Relations between Mid-Infrared and Near-Infrared Spectra Detected by Analysis of Variance of an Intervariable Data Matrix
- 1 September 1997
- journal article
- research article
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 51 (9) , 1384-1393
- https://doi.org/10.1366/0003702971942097
Abstract
A mathematical procedure based on the analysis of variance of an intervariable data matrix (AVID) was used to relate wavenumbers and wavelengths between the mid-infrared and near-infrared domains. Initially the method calculates for each sample the product of intensities at all combinations of the frequencies in the two domains. This data matrix is submitted to analysis of variance (ANOVA) based on a classification criterion. This procedure gives a matrix of Fisher F values for all possible combinations of wavenumbers and wavelengths. To remove the masking effect due to a few extremely significant frequencies and to highlight the relations between the frequencies, this matrix of F values was corrected by subtraction of a matrix of independence. The examination of the corrected data matrix allowed the assignment of the most important peaks for the discriminating criterion. This procedure also allows the study of vector profiles, where one spectral domain is examined in relation to a particular frequency in the other domain. The study of vector profiles is a very useful tool to see the relations between the wavenumbers and wavelengths of the two domains under study.Keywords
This publication has 8 references indexed in Scilit:
- A novel tool for two-dimensional correlation spectroscopyChemometrics and Intelligent Laboratory Systems, 1995
- Application of procrustean methods to mid‐and near‐infrared spectral dataJournal of Chemometrics, 1995
- Canonical Correlation Analysis of Mid- and Near-Infrared Oil SpectraApplied Spectroscopy, 1993
- Two-Dimensional Vibration Spectroscopy: Correlation of Mid- and Near-Infrared RegionsApplied Spectroscopy, 1992
- Preferred set selection by iterative key set factor analysisChemometrics and Intelligent Laboratory Systems, 1989
- Obtaining the key set of typical vectors by factor analysis and subsequent isolation of component spectraAnalytica Chimica Acta, 1982
- Separation of mass spectra of mixtures by factor analysisAnalytical Chemistry, 1979
- Self Modeling Curve ResolutionTechnometrics, 1971