Journal of Chemometrics

Cover image for Vol. 25 Issue 9

September 2011

Volume 25, Issue 9

Pages 467–525

  1. Research Articles

    1. Top of page
    2. Research Articles
    1. Multiblock redundancy analysis: interpretation tools and application in epidemiology (pages 467–475)

      Stéphanie Bougeard, El Mostafa Qannari and Nicolas Rose

      Version of Record online: 29 APR 2011 | DOI: 10.1002/cem.1392

      For the purpose of exploring and modeling the relationships between a dataset and several datasets measured on the same individuals, multiblock Partial Least Squares is a regression technique which is widely used, particularly in process monitoring, chemometrics and sensometrics. In the same vein, an new multiblock method, called multiblock Redundancy Analysis, is proposed. Multiblock modeling methods provide to the user a large spectrum of interpretation indices for the investigation of the relationships among variables and among datasets.

    2. Dissimilarity representation on functional spectral data for classification (pages 476–486)

      Diana Porro-Muñoz, Isneri Talavera, Robert P. W. Duin, Noslen Hernández and Mauricio Orozco-Alzate

      Version of Record online: 29 APR 2011 | DOI: 10.1002/cem.1393

      Spectral data are typically represented by vectors of features, despite their functional nature. In the representation, this functional information that can be essential for discrimination is thereby not reflected. In this paper, we demonstrate the importance of reflecting the functional characteristics of chemical spectral data in their representation, by comparing approaches that take this information into account i.e. Functional Data analysis and Dissimilarity Representation; for this purpose we also introduced the combination of these two approaches, which improves the classification results.

    3. Chemometrics in fuel science: demonstration of the feasibility of chemometrics analyses applied to physicochemical parameters to screen solvent tracers in Brazilian commercial gasoline (pages 487–495)

      Guilherme Tsuguio Tanaka, Fabrício de Oliveira Ferreira, Carlos Eduardo Ferreira da Silva, Danilo Luiz Flumignan and José Eduardo de Oliveira

      Version of Record online: 29 APR 2011 | DOI: 10.1002/cem.1394

      Commercial gasolines were collected from gas stations located in the Midwestern Sao Paulo State, and analyzed by several physicochemical methods established by ANP Resolution 309. Also were analyzed with the marker solvent. Statistical and exploratory chemometric were employed to discriminate the presence of solvents markers. Results showed that physicochemical parameters such as T10, T90, RON, benzene, saturated and aromatic describe satisfactorily the presence of solvent marker. SIMCA algorithm reveals sensitivity in the training (83.8%) and prediction set (77.1%).

    4. Calibration transfer of near-IR partial least squares property models of fuels using virtual standards (pages 496–505)

      John B. Cooper, Christopher M. Larkin and Mohamed F. Abdelkader

      Version of Record online: 19 JUL 2011 | DOI: 10.1002/cem.1395

      Partial least squares (PLS) models of 10 important jet and diesel fuel properties were built using spectra from a master near-IR dispersive instrument and then subsequently transferred to a secondary dispersive instrument via a novel calibration transfer method using virtual standards and a slope-bias correction. Implementation of the transfer requires that only seven spectra of neat solvents be acquired on the master and secondary instruments. The spectra of the neat solvents are then used to digitally replicate spectra from the calibration set to generate virtual standards.

    5. Method comparison on confidence interval construction for the slope in a linear measurement model with heteroscedastic errors (pages 506–513)

      Jia-Ren Tsai and Chen-Tuo Liao

      Version of Record online: 21 JUL 2011 | DOI: 10.1002/cem.1396

      This paper provides a novel approach based on the concepts of a generalized pivotal quantity (GPQ) to construct confidence intervals for the slope in a linear measurement model with heteroscedastic errors. The proposed method is shown to outperform two maximum likelihood estimation (MLE)-based approaches through simulation studies. Two real datasets are given to illustrate the approaches.

    6. Orthogonal projection to latent structures solution properties for chemometrics and systems biology data (pages 514–525)

      David J. Biagioni, David P. Astling, Peter Graf and Mark F. Davis

      Version of Record online: 27 SEP 2011 | DOI: 10.1002/cem.1398

      Partial least squares (PLS) is a widely used algorithm in the field of chemometrics. In calibration studies, a PLS variant called orthogonal projection to latent structures (O-PLS) has been shown to successfully reduce the number of model components while maintaining good prediction accuracy, although no theoretical analysis exists demonstrating its applicability in this context. Using a discrete formulation of the linear mixture model known as Beer's law, we explicitly analyze O-PLS solution properties for calibration data.

SEARCH

SEARCH BY CITATION