To see the other types of publications on this topic, follow the link: GLM.
Dissertations / Theses on the topic 'GLM'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'GLM.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Godoy, Daniela Ferro de. "O Boto-cinza (Sotalia guianensis) no complexo estuarino lagunar de Cananéia: fatores associados ao uso de habitat." Universidade Federal de Juiz de Fora (UFJF), 2016. https://repositorio.ufjf.br/jspui/handle/ufjf/3147.
Full textAbstract:
Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-01-06T14:31:54Z
No. of bitstreams: 1
danielaferrodegodoy.pdf: 2931952 bytes, checksum: 08ac03607124e73f9ec9318d1bbc4e9a (MD5)<br>Approved for entry into archive by Diamantino Mayra (mayra.diamantino@ufjf.edu.br) on 2017-01-31T11:25:03Z (GMT) No. of bitstreams: 1
danielaferrodegodoy.pdf: 2931952 bytes, checksum: 08ac03607124e73f9ec9318d1bbc4e9a (MD5)<br>Made available in DSpace on 2017-01-31T11:25:03Z (GMT). No. of bitstreams: 1
danielaferrodegodoy.pdf: 2931952 bytes, checksum: 08ac03607124e73f9ec9318d1bbc4e9a (MD5)
Previous issue date: 2016-07-12<br>CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior<br>A modelagem pode ser utilizada para determinar a distribuição de uma determinada espécie em uma área. Deste modo, pode auxiliar na conservação de espécies ameaçadas. Neste estudo, modelos foram utilizados para avaliar a influência do habitat, do tipo de presas capturadas por pescadores artesanais e do Valo Grande sobre a presença do boto-cinza na região do Complexo Estuarino Lagunar de Cananéia. Os dados foram coletados entre janeiro de 2012 a novembro de 2014, durante três 3 saídas de campo por estação do ano. Estas saídas de campo foram realizadas em quatro setores pré-definidos, que foram percorridos em transecções lineares. O setor II foi o de maior ocorrência de botos, provavelmente pela proximidade com o oceano adjacente. A distribuição entre os setores foi mais homogênea nas estações mais frias, onde os valores das variáveis ambientais são mais estáveis. Os maiores agrupamentos de animais também foram encontrados no inverno. Os botos foram avistados em diversos valores das variáveis ambientais analisadas. No entanto, as maiores ocorrências foram registradas em águas mais turvas; profundidades maiores que 10 metros; salinidade acima de 10 ppm; e águas mais frias e nas marés de sizígias. A presença do cerco-fixo no estuário também influenciou positivamente a ocorrência dos botos, que utilizam essa armadilha de pesca como barreira, minimizando a fuga das suas presas. A tainha foi a categoria de peixe que teve a maior associação com a presença dos botos, seguida pela guaivira e prejereba. Já o parati e o camarão estuarino apresentaram uma influência negativa com a presença do boto. O modelo preditivo do Valo Grande mostrou que a descarga de água doce influencia de maneira negativa na presença dos botos. Pelo exposto, fica claro que os botos-cinza apresentaram uma distribuição heterogênea dentro do estuário estudado e as áreas de maior concentração merecem maior atenção na elaboração de estratégias de conservação.<br>Niche modelling can be used to determine the distribution of a particular species in an enviromental space (ecological niche). It may be important to help to preserve endangered species. Therefore, in this study, niche modelling was used to evaluate the influence of: the habitat; the artisanal fishermen‟s catch species; and the Valo Grande on the presence of the Guiana dolphins (Sotalia guianensis) in the Estuarine Lagunar Complex of Cananéia, Brazil. The data were collected in three fieldworks per season, from January 2012 to November 2014. The fieldworks took place in four predefinied sectors. These sectors were sampled using a line-transect method. The presence of the Guiana dolphin was observed mostly on sector II. Probably because of the proximity to the adjacent ocean. The distribution among sectors was more homogeneous in the short cool season, when the environmental variables are more stable. The larger dolphin clusters were found during the winter. Guiana dolphins were sighted in a great diversity of environmental conditions. Nonetheless, the highest occurrences were recorded in cooler and turbid waters; depths greater than 10 meters; salinity above 10 ppm; and during spring tides (technically known in Portuguese as 'maré de sizígia'). Furthermore, the presence of an artisanal fish trap, known locally as cerco-fixo, has positively influenced the occurrence of Guiana dolphins in the estuary. The dolphins use cerco-fixo fish traps to corner shoals and reduce the escape routes of their prey. The mullet (Mugil brasiliensis) was the fish species which had the highest positive correlation with the presence of dolphins, followed by the leatherjacket (Oligoplites saurus) and the tripletail (Lobotes surinamensis). On the other hand, the white mullet (Mugil curema) and the whiteleg shrimp (Litopenaeus vannamei) had a negative correlation with the presence of the Guiana dolphin. The data collected on the Valo Grande Channel showed that freshwater discharges decrease the presence of Guiana dolphins. We can conclude that the Guiana dolphins have an heterogeneous distribution within the studied estuary. Therefore, the areas of greatest ocurrence deserve greater attention in the development of preservation strategies.
2
Moreno, Maria Paula Teixeira. "Environmental predictors of bottlenose dolphins distribution and core feeding densities in Galveston Bay, Texas." Texas A&M University, 2005. http://hdl.handle.net/1969.1/3803.
Full textAbstract:
Coastal dolphins are often exposed to habitat degradation and direct interactions with
humans. Major factors that influence dolphin distribution, critical for conservation
concerns, are still poorly understood even for the bottlenose dolphin, the best-studied
cetacean. To establish the environmental conditions that best predict occurrence of
bottlenose dolphins and high feeding densities in Galveston Bay, I conducted a total of
367 boat surveys in five locations of the estuary, totaling 3,814.77 km of search effort. I
counted groups of dolphins and measured surface water temperature, salinity, turbidity,
total number of boats, shrimp vessels, and number of seabirds. Using geospatial tools,
these data -- along with location, distance to the Gulf of Mexico and water depth -- were
analyzed on a 500- m resolution grid. Temporal factors at daily and seasonal scales were
also examined. Occurrence was modeled using a Generalized Additive Model and core
feeding densities (i.e., feeding densities above 2 SD of the mean) were modeled with a
Generalized Linear Model. A total of 1,802 dolphins in 262 groups were detected,
56.87% of which were feeding. I found that all factors except warm/cold seasons and
turbidity were useful to predict dolphin distribution, which was related non-linearly to
most predictors. Fewer variables were relevant in predicting core feeding densities.
These were, in decreasing order of relevance, distance to the Gulf of Mexico, surface
water temperature, depth, number of boats, and warm/cold seasons. Feeding was highly
clustered and the main core areas, less than approximately 3 km2 wide, were stable
across time of day and season. The majority of the occurrences (86.2%) and feeding
groups (94%) were situated in two bay locations - Galveston Ship Channel (GSC) and
Bolivar Roads (BRD) - that amounted to only one- fifth of the surveyed area. Compared
to conditions in GSC and BRD when no dolphins were sighted, feeding cores weredeeper and more seabirds were observed. This fine-scale study of bottlenose dolphin
distribution may contribute to a better understanding of habitat requirements for coastal
dolphins. It also may provide information needed to minimize potential negative impacts
to this population caused by human activities.
3
Silva, Jairo Moreira Caetano da. "Risk modeling journey - GLM and impact analysis." Master's thesis, Instituto Superior de Economia e Gestão, 2021. http://hdl.handle.net/10400.5/23313.
