Volume 3 Supplement 1
Comparison of some linear regression methods – available in R – for a QSPR problem
© Varmuza and Filzmoser; licensee BioMed Central Ltd. 2009
Published: 05 June 2009
with for the predicted property and m the number of x-variables.
Efficient means that model generation is possible for data with more variables than objects, for data with highly correlating variables, and that the complexity of the model is optimized for best prediction performance (not necessarily for best fit).
The compared methods comprise PLS (partial least-squares) regression, robust PLS, PCR (principal component regression), ridge regression, and lasso regression as implemented in the free software system R  by the package "chemometrics" described in . The strategy "repeated double cross validation"  has been applied to optimize the model complexity (i.e. to find the optimum number of PLS components), and to estimate the prediction errors for new cases. The QSPR problem used is modeling the gas chromatographic retention indices of 209 polycyclic aromatic compounds characterized by 467 molecular descriptors.
- Software R: A language and environment for statistical computing, version 2.2.7. 2008, Vienna, Austria: R Development Core Team, Foundation for Statistical Computing, [http://www.r-project.org]Google Scholar
- Varmuza K, Filzmoser P: Introduction to multivariate statistical analysis in chemometrics. 2009, CRC Press, Boca Raton, FL, USA.View ArticleGoogle Scholar
This article is published under license to BioMed Central Ltd.