Seasonal Dynamic Factor Analysis and Bootstrap Inference: Application to Electricity Market Forecasting

In this work, we propose the Seasonal Dynamic Factor Analysis (SeaDFA), an extension of Nonstationary Dynamic Factor Analysis, through which one can deal with dimensionality reduction in vectors of time series in such a way that both common and specific components are extracted. Furthermore, common factors are able to capture not only regular dynamics (stationary or not) but also seasonal ones, by means of the common factors following a multiplicative seasonal VARIMA(p, d, q) × (P, D, Q)s model. Additionally, a bootstrap procedure that does not need a backward representation of the model is proposed to be able to make inference for all the parameters in the model. A bootstrap scheme developed for forecasting includes uncertainty due to parameter estimation, allowing enhanced coverage of forecasting intervals. A challenging application is provided. The new proposed model and a bootstrap scheme are applied to an innovative subject in electricity markets: the computation of long-term point forecasts and prediction intervals of electricity prices. Several appendices with technical details, an illustrative example, and an additional table are available online as Supplementary Materials.

Improving web learning through model optimization using bootstrap for a tour-guide robot

We perform a review of Web Mining techniques and we describe a Bootstrap Statistics methodology applied to pattern model classifier optimization and verification for Supervised Learning for Tour-Guide Robot knowledge repository management. It is virtually impossible to test thoroughly Web Page Classifiers and many other Internet Applications with pure empirical data, due to the need for human intervention to generate training sets and test sets. We propose using the computer-based Bootstrap paradigm to design a test environment where they are checked with better reliability.

Aplicación de la metodología bootstrap para la estimación de la movilidad de furgonetas

En este trabajo se muestran los resultados de la aplicación de la metodología bootstrap a datos de 3369 encuestas realizadas en 2009 a nivel nacional entre conductores de furgonetas, para obtener datos de movilidad interurbana y total, según edad de los vehículos, uso, conductores y otras características de este tipo de vehículo. Se obtienen estimaciones puntuales e intervalos de confianza para la movilidad total de furgonetas, así como para los cuatro tipos de furgonetas según la clasificación realizada en el proyecto de referencia. Se comparan los resultados obtenidos con estimaciones alternativas realizadas con otras fuentes de datos para el mismo colectivo (encuestas realizadas en inspecciones en carretera realizadas por la ATGC de la DGT e inspecciones en ITV) y datos publicados por fuentes oficiales. Estos resultados de movilidad (en término de vehículo-kilómetro) se usarán para la estimación de ratios de accidentalidad en un estudio comparado con otros colectivos de vehículos.

Bootstrap confidence levels for phylogenetic trees

Evolutionary trees are often estimated from DNA or RNA sequence data. How much confidence should we have in the estimated trees? In 1985, Felsenstein [Felsenstein, J. (1985) Evolution 39, 783–791] suggested the use of the bootstrap to answer this question. Felsenstein’s method, which in concept is a straightforward application of the bootstrap, is widely used, but has been criticized as biased in the genetics literature. This paper concerns the use of the bootstrap in the tree problem. We show that Felsenstein’s method is not biased, but that it can be corrected to better agree with standard ideas of confidence levels and hypothesis testing. These corrections can be made by using the more elaborate bootstrap method presented here, at the expense of considerably more computation.

Symplasmic Constriction and Ultrastructural Features of the Sieve Element/Companion Cell Complex in the Transport Phloem of Apoplasmically and Symplasmically Phloem-Loading Species1

The ultrastructural features of the sieve element/companion cell complexes were screened in the stem phloem of two symplasmically loading (squash, [Cucurbita maxima L.] and Lythrum salicaria L.) and two apoplasmically loading (broad bean [Vicia faba L.] and Zinnia elegans L.) species. The distinct ultrastructural differences between the companion cells in the collection phloem of symplasmically and apoplasmically phloem-loading species continue to exist in the transport phloem. Plasmodesmograms of the stem phloem showed a universal symplasmic constriction at the interface between the sieve element/companion cell complex and the phloem parenchyma cells. This contrasts with the huge variation in symplasmic continuity between companion cells and adjoining cells in the collection phloem of symplasmically and apoplasmically loading species. Further, the ultrastructure of the companion cells in the transport phloem faintly reflected the features of the companion cells in the loading zone of the transport phloem. The companion cells of squash contained numerous small vacuoles (or vesicles), and those of L. salicaria contained a limited number of vacuoles. The companion cells of broad bean and Z. elegans possessed small wall protrusions. Implications of the present findings for carbohydrate processing in intact plants are discussed.