Full textAbstract:
Mestrado Bolonha em Actuarial Science<br>Generalized Linear Models (GLMs) are not a new topic. With increases in computing power and access to big data, actuaries have in fact been using GLMs in the insurance rating process for many years. Besides being well established, GLMs have straightforward interpretation which helps the com- munication with underwriters and the Product department. Although many theoretical works have been done regarding GLMs in the in- surance business, it is also important for actuaries to explore this subject in a work experience perspective. In this context, this project aims to present a practical view on the GLM model-building process from start to finish. This work is applied to the Liberty Seguros motor insurance policy database and different risk models are built considering the automotive perils with higher exposure. The model evaluation step shows how well the model built aligns with historical data, which means that it is possible to verify the model ability to predict the risk behavior for new datasets after model development. During the impact analysis, it is shown the suggested changes in the prices for specific variables and how it affects the overall price, which can help the company to improve the underwriting process and profitability.<br>Generalized Linear Models (GLMs) não são um tópico novo. Com o aumento da potência computacional e o acesso a big data, atuários têm de fato usado GLMs no processo de tarifação de seguros durante muitos anos. Além de ser bem consolidado, GLMs têm uma interpretação direta, o que ajuda a comunicação com subscritores e o departamento de Produto. Apesar de muitos trabalhos teóricos terem sido realizados acerca de GLMs aplicados à indústria de seguros, também se faz importante para atuários explorar este assunto sob a ótica da experiência profissional. Neste contexto, este projeto tem como objetivo apresentar uma visão prática de todo o processo de construção de modelo de risco baseado em GLMs. Este trabalho é aplicado à base de dados de apólices de seguro de automóvel da Liberty Seguros e são desenvolvidos diferentes modelos de risco considerando as coberturas automotivas de maior exposição. A etapa de avaliaçã do modelo mostra quão bem o modelo construído se alinha com os dados históricos, o que quer dizer que é possível verificar a capacidade do modelo em prever o comportamento do risco para novos conjuntos de dados após o desenvolvimento do modelo. Durante a análise de impacto, são mostradas as mudanças sugeridas nos preços para variáveis específicas e como isso afeta o preço geral, o que pode ajudar a companhia a melhorar o processo de subscrição e a lucratividade.<br>info:eu-repo/semantics/publishedVersion
4
Milhinhas, Catarina Isabel Ralo. "Factors influencing the bat community in vineyards: the role of landscape characteristics, natural structures and management." Master's thesis, Universidade de Évora, 2019. http://hdl.handle.net/10174/25397.
Full textAbstract:
Fatores que influenciam a comunidade de morcegos em vinhas: o papel das caraterísticas da paisagem, estruturas naturais e gestão
As vinhas são um sistema agrícola muito representado na Europa. Essas áreas apresentam baixos níveis de biodiversidade devido à simplificação da paisagem e ao elevado uso de pesticidas, o que reduz a disponibilidade de insetos e as torna pouco atrativas para morcegos. Nós investigámos o efeito da gestão, do tipo de uso do solo e das estruturas naturais na atividade e riqueza de morcegos em vinhas a duas escalas espaciais: 500 m (escala de vinha) e 1500 m (escala de paisagem). Os resultados demonstraram que as estruturas e os habitats naturais foram mais importantes para os morcegos do que a gestão da vinha. Nós sugerimos que as prioridades de conservação devem ser criar ou manter vegetação ripária e áreas de montado. Essas estruturas naturais são uma componente chave na gestão para promover o uso das vinhas por morcegos, aumentando o seu potencial como reguladores de pragas agrícolas; ABSTRACT: Vineyards are one of most represented agricultural systems in European landscape. These areas can present low biodiversity levels due to simplification of landscape and the high input of pesticides, which reduce insect availability and makes them unattractive for bats. We assessed the effect of farming management, land use type and natural structures on bat activity and species richness in vineyards at two spatial scales: 500 m (vineyard scale) and 1500 m (landscape scale). Our results demonstrate that natural structures and habitats were more important to the bat community than vineyard management. We suggest that conservation priorities should be to create or maintain riparian vegetation – near streams or small dams - and areas of “montados”. These natural structures are important for bat populations within or near vineyards, and a key component of agricultural management to promote bat use of vineyards, enhancing their role as pest regulators.
5
Brodersson, Anna Lilly. "Flygbesiktning av Luftledningar : Modellering av samband mellan besiktningsanmärkningar och systemtillförlitlighet." Thesis, Uppsala universitet, Tillämpad matematik och statistik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-219572.
Full textAbstract:
This paper thoroughly investigates needs and requirements for overhead distribution feeder inspection and develops models to investigate possible relations between short term inspections remarks and outages. The study was conducted in collaboration with Fortum Distribution AB that supplied extensive information about their overhead power feeders concerning both inspection and power outages. The investigated models where lognormal linear model, Poisson generalized linear model and negative binomial generalized linear model. All models were implemented utilizing offset terms to compensate for differences in feeder length and amount of overhead versus underground feeders. The Poisson generalized linear model was rejected at an early stage due to overdispersion and neither of the remaining models fit the data perfectly. There for conclusions were primarily concluded from similarities and differences amongst the models. The results either implicate that maintenance is scheduled sufficiently fast, with respect to short term inspection, to ensure a high system reliability or no relationships between short term inspection and feeder outages exist. Therefore the final conclusion was that maintenance and reinvestment decisions should not be based on short cycle inspection data.
6
Van, der Walt Anchen. "Small holder farmers' perceptions, host plant suitability and natural enemies of the groundnut leafminer, Aproaerema modicella (Lepidoptera: Gelechiidae) in South Africa / Anchen van der Walt." Thesis, North-West University, 2007. http://hdl.handle.net/10394/1950.
Full text
7
Štens, Radovan. "Analýza obrazových dat funkční magnetické rezonance (fMRI)." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2010. http://www.nusl.cz/ntk/nusl-375489.
Full textAbstract:
Master's thesis focuses on processing fMRI data, which are mapping blood oxygenation level dependence in a state of brain activity. Usable and necessarily preprocessing tech- niques of the data, together with two main analysis approaches are introduced. The area of univariate methods, especially general linear model and multivariate principal or independent component analysis is explained. Practical application of the methods involved on the real fMRI data set is implemented. Relevant results as well as theirs mutual possible comparison is presented.
8
Ali, Muhammad Younis. "Some aspects of fitting multinomial models in a GLM framework." Thesis, London Metropolitan University, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.540613.
Full text
9
Azevedo, Venancio Guedes de. "\"Aspectos biológicos e dinâmica das capturas do tubarão-azul (Prionace glauca) realizadas pela frota espinheleira de Itajaí - SC, Brasil." Universidade de São Paulo, 2003. http://www.teses.usp.br/teses/disponiveis/21/21131/tde-13082004-111652/.
Full textAbstract:
Foram analisados dados referentes às capturas do tubarão-azul (Prionace glauca) pela frota espinheleira baseada na localidade de Itajaí (SC), operando nas regiões Sudeste e Sul do Brasil e em águas internacionais adjacentes, entre os anos de 1996 a 2002. Estes foram obtidos na forma de mapas de bordo, fichas de desembarque e através de embarques nesta frota. Com as informações biológicas dos cruzeiros ajustou-se equações para a conversão dos dados de peso eviscerado dos animais capturados das fichas de desembarques para comprimento total e peso total. Após convertidos, elaborou-se a distribuição de frequência das classes de comprimento mensais e a análise da captura acumulada. Com dados dos mapas de bordo, analisouse a captura por unidade de esforço (CPUE) em peso e em número de indivíduos. Posteriormente desenvolveu-se modelagem estatística com o uso do modelo linear generalizado (GLM) para avaliar a magnitude do efeito das variáveis temporais e espaciais sobre as CPUEs. Verificou-se que o recrutamento por pesca ocorre entre maio e novembro, a ampliação da área de cópula para os 34º S, que as variáveis temporais influenciam mais nas CPUEs do que as espaciais, a correlação positiva da latitude com as CPUEs e negativa para a longitude e a necessidade de conservação deste importante grupo de predadores.<br>This study analyzed data from the capture of blue shark (Prionace glauca) by the longline fleet based in Itajaí, State of Santa Catarina, Brazil, operating in south and southeast regions and in international neighboring waters from 1996 to 2002. The data were collected in the form of logbooks, landing sheets and through research cruises personally conducted aboard the commercial fleet. Based on the biological information gathered from the cruises, equations were calculated in order to convert the data of carcass weight captured and listed in the landing sheets for total length and total weight. After data conversion, length frequency for each month and the analysis of accumulated capture was rebuilt. With the data from logbooks, CPUE/1000 hooks were analyzed in terms of kg and the number of individuals plotting of results. Statistical modeling was then developed with the use of GLM to assess the effect of time and space variables in CPUEs. At the time of fishery recruitment between May and November, the following were observed: (i) the expansion of the mating area to 34º S (ii) time variables influenced more the CPUEs than the space variables (iii) a positive correlation of the latitude with the CPUEs and a negative correlation for longitude and (iv) the need for conservation of this important group of predators.
