Open Access Repository

Error measures in quantitative structure-retention relationships studies

Taraji, M, Haddad, PR, Amos, RIJ ORCID: 0000-0002-8642-4909, Talebi, M ORCID: 0000-0003-0593-4198, Szucs, R, Dolan, JW and Pohl, CA 2017 , 'Error measures in quantitative structure-retention relationships studies' , Journal of Chromatography A, vol. 1524 , pp. 298-302 , doi: 10.1016/j.chroma.2017.09.050.

Full text not available from this repository.

Abstract

An analysis and comparison of the use of four commonly used error measures (mean absolute error, percentage mean absolute error, root mean square error, and percentage root mean square error) for evaluating the predictive ability of quantitative structure-retention relationships (QSRR) models is reported. These error measures are used for reporting errors in the prediction of retention time of external test analytes, that is, analytes not employed during model development. The error-based validation metrics were compared using a simple descriptive statistic, the sum of squared residuals (SSR) of outliers to the edge of an error window. The comparisons demonstrate that Percentage Root Mean Squared Error of Prediction (RMSEP) provides the best estimate of the predictive ability of a QSRR model, having the lowest SSR value of 20.43.

Item Type: Article
Authors/Creators:Taraji, M and Haddad, PR and Amos, RIJ and Talebi, M and Szucs, R and Dolan, JW and Pohl, CA
Keywords: QSRR modelling, external validation, prediction error measures, root mean squared error of prediction
Journal or Publication Title: Journal of Chromatography A
Publisher: Elsevier Science Bv
ISSN: 0021-9673
DOI / ID Number: 10.1016/j.chroma.2017.09.050
Copyright Information:

Copyright 2017 Crown Copyright. Published by Elsevier B.V.

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP