Search results for "multivariate statistic"
showing 10 items of 327 documents
Imputation Strategies for Missing Data in Environmental Time Series for An Unlucky Situation
2005
After a detailed review of the main specific solutions for treatment of missing data in environmental time series, this paper deals with the unlucky situation in which, in an hourly series, missing data immediately follow an absolutely anomalous period, for which we do not have any similar period to use for imputation. A tentative multivariate and multiple imputation is put forward and evaluated; it is based on the possibility, typical of environmental time series, to resort to correlations or physical laws that characterize relationships between air pollutants.
Comparison of different predictive models for nutrient estimation in a sequencing batch reactor for wastewater treatment
2006
Abstract In this paper different predictive models for nutrient estimation in a sequencing batch reactor (SBR) for wastewater treatment are compared: principal component regression (PCR), partial least squares (PLS), and artificial neural networks (ANNs). Two unfolding procedures were used: batch-wise and variable-wise. For the latter unfolding method, X and Y matrix augmentation with lagged variables were used in some models to incorporate process dynamics. The results have shown that batch-wise unfolding PLS models outperform the other approaches. The ANN models are good predictive models, but in this particular case-study, they do not outperform those multivariate projection models that …
Assessing directional interactions among multiple physiological time series: The role of instantaneous causality
2012
This paper deals with the assessment of frequency domain causality in multivariate (MV) time series with significant instantaneous interactions. After providing different causality definitions, we introduce an extended MV autoregressive modeling approach whereby each definition is described in the time domain in terms of the model coefficients, and is quantified in the frequency domain by means of novel measures of directional connectivity. These measures are illustrated in a theoretical example showing how they reduce to known indexes when instantaneous causality is trivial, while they describe peculiar aspects of directional interaction in the presence of instantaneous causality. The appl…
Comparison of canonical variate analysis and principal component analysis on 422 descriptive sensory studies
2015
International audience; Although Principal Component Analysis (PCA) of product mean scores is most often used to generate a product map from sensory profiling data, it does not take into account variance of product mean scores due to individual variability. Canonical Variate Analysis (CVA) of the product effect in the two-way (product and subject) multivariate ANOVA model is the natural extension of the classical univariate approach consisting of ANOVAs of every attribute. CVA generates successive components maximizing the ANOVA F-criterion. Thus, CVA is theoretically more adapted than PCA to represent sensory data. However, CVA requires a matrix inversion which can result in computing inst…
Structural invariants for the prediction of relative toxicities of polychloro dibenzo-p-dioxins and dibenzofurans
2004
Multivariate models are reported that can predict the relative toxicity of compounds with severe environmental impact, namely polychloro dibenzo-p-dioxins (PCDDs) and dibenzofurans (PCDFs). Multiple linear regression analysis (MLR) and partial least square projections of latent variables (PLS) show the usefulness of graph-theoretical descriptors, mainly topological charge indices (TCIs), in these series. The general trends of the group are correctly reproduced and better results are presented than have previously been published. In general, the more toxic compounds exhibit more symmetric molecular structures.
A multivariate approach to the study of orichalcum ingots from the underwater Gela's archaeological site
2017
Abstract In this work a careful ICP-OES and ICP-MS investigation of 38 ancient ingots has been performed to determine both major components and trace elements content to find a correlation between the observed different features and the composition. The ingots, recovered in an underwater archaeological site of various finds near Gela (CL, Italy), were previously investigated by X-Ray Fluorescence (XRF) spectroscopy to know the composition of the alloy and it was found that the major elements were copper and zinc, in a ratio compatible with the famous orichalcum similar to the contemporary brass that was considered a precious metal in ancient times. The discovery of huge amount this alloy is…
Capillary electrophoresis enhanced by automatic two-way background correction using cubic smoothing splines and multivariate data analysis applied to…
2005
Mixtures of the surfactant classes coconut diethanolamide, cocamido propyl betaine and alkylbenzene sulfonate were separated by capillary electrophoresis in several media containing organic solvents and anionic solvophobic agents. Good resolution between both the surfactant classes and the homologues within the classes was achieved in a BGE containing 80 mM borate buffer of pH 8.5, 20% n-propanol and 40 mM sodium deoxycholate. Full resolution, assistance in peak assignment to the classes (including the recognition of solutes not belonging to the classes), and improvement of the signal-to-noise ratio was achieved by multivariate data analysis of the time-wavelength electropherograms. Cubic s…
Towards unsupervised analysis of second-order chromatographic data: automated selection of number of components in multivariate curve-resolution meth…
2007
A method to apply multivariate curve-resolution unattendedly is presented. The algorithm is suitable to perform deconvolution of two-way data (e.g. retrieving the individual elution profiles and spectra of co-eluting compounds from signals obtained from a chromatograph equipped with multiple-channel detection: LC-DAD or GC-MS). The method is especially adequate to achieve the advantages of deconvolution approaches when huge amounts of data are present and manual application of multivariate techniques is too time-consuming. The philosophy of the algorithm is to mimic the reactions of an expert user when applying the orthogonal projection approach--multivariate curve-resolution techniques. Ba…
Decoupling factors on the energy–output linkage: The Spanish case
2007
The recent increase of energy intensity in Spain and the ratification of the Kyoto protocol call for the implementation of energy policies in Spain. In this paper, we investigate the relationship between Gross Domestic Product (GDP) and Energy Consumption (EC) by taking into account several decoupling factors that can affect this linkage. Specifically, we have considered the temporal aggregation of data and its seasonal adjustments, the multivariate methodology, the substitution between EC and other inputs and the technological changes. Empirical tests reveal a long-run relationship between EC and GDP that can only be established in a complete way with a multivariate cointegration analysis.…
Assessing Frequency Domain Causality in Cardiovascular Time Series with Instantaneous Interactions
2009
Summary Background: The partial directed coherence (PDC) is commonly used to assess in the frequency domain the existence of causal relations between two time series measured in conjunction with a set of other time series. Although the multivariate autoregressive (MVAR) model traditionally used for PDC computation accounts only for lagged effects, instantaneous effects cannot be neglected in the analysis of cardiovascular time series. Objectives: We propose the utilization of an extended MVAR model for PDC computation, in order to improve the evaluation of frequency domain causality in the presence of zero-lag correlations among multivariate time series. Methods: A procedure for the identif…