10
Park, Jeanseong. "Longitudinal Data Analysis Using Generalized Linear Model with Missing Responses." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/33355.
Full textAbstract:
Longitudinal studies rely on data collected at several occasions from a set of selected individuals. The purpose of these studies is to use a regression-type model to express a response variable as a function of explanatory variables, or covariates. In this thesis, we use marginal models for the analysis of such data, which, coupled with the method of estimating equations, provide estimators of the main regression parameter. When some of the responses are missing or there is error in the recorded covariates, the original estimating equation may be biased. We use techniques available in the literature to modify it and regain the unbiasedness property. We prove the asymptotic normality of the regression estimator obtained under these more realistic circumstances, and provide theoretical and numerical examples to illustrate this approach.
11
Vrabeľ, Matej. "Neurčitost spojená s designem sběru dat v modelech druhové distribuce." Master's thesis, Česká zemědělská univerzita v Praze, 2017. http://www.nusl.cz/ntk/nusl-262770.
Full textAbstract:
Properly choosen input data, their form, way of the collection an the following correction as well, are the key factors affecting the accuracy of the more and more popular models of the species model distribution (SDM). A design unfluence of the data to the choosen distribution model of the virtual species has been tested. The General Linear Model (GLM) has been used. Four types of the present-absent collection designs have been tested for a virtual species on the area of the Czech Republic as follows: accidental, systematic, points on the easy accessible areas (near the communications) and the points with the higher concentration of the scientists (an area of CHKO).The TSS (True skills statistics), KAPPA and AUC (Area under curve) have been used to compare the accuracy of the prediction of the models .The points being choosen from the easy to access areas and CHKO had worse results in all of the monitored values than the accidental or the systematic choice of the points from the whole area of the Czech Republic.It results that the data collection mode affects the final accuracy of the species distribution models.
12
Xu, Zhifeng. "Best practice of risk modelling in motor insurance : using GLM and Machine Learning approach." Master's thesis, Instituto Superior de Economia e Gestão, 2020. http://hdl.handle.net/10400.5/20405.
Full textAbstract:
Mestrado em Actuarial Science<br>O pricing na atividade seguradora está a tornar-se cada vez mais interessante e desafi- ador pelo facto de a dimensão dos dados a analisar estar a crescer de forma explosiva. Torna-se assim urgente para as seguradoras reconsiderar a forma de lidar com este vol- ume de dados.
Para implementar modelos sofisticados de pricing para produtos de seguro automóvel, aplicámos técnicas de machine learning, incluindo modelos GLM penalizados e métodos de boosting, que ajudam a identificar as características mais importantes de entre uma grande quantidade de variáveis candidatas. Estes métodos também permitem detetar potenciais interações sem testar as inúmeras combinações bidimensionais. Para um uso eficiente desses métodos, é necessário compreender o objetivo do modelo, as hipóteses que o suportam e dominar as metodologias estatísticas.
Embora haja alguma evidência de um maior poder preditivo dos modelos baseados em machine learning quando comparados com os tradicionais GLM, estes últimos beneficiam de uma estrutura, mais conveniente e mais interpretável. O modelo GLM é mais fácil de ex- plicar às partes interessadas o que nos levou a utilizar os GLM na modelação do risco, mas absorvendo os ensinamentos dados pelos modelos de machine learning.
A avaliação dos modelos é realizada pela análise dos resíduos quer na fase de treino quer de validação quer ainda de teste.
Após a revisão pela equipa, aplicam-se alguns ajustes em cada modelo para reforçar a sua significância e a sua robustez. Espera-se que eles tenham alto poder preditivo nos dados fora da amostra e possam, portanto, ser usados no futuro.<br>Insurance pricing nowadays is getting more and more interesting and challenging due to the fact that the dimension of analysable data is evolutionarily exploding. It is an urgent call for insurers to reconsider how to deal with the data more accurately and precisely. To implement pricing sophistication in motor insurance products, we apply cutting edge machine learning techniques including penalized GLM and boosting methods, which help us identify the important features among massive amount of candidate variables, and detect potential interactions without trying the endless two-way combinations manually. In order to sufficiently make use of these methods, we need to deeply understand the research objective, preliminary assumptions and statistical backgrounds.
Although there is some evidence indicating the existence of higher predictive power of machine learning models compared with traditional GLM (Generalized Linear Models), GLM is more convenient and interpretable, especially for multiplicative models. GLM model is easier to be demonstrated to stakeholder, therefore we still achieve our risk models in GLM, but absorbing the insights from our machine learning results.
The evaluation of models is done by progression, it is generally performed by residual analysis of the training or validation dataset, and testing errors for the holdout dataset. After peer review, we apply some adjustment in each model, to get models that are significant and robust. They are expected to have high predictive power in the out-of- sample data, thus can be used in the future.<br>info:eu-repo/semantics/publishedVersion
13
Penedo, Marta Sofia Grilo. "Análise por componentes independentes dos exames de EEG/IfRM de epilepsia." Master's thesis, Faculdade de Ciências e Tecnologia, 2012. http://hdl.handle.net/10362/8472.
Full textAbstract:
Dissertação para obtenção do Grau de Mestre em Engenharia Biomédica<br>A associação de técnicas de imagem, para obter resultados mais fiáveis e reais, tem sido uma constante. Uma das associações com maior utilização e sucesso é EEG/IfRM, em especial na epilepsia. A aquisição simultânea EEG/IfRM na actividade epileptiforme interictal alia a elevada resolução temporal do EEG à grande resolução espacial da IfRM, permitindo obter a localização do foco epiléptico, necessária para o planeamento cirúrgico.
Neste trabalho pretende-se apresentar a Análise por Componentes Independentes (ICA), como um método de análise de dados de EEG/IfRM, capaz de extrair a topografia das descargas epileptiformes. Os objectivos passam pela análise da ocorrência de activações no sinal BOLD, relativas às descargas epilépticas, e da relação entre as sequências funcionais de cada indivíduo, segundo duas abordagens: (1) referente à localização das zonas de activação, com o modelo GLM, através dos dados de EEG e IfRM, e (2) recorrendo à ICA para obter as zonas de activação detectadas pela primeira abordagem.
Os resultados permitem sugerir a ICA como um método complementar com elevado potencial, possibilitando a obtenção das zonas de descarga epiléptica esperadas, bem como outras activações, apresentando algumas limitações que constituem objecto de estudo.
14
Hatzinger, Reinhold. "A GLM framework for item response theory models. Reissue of 1994 Habilitation thesis." Department of Statistics and Mathematics, WU Vienna University of Economics and Business, 2008. http://epub.wu.ac.at/1384/1/document.pdf.
Full textAbstract:
The aim of the monograph is to contribute towards bridging the gap between methodological developments that have evolved in the social sciences, in particular in psychometric research, and methods of statistical modelling in a more general framework. The first part surveys certain special psychometric models (often referred to as Rasch family of models) that share common properties: separation of parameters describing qualities of the subject under investigation and parameters related to properties of the situation under which the response of a subject is observed. Using conditional maximum likelihood estimation, both types of parameters may be estimated independently from each other. In particular, the Rasch model, the rating scale model, the partial credit model, hybrid types, and linear extensions thereof are treated. The second part reviews basic ideas of generalized linear models (GLMs) as an an excellent framework for unifying different approaches and providing a natural, technical background for model formulation, estimation and testing. This is followed by a short introduction to the software package GLIM chosen to illustrate the formulation of psychometric models in the GLM framework. The third part is the main part of this monograph and shows the application of generalized linear models to psychometric approaches. It gives a unified treatment of Rasch family models in the context of log-linear models and contains some new material on log-linear longitudinal modelling. The last part of the monograph is devoted to show the usefulness of the latent variable approach in a variety of applications, such as panel, cross-over, and therapy evaluation studies, where standard statistical analysis does not necessarily lead to satisfactory results. (author´s abstract)<br>Series: Research Report Series / Department of Statistics and Mathematics
15
Biasoli, Patrícia Klaser. "Modelagem conjunta de média e variância em experimentos fracionados sem repetição utilizando GLM." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2005. http://hdl.handle.net/10183/5631.
