The Optimum Number of Latent Variables

  • Alejandro C. Olivieri


The relevant issue of optimizing the number of latent variables in full-spectral inverse models is discussed, with emphasis on interpretation rather on statistical and mathematical issues.


Latent variables Explained variance Loading inspection Leave-one-out cross validation Monte Carlo cross validation Physical interpretation 


  1. Arancibia, J.A., Rullo, A., Olivieri, A.C., Di Nezio, S., Pistonesi, M., Lista, A., Fernández Band, B.S.: Fast spectrophotometric determination of fluoride in ground waters by flow injection using partial least-squares calibration. Anal. Chim. Acta. 512, 157–163 (2004)CrossRefGoogle Scholar
  2. Faber, N.M., Rajko, R.: How to avoid over-fitting in multivariate calibration—the conventional validation approach and an alternative. Anal. Chim. Acta. 595, 98–106 (2007)CrossRefPubMedGoogle Scholar
  3. Goicoechea, H.C., Olivieri, A.C.: Determination of bromhexine in cough–cold syrups by absorption spectrophotometry and multivariate calibration using partial least-squares and hybrid linear analyses. Application of a novel method of wavelength selection. Talanta. 49, 793–800 (1999)CrossRefPubMedGoogle Scholar
  4. Method 4500 F D: Standard Methods for the Examination of Water and Wastewater, 20th edn, pp. 4–62. American Public Health Association, Washington, DC (1998)Google Scholar
  5. Thomas, E.V., Haaland, D.M.: Partial least-squares methods for spectral analyses. 1. Relation to other quantitative calibration methods and the extraction of qualitative information. Anal. Chem. 60, 1193–1202 (1988)CrossRefGoogle Scholar
  6. Xua, Q.S., Liang, Y.Z.: Monte Carlo cross validation. Chemom. Intell. Lab. Syst. 56, 1–11 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Alejandro C. Olivieri
    • 1
  1. 1.Universidad Nacional de Rosario, Instituto de Química Rosario - CONICETRosarioArgentina

Personalised recommendations