Bootstrap confidence levels for phylogenetic trees.

Evolutionary trees are often estimated from DNA or RNA sequence data. How much confidence should we have in the estimated trees? In 1985, Felsenstein [Felsenstein, J. (1985) Evolution 39, 783-791] suggested the use of the bootstrap to answer this question. Felsenstein's method, which in concept is a straightforward application of the bootstrap, is widely used, but has been criticized as biased in the genetics literature. This paper concerns the use of the bootstrap in the tree problem. We show that Felsenstein's method is not biased, but that it can be corrected to better agree with standard ideas of confidence levels and hypothesis testing. These corrections can be made by using the more elaborate bootstrap method presented here, at the expense of considerably more computation.

Effect of the stabilisation time of pitch fibres on the molecular sieve properties of carbon fibres

The stabilisation of pitch fibres (PFs) is the most important step for their subsequent use in the preparation of carbon fibres (CFs) and their resulting characteristics. The present work studies the influence that the stabilisation time has on the porosity of the CFs, and on the subsequent properties as carbon molecular sieve (CMS). The increase of the stabilisation time carried out at 573 K, from 2 to 8 h favours their CMS properties producing a decrease in the microposity accessible to N2, which gets completely blocked after 6 and 8 h, while the narrow microporosity (V-DR CO2) remains accessible. Adsorption kinetic studies with CH4 and CO2 were performed to assess the possibility of using these CFs as CMS by comparing them with Takeda 3A CMS. The results suggest that there is an optimal stabilisation time which allows the preparation of CFs from an abundant raw precursor with properties similar to Takeda 3A CMS.

Novel silica membrane material for molecular sieve applications

Development of new silica membranes properties, e.g., molecular sieving properties, has been increasingly gaining importance in the last few years. A novel unsupported silica membrane, referred to as hydrophobic metal-doped silica, was developed by cobalt-doping within the organic templated silica matrix. The novel material was prepared by the acid-catalyzed hydrolysis and condensation process of tetraethylorthosilicate (TEOS) and methyltriethoxysilane (MTES), which is the precursor for methyl ligand covalently bounded to the silica matrix. The synthesis and surface properties of the novel unsupported silica membrane as well as the unsupported blank silica and modified silica membranes were revealed by surface and microstructural techniques, such as water contact angle measurement, FTIR, X-ray, Solid-state 29Si MAS NMR, TGA and N2 and CO2 adsorption measurements. The results showed that the thermal stability of the organic templated silica matrix was enhanced by cobalt-doping process. A hydrophobic microporous silica membrane material with high thermal stability up to ∼560 °C in oxidizing atmosphere and a narrow pore size distribution centered at 1.1 nm was obtained. Therefore, a novel precursor material for molecular sieve silica membranes applications has been achieved and developed.

Characterization of Carbon Molecular Sieve Membranes Supported on Ceramic Tubes

Carbon molecular sieve membranes have been analyzed in supported and unsupported configurations in this experimental study. The membranes were used to adsorb CO2, N2 and CH4, and their adsorption data were analyzed to establish differences in rate and capacity of adsorption between the two types of samples (supported and unsupported). Experimental results show an important effect of the support, which can be considered as an additional parameter to tailor pore size on these carbon membranes. Immersion calorimetry values were measured by immersing the membranes into liquids of different molecular dimensions (dichloromethane, benzene, n-hexane, 2,2-dimethylbutane). Similarities were found between adsorption and calorimetric analysis. The pore volume of the samples analyzed ranged from 0.016 to 0.263 cm3/g. The effect of the pyrolysis temperature, either 550 or 700 °C, under N2 atmosphere was also analyzed. Quantification of the pore-size distribution of the support was done by liquid-liquid displacement porosimetry. The composite membrane was used for CO2/CH4 separation before and after pore plugging was done. The ideal selectivity factors value (4.47) was over the Knudsen theoretical factor (0.60) for membrane pyrolyzed at 600 °C, which indicates the potential application of these membranes for the separation of low-molecular weight gases.