Full textAbstract:
A modelagem conjunta de média e variância tem se mostrado particularmente relevante na obtenção de processos e produtos robustos. Nesse contexto, deseja-se minimizar a variabilidade das respostas simultaneamente com o ajuste dos fatores, tal que se obtenha a média da resposta próxima ao valor alvo. Nos últimos anos foram desenvolvidos diversos procedimentos de modelagem conjunta de média e variância, alguns envolvendo a utilização dos Modelos Lineares Generalizados (GLMs) e de projetos fatoriais fracionados. O objetivo dessa dissertação é apresentar uma revisão bibliográfica sobre projetos fatoriais fracionados e GLM, bem como apresentar as propostas de modelagem conjunta encontradas na literatura. Ao final, o trabalho enfatiza a proposta de modelagem conjunta de média e variância utilizando GLM apresentada por Lee e Nelder (1998), ilustrando-a através de um estudo de caso.
16
Lachmann, Jon. "Subsampling Strategies for Bayesian Variable Selection and Model Averaging in GLM and BGNLM." Thesis, Stockholms universitet, Statistiska institutionen, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-194715.
Full textAbstract:
Bayesian Generalized Nonlinear Models (BGNLM) offer a flexible alternative to GLM while still providing better interpretability than machine learning techniques such as neural networks. In BGNLM, the methods of Bayesian Variable Selection and Model Averaging are applied in an extended GLM setting. Models are fitted to data using MCMC within a genetic framework in an algorithm called GMJMCMC. In this thesis, we present a new implementation of the algorithm as a package in the programming language R. We also present a novel algorithm called S-IRLS-SGD for estimating the MLE of a GLM by subsampling the data. Finally, we present some theory combining the novel algorithm with GMJMCMC/MJMCMC/MCMC and a number of experiments demonstrating the performance of the contributed algorithm.
17
Milhaud, Xavier. "Mélanges de GLMs et nombre de composantes : application au risque de rachat en Assurance Vie." Thesis, Lyon 1, 2012. http://www.theses.fr/2012LYO10097/document.
Full textAbstract:
La question du rachat préoccupe les assureurs depuis longtemps notamment dans le contexte des contrats d'épargne en Assurance-Vie, pour lesquels des sommes colossales sont en jeu. L'émergence de la directive européenne Solvabilité II, qui préconise le développement de modèles internes (dont un module entier est dédié à la gestion des risques de comportement de rachat), vient renforcer la nécessité d'approfondir la connaissance et la compréhension de ce risque. C'est à ce titre que nous abordons dans cette thèse les problématiques de segmentation et de modélisation des rachats, avec pour objectif de mieux connaître et prendre en compte l'ensemble des facteurs-clefs qui jouent sur les décisions des assurés. L'hétérogénéité des comportements et leur corrélation ainsi que l'environnement auquel sont soumis les assurés sont autant de difficultés à traiter de manière spécifique afin d'effectuer des prévisions. Nous développons ainsi une méthodologie qui aboutit à des résultats très encourageants ; et qui a l'avantage d'être réplicable en l'adaptant aux spécificités de différentes lignes de produits. A travers cette modélisation, la sélection de modèle apparaît comme un point central. Nous le traitons en établissant les propriétés de convergence forte d'un nouvel estimateur, ainsi que la consistance d'un nouveau critère de sélection dans le cadre de mélanges de modèles linéaires généralisés<br>Insurers have been concerned about surrenders for a long time especially in Saving business, where huge sums are at stake. The emergence of the European directive Solvency II, which promotes the development of internal risk models (among which a complete unit is dedicated to surrender risk management), strengthens the necessity to deeply study and understand this risk. In this thesis we investigate the topics of segmenting and modeling surrenders in order to better know and take into account the main risk factors impacting policyholders’ decisions. We find that several complex aspects must be specifically dealt with to predict surrenders, in particular the heterogeneity of behaviours and their correlations as well as the context faced by the insured. Combining them, we develop a methodology that seems to provide good results on given business lines, and that moreover can be adapted for other products with little effort. However the model selection step suffers from a lack of parsimoniousness: we suggest to use another criteria based on a new estimator, and prove its consistant properties in the framework of mixtures of generalized linear models
18
Chardon, Jérémy. "Intérêts de la méthode des analogues pour la génération de scénarios de précipitations à l'échelle de la France métropolitaine : Cohérence spatiale et adaptabilité du lien d'échelle." Thesis, Grenoble, 2014. http://www.theses.fr/2014GRENU044/document.
Full textAbstract:
Les scénarios hydrologiques requis pour les études d'impacts hydrologiques nécessitent de disposer de scénarios météorologiques non biaisés et qui soient de surcroît adaptés aux échelles spatiales et temporelles des hydro-systèmes considérés. Les scénarios météorologiques obtenus en sortie brute des modèles de climat et/ou des modèles de prévision numérique du temps sont de ce fait non appropriées. Les sorties de ces modèles sont par suite souvent adaptées à l'aide de Méthodes de Descente d'Echelle Statistique (MDES). Depuis les années 2000, les MDES ont beaucoup été utilisées pour la génération de scénarios météorologiques en un site. En revanche, la génération de scénarios spatiaux couvrant de larges territoires est une tâche plus difficile, en particulier lorsque l'on souhaite respecter la cohérence spatiale des précipitations à prédire. Parmi les MDES usuelles, les approches basées sur la recherche de situations analogues passées permettent de satisfaire cette contrainte. Dans cette thèse, nous évaluons la capacité d'un Modèle Analog (MA) – où l'analogie porte sur les géopotentiels 1 000 et 500 hPa – pour la génération de scénarios de précipitation spatialement cohérents pour le territoire Français métropolitain. Dans un premier temps, la transposition spatiale du modèle MA est évaluée : le modèle s'avère utilisable pour la génération de scénarios spatiaux cohérents sur des territoires couvrant plusieurs dizaines de milliers de kilomètres carrés dès lors qu'aucune barrière climatique n'est rencontrée. Dans un second temps, nous évaluons la sensibilité des performances de prédiction à l'agrégation spatiale de la variable à prédire. L'augmentation de performance avec l'agrégation s'explique alors par la diminution de la variabilité du prédictand, pour autant que les variables de grande échelle considérées soient de bons prédicteurs pour la région considérée. Dans une dernière étude, nous explorons la possibilité d'améliorer la performance locale du modèle analogue par l'ajout de prédicteurs locaux. Le modèle combiné qui en résulte permet d'accroître sensiblement les performances de prédiction par l'adaptation du lien d'échelle sur la base d'un jeu de prédicteurs additionnels. Il apparaît de plus que la pertinence de ces prédicteurs dépend de la situation de grande échelle rencontrée ainsi que de la région considérée<br>Hydrological scenarios required for the impact studies need to have unbiased meteorological scenarios adapted to the space and time scales of the considered hydro-systems. Hence, meteorological scenarios obtained from global climate models and/or numerical weather prediction models are not really appropriated. Outputs of these models have to be post-processed, which is often carried out thanks to Statistical Downscaling Methods (SDMs). Since the 2000's, SDMs are widely used for the generation of scenarios at a single site. The generation of relevant precipitation fields over large regions or hydro-systems is conversely not straightforward, in particular when the spatial consistency has to be satisfied. One strategy to fulfill this constraint is to use a SDM based on the search of past analog situations. In this PhD, we evaluate the ability of an Analog Model (AM) – where the analogy is applied to the geopotential heights 1000 and 500 hPa – for the generation of spatially coherent precipitation scenarios over the French metropolitan territory. In a first part, the spatial transferability of an AM is evaluated: the model appears to be usable for the generation of spatial coherent scenarios over territories covering several tens of thousands squared kilometers if no climatological barrier is met in between. In a second part, we evaluate the sensitivity of the prediction performance to the spatial aggregation of the predictand. The performance increases with the aggregation level as long as the large scale variables are good predictors of precipitation for the region under consideration. This performance increase has to be related to the decrease of the predictand variability. We finally explore the possibility of improving the local performance of the AM using additional local scale predictors. For each prediction day, the prediction is obtained from a parametric regression model, for which predictors and parameters are estimated from the analog dates. The resulting combined model noticeably allows increasing the prediction performance by adapting the downscaling link for each prediction day. The selected predictors for a given prediction depend on the large scale situation and on the considered region
19
Vermelho, Alexandre Filipe Correia Cajana. "Calculating best estimates in a GLM framework. Frequency/severity models vs total loss models." Master's thesis, Instituto Superior de Economia e Gestão, 2014. http://hdl.handle.net/10400.5/7040.
