The importance of outlier detection and training set selection for reliable environmental QSAR predictions.

@article{Furusj2006TheIO,
  title={The importance of outlier detection and training set selection for reliable environmental QSAR predictions.},
  author={Erik Furusj{\"o} and Anders Svenson and Magnus Rahmberg and Magnus Andersson},
  journal={Chemosphere},
  year={2006},
  volume={63 1},
  pages={99-108}
}
Empirical QSAR models are only valid in the domain they were trained and validated. Application of the model to substances outside the domain of the model can lead to grossly erroneous predictions. Partial least squares (PLS) regression provides tools for prediction diagnostics that can be used to decide whether or not a substance is within the model domain, i.e. if the model prediction can be trusted. QSAR models for four different environmental end-points are used to demonstrate the… CONTINUE READING

From This Paper

Topics from this paper.
24 Citations
0 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

Similar Papers

Loading similar papers…