139,663 research outputs found
Permutation inference for a class of mixture models
No full textIn statistical surveys, people are often asked to express evaluations on several topics or to make an ordered arrangement in a list of objects (items, services, sentences, etc.); thus, the analysis of ratings and rankings is receiving a growing interest in many fields. In this framework, we develop a testing procedure for a class of mixture models with covariates (defined as cub models), proposed by Piccolo (2003) and D'Elia and Piccolo (2005) and generally developed in a parametric context. Instead, we propose a nonparametric solution to perform inference on cub models, specifically on the coefficients of the covariates. A simulation study proves that this approach is more appropriate in some specific data settings, mostly for small sample sizes
Aggregation and disaggregation of humic supramolecular assemblies by NMR diffusion ordered spectroscopy (DOSY-NMR)
No full textDiffusion ordered nuclear magnetic resonance spectroscopy
(DOSY-NMR) was applied to a number of fulvic (FA) and humic
(HA) acids of different origin. Spectral separation achieved
by DOSY based on diffusion coefficients (D), and correlated to
molecular sizes by calibration standards, showed that
carbohydrates had the largest molecular size in FA, whereas
alkyl or aromatic components were the most slowly diffusing
moieties in HA. At increasing concentrations, these components
had invariably lower D values in DOSY spectra for all humic
samples, thereby indicating an aggregation into apparently larger
associations, whose increased hydrodynamic radius was
confirmed by viscosity measurements. When humic solutions
werebroughtfromalkalinetoacidicpH(3.6),componentsdiffusivity
detected by DOSY increased significantly, suggesting a
decreaseofaggregationandmolecularsize.Ageneralcomparison
of HA and FA molecular sizes was achieved by multivariate
statistical analysis. While a larger extent of aggregation and
disaggregation was observed for HA than for FA, no aggregation
wasdetected,undersimilar conditions, foratruemacropolymeric
standard. Such difference in diffusion between a polymeric
molecule and humic samples, is in line with the supramolecular
nature of humic matter. The possible formation of humic
micelles was also investigated by both changes of diffusivity
in DOSY spectra and shift of 1H NMR signals. Except for HA of
peat and soil origin, revealing a self-assembling in micellelike
structures at the 4 mg mL-1 concentration, no other humic
sample showed evidence of critical micelle concentration
(cmc) up to 20 mg mL-1. These results indicated that DOSYNMRspectroscopy
is a useful technique to evaluate components
of different molecular size in natural humic superstructures
Test di autovalutazione
No full textQuesti test di autovalutazione consentono un'autoverifica costante e in itinere dell'apprendimento degli elementi della scienza statistica, nei termini sia di una comprensione della materia nei suoi principi generali, sia della padronanza degli strumenti essenziali per il calcolo e l'interpretazione corretta dei risultati dell'analisi statistica di base. Nell'ottica di fornire uno strumento efficace di autovalutazione, i test sono corredati non solo dalle soluzioni, ma anche da schede nelle quali sono indicati i riferimenti necessari per risolvere i quesiti proposti. Lo studente viene così indirizzato ai paragrafi del volume di D. Piccolo, "Statistica per le decisioni", di cui i test qui presentati, che ne adottano sia la simbologia e notazione, sia la logica didattica, intendono essere naturale e utile integrazione
Delegation, Ownership Concentration and R&D Spending: Evidence From Italy
No full textWe use data from the Italian manufacturing industry to document a positive correlation between delegation and R&D. This result is robust to controlling for the determinants of R&D such as human capital, capital intensity and sectoral or regional effects. We further investigate the determinants of delegation and find that ownership concentration is significantly related to delegation. Among large firms with a dispersed ownership structure, larger ownership concentration implies less delegation, whereas the opposite emerges with more concentrated ownership. Differences between the Northern and Southern regions in terms of firms' propensity to delegate decisions and engage in R&D also emerge
Modelling consumers' qualitative perceptions of inflation
No full textRepeated surveys about opinions, perceptions or attitudes of the interviewees are regularly carried out by national statistical offices. This is the case of the surveys concerning the qualitative assessment or anticipations on price level that ISTAT carries out every month. Earlier studies of perceived and expected inflation focussed either on quantifying the observed ordinal data in order to derive indices of perceived (or expected) inflation or on searching explicative models that could describe data in terms of economic explanatory variable. In this article, we discuss an innovative model for time seriesordinal data that extends the well established CUB model (Piccolo et al.,2018) to allow for time varying parameters. The method is illustrated by its application to the qualitative perceptions of inflation in Italy
High-power gradient diffusion NMR spectroscopy for the rapid assessment of extra-virgin olive oil adulteration
No full textHost-Guest Interactions between 2,4-Dichlorophenol and Humic Substances As Evaluated by H-1 NMR Relaxation and Diffusion Ordered Spectroscopy
No full textPhysical-chemical characteristics of lignins separated from biomasses for second-generation ethanol
No full textLignin was extracted by two extraction methods from two biomasses for energy (Mischantus and Giant Reed) and a lignocellulosic material resulting from a microbial treatment of giant reed. One method of extraction involved the use of H2SO4 (SA), providing a highly aromatic water-insoluble material, while a second method employed H2O2 at alkaline pH (Ox), resulting in a water-soluble lignin. Extraction yields were related to the total Klason lignin measured for the three materials. We compared the physical-chemical features of the isolated lignins, by employing solid-state nuclear magnetic resonance spectroscopy (13C-CPMAS spectra and derived T1ρH relaxation times), thermogravimetric analyses, infrared spectrometry and high performance size exclusion chromatography (HPSEC). We found that lignin separated by the Ox method owned a more mobile molecular conformation, and was largely more water-soluble and fragmented than the lignin obtained by the SA treatment. In line with T1ρH-NMR and thermogravimetric results, the HPSEC of Ox lignins showed nominal molecular weights less than 3kDa, indicating well depolymerized materials. Such low-molecular weight and fragmented lignin obtained from biomasses for energy may become useful for application of recycled products in agriculture and in green chemistry reactions, thereby promoting an increase in the economic sustainability of biorefineries. © 2014 Elsevier Ltd
Fuzzy logic based optimal power flow management in Hybrid Electric Vehicles
No full textParallel Hybrid Electric Vehicle powertrain (PHEV), combining an electric motor with an auxiliary power unit, improves vehicle performance and fuel economy, reducing the effects of private cars on air quality in cities. These advantages can be enhanced by using a dedicated control strategy to identify the optimal power flow distribution at each instant of time in the main powerdrive sources as a function of the state of the powerdrive components and the actual driving conditions. In this connection the literature analysis has evidenced as the research efforts in the field of PHEV optimal power flow management should be oriented not only to develop precise and robust control strategies that can improve the vehicle performances, but also to lower the required computational resources making the solution strategy suitable with the vehicle dynamics and allowing, moreover, a cost effective hardware implementation. To develop this complex activity, fuzzy logic (FL) was used. As demonstrated by the simulation studies developed, FL enables the optimal power flow management problem to be solved by handling its intrinsic non-linearity using rules, membership functions, and the inference process. This results in improved performance, simpler implementation, and reduced design costs compared with rigorous mathematics based approaches
- …