Full textAbstract:
Mestrado em Ciências Actuariais<br>When using generalized linear models to predict future claim payments, should actuaries use separate frequency/severity models or a single loss cost model? This is the question this paper addresses, covering some theoretical background, testing both alternatives on real data from the Industrial Multiple Risks (IMR) sub-‐branch and analysing its results. Data was provided by 7 companies operating in Portugal in the years 2010 and 2011, who own a 70% share of the Portuguese IMR market and was collected by Associação Portuguesa de Seguradores (APS).
20
Ziv, Ronen. "Moving Beyond the RNR and GLM Models: Building a New Vision for Offender Rehabilitation." University of Cincinnati / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1479819588267395.
Full text
21
Nargis, Suraiya, and n/a. "Robust methods in logistic regression." University of Canberra. Information Sciences & Engineering, 2005. http://erl.canberra.edu.au./public/adt-AUC20051111.141200.
Full textAbstract:
My Masters research aims to deepen our understanding of the behaviour of robust
methods in logistic regression. Logistic regression is a special case of Generalized Linear
Modelling (GLM), which is a powerful and popular technique for modelling a large
variety of data. Robust methods are useful in reducing the effect of outlying values in the
response variable on parameter estimates. A literature survey shows that we are still at
the beginning of being able to detect extreme observations in logistic regression analyses,
to apply robust methods in logistic regression and to present informatively the results of
logistic regression analyses.
In Chapter 1 I have made a basic introduction to logistic regression, with an example, and
to robust methods in general.
In Chapters 2 through 4 of the thesis I have described traditional methods and some
relatively new methods for presenting results of logistic regression using powerful
visualization techniques as well as the concepts of outliers in binomial data. I have used
different published data sets for illustration, such as the Prostate Cancer data set, the
Damaged Carrots data set and the Recumbent Cow data set. In Chapter 4 I summarize
and report on the modem concepts of graphical methods, such as central dimension
reduction, and the use of graphics as pioneered by Cook and Weisberg (1999). In Section
4.6 I have then extended the work of Cook and Weisberg to robust logistic regression.
In Chapter 5 I have described simulation studies to investigate the effects of outlying
observations on logistic regression (robust and non-robust). In Section 5.2 I have come to
the conclusion that, in the case of classical or robust multiple logistic regression with no
outliers, robust methods do not necessarily provide more reasonable estimates of the
parameters for the data that contain no st~ong outliers. In Section 5.4 I have looked into
the cases where outliers are present and have come to the conclusion that either the
breakdown method or a sensitivity analysis provides reasonable parameter estimates in
that situation. Finally, I have identified areas for further study.
22
Lycarião, Thainá Alves. "Fatores controladores de Najas arguta Kunth e Egeria densa Planch em um reservatório do semiárido do Brasil." Universidade Estadual da Paraíba, 2015. http://tede.bc.uepb.edu.br/tede/jspui/handle/tede/2473.
Full textAbstract:
Submitted by Jean Medeiros (jeanletras@uepb.edu.br) on 2016-08-25T12:54:34Z
No. of bitstreams: 1
PDF - Thainá Alves Lycarião.pdf: 852519 bytes, checksum: 636ecf5fa1e6e551257df1fb958919b3 (MD5)<br>Made available in DSpace on 2016-08-25T12:54:34Z (GMT). No. of bitstreams: 1
PDF - Thainá Alves Lycarião.pdf: 852519 bytes, checksum: 636ecf5fa1e6e551257df1fb958919b3 (MD5)
Previous issue date: 2015-02-24<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES<br>Understanding the dynamics of ecosystems in semiarid regions with dry and wet extremes may help elucidate issues related to the existing pattern of interaction in these environments, and these relationships can affect the ecological interactions of organisms present in the water body. Thus, this study aimed to determine the abiotic variables that act in development of Najas arguta (Kunth) and Egeria densa (Planch), highlighting how these variables influence the relationship of the two submerged macrophytes in a reservoir in semiarid region. N arguta biomass data and E. densa were obtained in six stands, located three out of the reservoir shoreline. In each stands is selected parcels 100x50 meters, which have been measured abiotic data and collected plants through cross hooks (cor er ) 0.5m in diameter (n = 4) at depths 1m, 2m and 3m. Analysis of Variance (ANOVA) factor a + b was used to test the seasonal and spatial variation of stands and environmental variables, linear regression analysis was used to understand the dependence of N. arguta and E. densa . Generalized Linear Models (GLM) were used to select environmental variables that explain the occurrence of N. arguta , E. densa and its relationship (Najas:Egeria ). Abiotic data showed low coefficients of temporal variation (<30%) due to continued drought conditions. N. Arguta presented a variation of biomass between the months of August / 13 and April / 14, with totals of 25.67 g.m-² and 1.06 g.m-², respectively. While E. densa maintained high biomass in the entire study period. The submerged plants had different niches, showing that E. densa competition relationship with N. arguta . The predictive model for biomass of N. arguta showed that physical and chemical variables had more influence in their biomass, whereas physical, chemical and climatic variables were related more to the biomass of E. densa . The relationship Najas Egeria was influenced by conductivity, total dissolved solids and nitrite. For presenting adaptations to the conditions of the reservoir, E. densa kept his high biomass, occupying more favorable niches and suppressing the development of N. arguta .<br>Entender a dinâmica dos ecossistemas em regiões do semiárido que apresentam extremos de seca e cheia pode ajudar a elucidar questões relacionadas ao padrão de interação existentes nesses ambientes, bem como essas relações podem afetar nas interações ecológicas dos organismos presentes no corpo aquático. Desta forma, o presente trabalho teve como objetivo determinar as variáveis abióticas que atuam no desenvolvimento de Najas arguta (Kunth) e Egeria densa (Planch), ressaltando como estas variáveis influenciam na relação das duas macrófitas submersas em um reservatório no semiárido. Dados de biomassa de N. arguta e E. densa foram obtidos em seis bancos, localizados três em cada margem do reservatório. Em cada selecionou-se parcelas 100x50 metros, onde foram medidos dados abióticos e coletados plantas através de ganchos de 0,5m de diâmetro (n=4), nas profundidades 1m, 2m e 3m. banco Análise de Variância (ANOVA) fatorial a+b foi utilizada para testar a variação sazonal e espacial dos bancos e das variáveis ambientais, análise de regressão linear foi utilizada para entender a relação de dependência de N. arguta e E. densa . Modelos Lineares Generalizados (GLM) foram utilizados para selecionar as variáveis ambientais que explicam a ocorrência de N. arguta , E. densa e sua relação (Naja s:Egeria ). Os dados abióticos apresentaram baixo coeficiente de variação temporal (<30%) devido à manutenção da condição de estiagem. N. arguta apresentou variação de biomassa entre - - os meses de agosto/13 e abril/14, com valores totais de 25.67 g.m ² e 1.06 g.m ², respectivamente. Enquanto que E. densa manteve biomassa alta em todo período estudado. As macrófitas submersas apresentaram nichos diferenciados, mostrando haver uma competição de E. densa em relação N. arguta . O modelo preditivo para a biomassa de N. arguta mostrou que variáveis físicas e químicas tiveram mais influencia na sua biomassa, enquanto que variáveis físicas, químicas e climatológicas se relacionaram mais com a biomassa de E. densa . A relação de Najas:Egeria foi influenciada pela condutividade, sólidos totais dissolvidos e nitrito. Por apresentar adaptações condições do reservatório, E. densa manteve sua biomassa alta, ocupando nichos mais às favoráveis e suprimindo o desenvolvimento de N. arguta.
