evaluation
Volume29
Issue number1
DOIs
StatePublished - 1 Jan 2001

Keywords

  • Linear regression
  • Lycopene
  • Multicollinearity
  • Near infrared spectroscopy
  • Ridge regression
  • Tomato

Fingerprint

Dive into the research topics of 'Overcoming Multicollinearity in Near Infrared Analysis for Lycopene Content Estimation in Tomatoes by Using Ridge Regression'. Together they form a unique fingerprint.

Cite this