Journal of Chemometrics

Cover image for Journal of Chemometrics

January 2011

Volume 25, Issue 1

Pages 1–49

  1. Research Articles

    1. Top of page
    2. Research Articles
    1. 3D superposition of chemical fragments for N-membered rings: application to conformational analysis (pages 1–9)

      Mathieu Kessler and José Pérez

      Article first published online: 22 OCT 2010 | DOI: 10.1002/cem.1338

      A procedure is suggested for the 3D superposition of chemical fragments, which is specifically designed for rings molecules and can be combined with statistical multivariate procedures to extract useful conformational information. The procedure relies on the plane introduced by Cremer and Pople to define the celebrated puckering coordinates, and provides a measure of distance between two geometrical conformations.

    2. Genetic algorithm-based wavelength selection method for spectral calibration (pages 10–19)

      Masamoto Arakawa, Yosuke Yamashita and Kimito Funatsu

      Article first published online: 1 SEP 2010 | DOI: 10.1002/cem.1339

      We propose a genetic algorithm-based wavelength selection method (GAWLS) for visible and near infrared spectral calibration. The objective of GAWLS is to construct robust and predictive regression models by selecting informative wavelength regions. To demonstrate the ability of the proposed method, regression models for soil properties and sugar content of apples are constructed by using GAWLS and other variable selection methods.

    3. Comparison of PARAFAC and PARALIND in modeling three-way fluorescence data array with special linear dependences in three modes: a case study in 2-naphthol (pages 20–27)

      Hao Chen, Binghui Zheng and Yonghui Song

      Article first published online: 25 SEP 2010 | DOI: 10.1002/cem.1340

      Three-mode fluorescence excitation–emission matrices of 2-naphthol having excited-state proton transfer are fit to three factors using standard PARAFAC and PARAFAC with linear dependencies (PARALIND) with three different types of constraints imposed in the modes during the fitting, respectively. Two PARALIND models (type 1 and type 2) do not correctly fit the data but PARAFAC and one PARALIND (type 3) do. Very different core consistency values are reported for PARAFAC and the type 3 PARALIND.

    4. Path modelling by sequential PLS regression (pages 28–40)

      T. Næs, O. Tomic, B.-H. Mevik and H. Martens

      Article first published online: 29 DEC 2010 | DOI: 10.1002/cem.1357

      This paper presents a new approach to path modelling, based on a sequential multi-block modelling in latent variables. Each separate model is constructed by stepwise use of the standard PLS regression on matrices that are orthogonalised with respect to each other. The advantage is that the method can allow for different dimensionality within each block, it is invariant to relative weighting of the blocks and is based on simple and standard methodology allowing for simple outlier detection, validation and interpretation.

    5. Variation in likelihood ratios for forensic evidence evaluation of XTC tablets comparison (pages 41–49)

      Annabel Bolck and Ivo Alberink

      Article first published online: 29 DEC 2010 | DOI: 10.1002/cem.1361

      In forensic comparison casework Q3 Q3, where it is investigated whether items are from the same source, the likelihood ratio (LR) is a measure for evaluating the strength of evidence of the observed (dis)similarity between these items. The paper concentrates on evaluation of various LR models for comparison of XTC tablets from different seizures. Starting from a two-level random effect model, where means are considered random, the distribution of these means may be assumed normal or approximated by kernel density estimations (KDEs), and measurement errors may or may not be allowed to differ per batch. It is investigated what effect the corresponding model and estimation choices have on the distribution of LRs for same- and different-batch comparisons.