23
Yu, Lixi. "Regularized efficient score estimation and testing (reset) approach in low-dimensional and high-dimensional GLM." Diss., University of Iowa, 2016. https://ir.uiowa.edu/etd/2301.
Full textAbstract:
Due to the rapid development and growing need for information technologies, more and more researchers start to focus on high-dimensional data. Much work has been done on problems like point estimation possessing oracle inequalities, coefficient estimation, variable selection in high-dimensional regression models. However, with respect to the statistical inference for the regression coefficients, there have been few studies. Therefore, we propose a regularized efficient score estimation and testing (RESET) approach for treatment effects in the presence of nuisance parameters, either low-dimensional or high-dimensional, in generalized linear models (GLMs). Based on the RESET method, we are also able to develop another two-step approach related to the same problem.
The RESET approach is based on estimating the efficient score function of the treatment parameters. This means we are trying to remove the influence of nuisance parameters on the treatment parameters and construct an efficient score function which could be used for estimating and testing for the treatment effect. The RESET approach can be used in both low-dimensional and high-dimensional settings. As the simulation results show, it is comparable with the commonly used maximum likelihood estimators in most low-dimensional cases. We will prove that the RESET estimator is consistent under some regularity conditions, either in the low-dimensional or the high-dimensional linear models. Also, it is shown that the efficient score function of the treatment parameters follows a chi-square distribution, based on which the regularized efficient score tests are constructed to test for the treatment effect, in both low-dimensional and high-dimensional GLMs.
The two-step approach is mainly used for high-dimensional inference. It combines the RESET approach with a first step of selecting "promising" variables for the purpose of reducing the dimension of the regression model. The minimax concave penalty is adopted for its oracle property, which means it tends to choose "correct" variables asymptotically. The simulation results show that some improvement is still required for this approach, which will be part of our future research direction.
Finally, both the RESET and the two-step approaches are implemented with a real data example to demonstrate their application, followed by a conclusion for all the problems investigated here and a discussion for the directions of future research.
24
Davidson, Fiona. "Predicting Glass Sponge (Porifera, Hexactinellida) Distributions in the North Pacific Ocean and Spatially Quantifying Model Uncertainty." Thesis, Université d'Ottawa / University of Ottawa, 2020. http://hdl.handle.net/10393/40028.
Full textAbstract:
Predictions of species’ ranges from distribution modeling are often used to inform marine management and conservation efforts, but few studies justify the model selected or quantify the uncertainty of the model predictions in a spatial manner. This thesis employs a multi-model, multi-area SDM analysis to develop a higher certainty in the predictions where similarities exist across models and areas. Partial dependence plots and variable importance rankings were shown to be useful in producing further certainty in the results. The modeling indicated that glass sponges (Hexactinellida) are most likely to exist within the North Pacific Ocean where alkalinity is greater than 2.2 μmol l-1 and dissolved oxygen is lower than 2 ml l-1. Silicate was also found to be an important environmental predictor. All areas, except Hecate Strait, indicated that high glass sponge probability of presence coincided with silicate values of 150 μmol l-1 and over, although lower values in Hecate Strait confirmed that sponges can exist in areas with silicate values of as low as 40 μmol l-1. Three methods of showing spatial uncertainty of model predictions were presented: the standard error (SE) of a binomial GLM, the standard deviation of predictions made from 200 bootstrapped GLM models, and the standard deviation of eight commonly used SDM algorithms. Certain areas with few input data points or extreme ranges of predictor variables were highlighted by these methods as having high uncertainty. Such areas should be treated cautiously regardless of the overall accuracy of the model as indicated by accuracy metrics (AUC, TSS), and such areas could be targeted for future data collection. The uncertainty metrics produced by the multi-model SE varied from the GLM SE and the bootstrapped GLM. The uncertainty was lowest where models predicted low probability of presence and highest where the models predicted high probability of presence and these predictions differed slightly, indicating high confidence in where the models predicted the sponges would not exist.
25
Dasgupta, Tirthankar. "Robust Parameter Design for Automatically Controlled Systems and Nanostructure Synthesis." Diss., Georgia Institute of Technology, 2007. http://hdl.handle.net/1853/16300.
Full textAbstract:
This research focuses on developing comprehensive frameworks for developing robust parameter design methodology for dynamic systems with automatic control and for synthesis of nanostructures.
In many automatically controlled dynamic processes, the optimal feedback control law depends on the parameter design solution and vice versa and therefore an integrated approach is necessary. A parameter design methodology in the presence of feedback control is developed for processes of long duration under the assumption that experimental noise factors are uncorrelated over time. Systems that follow a pure-gain dynamic model are considered and the best proportional-integral and minimum mean squared error control strategies are developed by using robust parameter design. The proposed method is illustrated using a simulated example and a case study in a urea packing plant. This idea is also extended to cases with on-line noise factors. The possibility of integrating feedforward control with a minimum mean squared error feedback control scheme is explored.
To meet the needs of large scale synthesis of nanostructures, it is critical to systematically find experimental conditions under which the desired nanostructures are synthesized reproducibly, at large quantity and with controlled morphology. The first part of the research in this area focuses on modeling and optimization of existing experimental data. Through a rigorous statistical analysis of experimental data, models linking the probabilities of obtaining specific morphologies to the process variables are developed. A new iterative algorithm for fitting a Multinomial GLM is proposed and used. The optimum process conditions, which maximize the above probabilities and make the synthesis process less sensitive to variations of process variables around set values, are derived from the fitted models using Monte-Carlo simulations. The second part of the research deals with development of an experimental design methodology, tailor-made to address the unique phenomena associated with nanostructure synthesis. A sequential space filling design called Sequential Minimum Energy Design (SMED) for exploring best process conditions for synthesis of nanowires. The SMED is a novel approach to generate sequential designs that are model independent, can quickly "carve out" regions with no observable nanostructure morphology, and allow for the exploration of complex response surfaces.
26
Richter, Nils [Verfasser]. "On the use of Single-Trial Response Time in the GLM Analysis of fMRI Data / Nils Richter." Köln : Deutsche Zentralbibliothek für Medizin, 2011. http://d-nb.info/101787090X/34.
Full text
27
Zeileis, Achim, Christian Kleiber, and Simon Jackman. "Regression Models for Count Data in R." Foundation for Open Access Statistics, 2008. http://epub.wu.ac.at/4986/1/Zeileis_etal_2008_JSS_Regression%2DModels%2Dfor%2DCount%2DData%2Din%2DR.pdf.
Full textAbstract:
The classical Poisson, geometric and negative binomial regression models for count data belong to the family of generalized linear models and are available at the core of the statistics toolbox in the R system for statistical computing. After reviewing the conceptual and computational features of these methods, a new implementation of hurdle and zero-inflated regression models in the functions hurdle() and zeroinfl() from the package pscl is introduced. It re-uses design and functionality of the basic R functions just as the underlying conceptual tools extend the classical models. Both hurdle and zero-inflated model, are able to incorporate over-dispersion and excess zeros-two problems that typically occur in count data sets in economics and the social sciences-better than their classical counterparts. Using cross-section data on the demand for medical care, it is illustrated how the classical as well as the zero-augmented models can be fitted, inspected and tested in practice. (authors' abstract)
28
HUANG, BIN. "STATISTICAL ASSESSMENT OF THE CONTRIBUTION OF A MEDIATOR TO AN EXPOSURE OUTCOME PROCESS." University of Cincinnati / OhioLINK, 2001. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1005678075.
Full text
29
Drevon, Bastien. "Décomposition en blocs de la catégorie des représentations l-modulaires lisses et de longueur finie de GLm(D)." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASM002.
