Search results for " Regression"
showing 10 items of 1835 documents
Analysis of Caffeine, Sweeteners, and Other Additives in Beverages by Vibrational Spectroscopy
2001
This chapter presents a review of the scientific literature on the use of vibrational spectroscopy, near-infrared (NIR), mid-infrared (mid-IR), and Raman, for the analysis of caffeine, sweeteners, and other additives in beverages and related products. Direct analysis procedures of coffee and tea, for both classification according to precedence or variety and quantitative determination of caffeine, are available. For beverage analysis, caffeine has been determined by direct attenuated total reflection (ATR) measurement or by transmission spectroscopy in the mid-IR region after extraction with chloroform. Different strategies have been employed for the analysis of sweeteners in beverages and …
Use of electronic nose to determine defect percentage in oils. Comparison with sensory panel results
2010
Abstract An electronic nose based on an array of 6 metal oxide semiconductor sensors was used, jointly with linear discriminant analysis (LDA) and artificial neural network (ANN) method, to classify oils containing the five typical virgin olive oil (VOO) sensory defects (fusty, mouldy, muddy, rancid and winey). For this purpose, these defects, available as single standards of the International Olive Council, were added to refined sunflower oil. According to the LDA models and the ANN method, the defected samples were correctly classified. On the other hand, the electronic nose data was used to predict the defect percentage added to sunflower oil using multiple linear regression models. All …
ANALISI GIS E MODELLI STATISTICI PER LA VALUTAZIONE DELLA SUSCETTIBILITÀ DA FRANA A SCALA DI BACINO: IL CASO STUDIO DEL BACINO DEL TORRENTE MARVELLO
Lo studio condotto nel presente lavoro di tesi ha affrontato il tema della valutazione, a scala di bacino idrografico, della suscettibilità ai fenomeni di tipo colamento, attraverso l’applicazione di modelli statistici e tecniche di analisi spaziale GIS. La fase iniziale della preparazione di un modello di suscettibilità da frana prevede la realizzazione di un inventario degli eventi verificatesi nell’area di studio. Questo passo è di fondamentale importanza, considerando che proprio attraverso l’archivio frane è possibile analizzare ed individuare le condizioni che in passato hanno favorito l’innesco dei movimenti di versante. L’identificazione di queste condizioni, infatti, consente di pr…
Analisi comparativa di modelli euristici e statistici spaziali nella derivazione della suscettibilità da colate rapide di fango e detrito.
2013
La suscettibilità da frana può essere definita come la propensione di una determinata area all’innesco di movimenti di massa, in relazione alle caratteristiche intrinseche dei terreni di copertura e del substrato, delle caratteristiche morfologiche ed alla maggiore esposizione nei confronti degli agenti climatici. Nel corso degli anni sono stati sviluppati vari metodi per valutare la suscettibilità, basati su approcci sia di tipo deterministico che statistico. Tutti i metodi si basano su poche assunzioni fondamentali secondo cui la franosità è controllata da leggi meccaniche che possono essere determinate in modo empirico, statistico o deterministico. Scopo del presente lavoro è quello di v…
Functional principal component analysis of quantile curves
2017
Literature on functional data analysis is mainly focused on estimation of individuals curves and characterization of average dynamics. The idea underlying this proposal is to focus attention on other particular features of the distribution of the observed data, moving from mean functions towards functional quantiles. The motivating examples are functional data sets that are collections of high frequency data recorded along time. As quantiles provide information on various aspects of a time series, we propose a modelling framework for the joint estimation of functional quantiles, varying along time, and functional principal components, summarizing some common dynamics shared by the functiona…
Methodological advances in the functional profiling of genomic studies
2013
In this thesis we present bioinformatic tools and algorithms for the analysis of genomic data such as those generated by microarray devices or next generation sequencing techniques. Particularly, we develop new approaches to gene set analysis. The described procedures should be useful in practice to tackle complex biological experiments, but hopefully will also be methodologically relevant, as they introduce new ways of conceptualizing genomic functional profiling. Our very flexible approach allows for the inclusion of not just one kind of genomic measurement but many. It makes possible, for instance, to analyze expression measurement and genomic variation data at a time. This multidimensio…
Neighborhood Mobility and Unmet Physical Activity Need in Old Age: A 2-Year Follow-Up
2020
Background: Many older people report a willingness to increase outdoor physical activity (PA), but no opportunities for it, a situation termed as unmet PA need. The authors studied whether lower neighborhood mobility and PA precede the development of unmet PA need. Methods: Community-dwelling 75- to 90-year-old people (n = 700) were interviewed annually for 2 years. Unmet PA need, neighborhood mobility, and PA were self-reported. In addition, accelerometer-based step counts were assessed among a subgroup (n = 156). Results: Logistic regression analyses revealed that lower baseline neighborhood mobility (odds ratio 3.02, 95% confidence interval [1.86, 4.90] vs. daily) and PA (odds ratio 4.37…
Study on the financial performance of companies operating in the pharmaceutical industry in romania
2016
Abstract The study aims at determining the financial performance of companies in the pharmaceutical industry between 2009 and 2014 by means of the indicator of the financial return rate, using multiple linear regressions as research method. By analysing the evolution of the share of companies in the pharmaceutical industry based on the trend of the financial rate of return, we can estimate that the number of entities that resort to supporting the financial activities from loans and liabilities is growing in the period under analysis. This is due mainly to the liquidity crisis faced by entities, as a result of the high recovery duration of debts. Also, using the multiple linear regression we…
What is it and how to measure cultural tourism? A longitudinal study with time series for the Spanish case
2013
Por su poder diferenciador, y su débil contingencia a la moda el turismo cultural se ha convertido en un reto para los destinos. No solo dinamiza zonas de interior sino que es una manera para algunos destinos de salvar su patrimonio y crear empleos. Sin embargo, el concepto de turismo cultural es complejo y su delimitación y medición difíciles. En una primera parte teórica, este trabajo realiza una revisión conceptual del turismo cultural enfocando la dialéctica existente entre experiencia y autenticidad, y destacando después la diversidad de tipologías de turismo y de turista cultural. En la parte empírica, después de abordar la dificultad de medición, se presenta un estudio con series tem…
Sparse relative risk survival modelling
2016
Cancer survival is thought to closed linked to the genimic constitution of the tumour. Discovering such signatures will be useful in the diagnosis of the patient and may be used for treatment decisions and perhaps even the development of new treatments. However, genomic data are typically noisy and high-dimensional, often outstripping the number included in the study. Regularized survival models have been proposed to deal with such scenary. These methods typically induce sparsity by means of a coincidental match of the geometry of the convex likelihood and (near) non-convex regularizer.