Full textAbstract:
Le cadre de la thèse est le suivant : soit F un corps commutatif localement compact non archimédien de caractéristique résiduelle p et soit D une algèbre à division centrale de dimension finie sur F. On fixe m un entier strictement positif et on s'intéresse à la catégorie R des représentations lisses et de longueur finie de GLm(D) à coefficients dans un corps de caractéristique l différente de p.L'objectif de la thèse est de décomposer en blocs cette catégorie.La stratégie employée consiste à trouver une condition portant sur le support supercuspidal pour que deux représentations de R aient un espace d'extension non trivial, et à utiliser cette condition pour décomposer R. Dans un premier temps, on se restreint aux représentations supercuspidales de niveau 0, puis on en déduit le cas général<br>Let F be a nonarchimedean locally compact field of residue characteristic p and let D be a finite dimensional central division algebra over F. Let m be a stricly positive integer. We study the category R of smooth finite length representations of Glm(D) on a field of characteristic l, with l not equal to p, and the aim is to find a block decomposition of this category.For this, we find a condition involving supercuspidal support for two representations in R to have a non trivial extension space, and we use this to decompose the category R. At first, we work only with supercuspidal level 0 representations, then we deduce the general case
30
VACCA, GIANMARCO. "Redundancy Analysis Models with Categorical Endogenous Variables: New Estimation Techniques Based on Vector GLM and Artificial Neural Networks." Doctoral thesis, Università degli Studi di Milano-Bicocca, 2017. http://hdl.handle.net/10281/158304.
Full textAbstract:
I modelli ad equazioni strutturali con variabili latenti hanno subito un notevole sviluppo negli ultimi anni. Partendo dai pionieri delle due macro-definizioni di modelli con variabili latenti, Covariance Structure Analysis e Component Analysis, con LISREL e PLS-PM come le tecniche più importanti, diverse estensioni e miglioramenti sono stati proposti. Inoltre, per i modelli di analisi di ridondanza, che fanno parte della Component Analysis, ma hanno solo variabili endogene osservate, sono stati proposti nuovi metodi in letteratura per affrontare più di un gruppo di variabili osservate esogene, con equazioni lineari semplici ed un'ottimizzazione unificata del problema. La critica principale, che è stata affrontata di recente in nuovi filoni di letteratura riguardanti i modelli ad equazioni strutturali, è l'incapacità parziale di questi sistemi di equazioni di modellizzare indicatori categoriali. Sono stati proposti diversi metodi a tale scopo, in PLS-PM e LISREL rispettivamente, che sfruttano metodi di Optimal Scaling o l’algoritmo EM nel processo di ottimizzazione. Per l’analisi di ridondanza, con variabili endogene solo osservate, la possibilità di estendere le procedure di stima a variabili qualitative è notevolmente meno ostacolata da restrizioni del modello, ancor di più nel modello di analisi di ridondanza estesa, con più di un blocco di variabili esogene. Questo lavoro presenta una nuova stima di modelli di analisi di ridondanza estesa in presenza di variabili endogene binarie o categoriali, con due principali tecniche di stima: Iterated Reweighed Least Squares, e Gradient Descent con backpropagation tramite reti neurali. Per questi ultimi, recenti sviluppi nei modelli ad equazioni strutturali con reti neurali saranno esaminati, e la nuova tecnica sarà quindi introdotta.<br>Structural Equation Models with latent variables have considerably developed in recent years. Starting from the pioneers of the two most prominent ways of defining models with latent variables, namely Covariance Structure Analysis and Component Analysis, with LISREL and PLS-PM as the most famous techniques, several extensions and improvements have been put forward. Moreover, for Redundancy Analysis models, which are part of the Component Analysis framework, but have only observed endogenous variables, new methods have been proposed in literature to deal with more than one group of exogenous observed variables, with simple linear equations and a unified optimization problem. One main criticism, that has been dealt with recently in new strands of literature regarding Structural Equation Modeling, is the partial inability of these systems of linear equations to deal with categorical indicators. Several methods have been proposed, in PLS-PM and LISREL respectively, either related to Optimal Scaling, or adapting the EM algorithm to the particular case under examination. In the Redundancy Analysis framework, with only observed endogenous variables, the possibility of extending the estimation procedures to a qualitative setting is considerably less hampered by model restrictions, even more so in the Extended Redundancy Analysis model, with more than one block of exogenous variables. This work will hence present a new estimation of Extended Redundancy Analysis models in presence of binary or categorical endogenous variables, with two main estimation techniques: Iterated Reweighed Least Squares, and Gradient Descent with backpropagation in an Artificial Neural Network architecture. For the latter, recent developments in Structural Equation Models in the neural networks setting will be firstly examined, and the new technique will be subsequently introduced.
31
Kusi, Joseph. "Variations in Phenotypic Plasticity and Fluctuating Asymmetry of Leaf Morphology of Three Quercus (Oak) Species in Response to Environmental Factors." Digital Commons @ East Tennessee State University, 2013. https://dc.etsu.edu/etd/1160.
Full textAbstract:
Leaf morphology of Quercus (oak) species is highly variable and complicated confounded with phenotypic plasticity and fluctuating asymmetry (FA). However, the study of variation is mostly limited to leaf morphology. This study was extended to plasticity and FA variations in Q. alba (white oak), Q. palustris (pin oak), and Q. velutina (black oak). It was hypothesized that light exposure, individual trees, leaf position, and other leaf traits will influence variation in these species. Leaves were sampled from trees of these species and their morphological traits were measured. Absolute asymmetry of leaf width and area were determined and plasticity of each species was calculated. The data were analyzed using nested ANOVA with General Linear Model. Leaf morphology, plasticity and FA varied across the species and light exposure was the main source of variation. Individual trees and several leaf covariate traits also influenced leaf morphological and FA variations in all species.
32
Přibyl, Jakub. "Vizualizace a export výstupů funkční magnetické rezonance." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-221369.
Full textAbstract:
Thesis discusses the principles and methodology for measuring functional magnetic resonance imaging (fMRI), basically the origin and use of BOLD signal types used experiments. Further attention is paid fMRI data processing and statistical analysis. Subsequent chapters are devoted to a brief description of the most common software tools used to analyze data from fMRI. The main section was to create a program in MATLAB with a detailed graphic user interface for easy visualization and export output from analyzes of fMRI data. The second half is devoted to describing the program developer and graphic user interface, including key functionality. The final section describes the application program with real data from clinical studies of dynamic connectivity and use in an international project APGem.
33
Derigs, Dominik [Verfasser], Stefanie [Gutachter] Walch-Gassner, and Simon [Gutachter] Trebst. "Ideal GLM-MHD - a new mathematical model for simulating astrophysical plasmas / Dominik Derigs ; Gutachter: Stefanie Walch-Gassner, Simon Trebst." Köln : Universitäts- und Stadtbibliothek Köln, 2018. http://d-nb.info/1170872093/34.
Full text
34
Harudová, Jana. "Analýza závislosti sociální situace na úrovni transferů a dalších faktorech." Master's thesis, Vysoká škola ekonomická v Praze, 2017. http://www.nusl.cz/ntk/nusl-358975.
Full textAbstract:
This diploma thesis deals with the social policies of the European Union and with poverty. Social policies are divided into five social models, based on basic typologies. Individual social models are characterized separately and the claims are supported by appropriate economic indicators. The practical part builds on these theoretical foundations and examines the dependence of variables and social models. Based on the indicators of poverty, the social situation of the individual states of the European Union is defined. Dependencies were created using indicators of poverty and economic variables. A generalized linear model was designed to determine the dependence of the social situation in the EU based on selected factors.
35
Zeileis, Achim, Christian Kleiber, and Simon Jackman. "Regression Models for Count Data in R." Department of Statistics and Mathematics, WU Vienna University of Economics and Business, 2007. http://epub.wu.ac.at/1168/1/document.pdf.
Full textAbstract:
The classical Poisson, geometric and negative binomial regression models for count data belong to the family of generalized linear models and are available at the core of the statistics toolbox in the R system for statistical computing. After reviewing the conceptual and computational features of these methods, a new implementation of zero-inflated and hurdle regression models in the functions zeroinfl() and hurdle() from the package pscl is introduced. It re-uses design and functionality of the basic R functions just as the underlying conceptual tools extend the classical models. Both model classes are able to incorporate over-dispersion and excess zeros - two problems that typically occur in count data sets in economics and the social and political sciences - better than their classical counterparts. Using cross-section data on the demand for medical care, it is illustrated how the classical as well as the zero-augmented models can be fitted, inspected and tested in practice. (author's abstract)<br>Series: Research Report Series / Department of Statistics and Mathematics
36
Jurečková, Kateřina. "Hledání korelátů změn tepové frekvence v fMRI datech." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2017. http://www.nusl.cz/ntk/nusl-316818.
Full textAbstract:
This master’s thesis deals with problematic of correlates finding of heart rate changes in fMRI data. The first part describes principle of fMRI, creation of BOLD signal, data acquisition, their pre-processing and analysis. The next part describes heart rate variability and its impact on fMRI data. The following section is dedicated to pre-processing of heart rate time series to the form, which can be used in correlates finding of heart rate variability and fMRI data with generalized linear model. The process of statistical testing and its result with discussion can be found in the last part of this thesis.
37
Meguellati, Fatima. "Estimation par approximation de Laplace dans les modèles GLM Mixtes : application à la gravité corporelle maximale des accidents de la route." Thesis, Lille 1, 2014. http://www.theses.fr/2014LIL10204/document.
Full textAbstract:
Cette thèse est une contribution à la construction de méthodes statistiques applicables à l’évaluation (modélisation et estimation) de certains indices utilisés pour analyser la gravité corporelle des accidents de la route. On se focalise sur quatre points lors du développement de la méthodologie adoptée : la sélection des variables (ou facteurs) présentant un effet aléatoire, la construction de modèles logistique-normaux mixtes, l’estimation des paramètres par approximation de Laplace et PQL (quasi-vraisemblance pénalisée), et la comparaison de la performance des méthodes d’estimation. Dans une première contribution, on construit un modèle logistique-Normal avec « Type de collision » comme variable à effet aléatoire pour analyser la gravité corporelle maximale observée dans un échantillon de véhicules accidentés. Des méthodes d’estimation fondées sur l’approximation de Laplace de la log-vraisemblance sont proposées pour estimer et analyser la contribution des variables présentes dans le modèle. On compare, par simulation, cette approximation Laplacienne à celle basée sur l’adaptation des polynômes de Gauss-Hermite (AGH). On montre que les deux approches sont équivalentes par rapport à la précision de l’estimation bien qu’AGH soit légèrement supérieure. Une deuxième contribution consiste à adapter certains algorithmes de la famille PQL à l’estimation des paramètres d’un deuxième modèle et à comparer sa performance en termes de biais aux méthodes de Laplace et AGH. Deux exemples de données simulées illustrent les résultats obtenus. Dans une troisième et dense contribution, on identifie plusieurs modèles logistique-normaux mixtes avec plus d’un effet aléatoire. La convergence numérique des algorithmes (Laplace, AGH, PQL) ainsi que la précision des estimations sont étudiées. Des simulations ainsi qu’une base de données détaillées d’accidents sont utilisées pour analyser la performance des modèles à détecter des véhicules contenant des usagers ayant des blessures graves corporelles maximales. Une programmation orientée R accompagnent l’ensemble des résultats obtenus. La thèse se termine sur des perspectives relatives aux critères de sélection de modèles GLM Mixtes et à l’extension de ces modèles à la famille multinomiale<br>This thesis is a contribution to the construction of statistical methods for the evaluation (modeling and estimation) of some indices used to analyze the injury severity of road crashes. We focus on four points during the development of the adopted methodology: the random variables (or factors) selection, the construction of mixed logistic-Normal model, the parameters estimation by Laplace approximation and PQL (penalized quasi-likelihood) and the performance comparison of the estimation methods. In a first contribution, a logistic-Normal model is constructed with "collision type" as random variable to analyze the maximum injury severity observed in a sample of crashed vehicles. Estimation methods based on the Laplace approximation of the log-likelihood are proposed to estimate and analyze the contribution of variables in the model. We compare, by simulation, this Laplacian approximation to those based on the adaptation of Gauss-Hermite polynomials (AGH). We show that the two approaches are equivalent with respect to the accuracy of the estimate although AGH is superior. A second contribution is to adapt some algorithms of PQL family to estimate the parameters of a second model and compare its performance to Laplace and AGH methods in terms of bias. Two examples of simulated data illustrate the obtained results. In a third and dense contribution, we identify several mixed logistic-Normal models with more than one random effect. The convergence of the algorithms (Laplace, AGH, and PQL) and the precision of the estimates are investigated. Simulations as well as a database of detailed crash data are used to analyze the models performance to detect vehicles containing users with maximum injury severity. Programming oriented R accompany all results. The thesis concludes with perspectives on GLM Mixed models selection criteria and the extension of these models to the multinomial family
38
Torres, Lopez Luis Enrique, and Salazar Alejandro Munguia. "CONTRASTE ENTRE MODELOS DE REDES NEURONALES ARTIFICIALES, GLM Y GARCH EN EL PRONOSTICO Y ANALISIS DEL TIPO DE CAMBIO MEXICANO: 2000-2014." Tesis de Licenciatura, UNIVERSIDAD AUTONOMA DEL ESTADO DE MEXICO, 2016. http://hdl.handle.net/20.500.11799/64256.
Full textAbstract:
En el análisis y pronóstico del tipo de cambio existen estudios basados en técnicas de series de tiempo junto a modelos paramétricos tales como: regresiones, modelos multivariados y de panel pero muy pocos se aventuran en el terreno no para-métrico como el de la inteligencia artificial específicamente las redes neuronales artificiales (RNA) las cuales tienen ventajas como: aprendizaje, auto organización, tolerancia a fallos, flexibilidad y por ello es posible crear una herramienta basada en RNA con mayor certidumbre a los métodos tradicionales, con ellas, se pueden observar los periodos con mayores fluctuaciones así como los componentes que determinan el comportamiento del tipo de cambio
39
MUNGUIA, SALAZAR ALEJANDRO, and LOPEZ LUIS ENRIQUE TORRES. "CONTRASTE ENTRE MODELOS DE REDES NEURONALES ARTIFICIALES, GLM Y GARCH EN EL PRONOSTICO Y ANALISIS DEL TIPO DE CAMBIO MEXICANO: 2000-2014." Tesis de Licenciatura, Universidad Autónoma del Estado de México, 2016. http://hdl.handle.net/20.500.11799/64274.
Full textAbstract:
En el análisis y pronóstico del tipo de cambio existen estudios basados en técnicas de series de tiempo junto a modelos paramétricos tales como: regresiones, modelos multivariados y de panel pero muy pocos se aventuran en el terreno no para-métrico como el de la inteligencia artificial específicamente las redes neuronales artificiales (RNA) las cuales tienen ventajas como: aprendizaje, auto organización, tolerancia a fallos, flexibilidad y por ello es posible crear una herramienta basada en RNA con mayor certidumbre a los métodos tradicionales, con ellas, se pueden observar los periodos con mayores fluctuaciones así como los componentes que determinan el comportamiento del tipo de cambio
8
Se construyeron 5 modelos en total, 3 de Redes Neuronales Artificiales (RNA), un modelo lineal (GLM) y uno de tipo GARCH donde los modelos basados en inteligencia artificial permitieron una mayor certidumbre de predicción con los datos disponibles y publicados únicamente por el Instituto Nacional de Estadística y Geografía (INEGI) en un periodo de análisis de 2000 a 2014, datos libres y homólogos en metodología para su consulta, así como se destaca el uso dado al software libre especializado.
40
TORRES, LOPEZ LUIS ENRIQUE. "“Contraste entre modelos de Redes Neuronales Artificiales, GLM y GARCH en el pronóstico y análisis del tipo de cambio mexicano: 2000-2014”." Tesis de Licenciatura, UNIVERSIDAD AUTONOMA DEL ESTADO DE MEXICO, 2016. http://hdl.handle.net/20.500.11799/67002.
Full textAbstract:
El tipo de cambio, visto como relación proporcional entre el valor de una moneda y otra
es una variable macroeconómica importante de la economía globalizada, en el caso de
México la paridad más importante que existe es la del peso (MXN) con respecto al dólar
americano (USD) por la estrecha relación de intercambio comercial y de inversión que
existe con los Estados Unidos.
La variable es comparativa, una imagen útil para los hacedores de política y
tomadores de decisiones en empresas privadas; repercute en la inflación, en el poder
adquisitivo, golpea seriamente al comercio en mercados que dependen de insumos
importados, así como los empleos generados por él, debilita e impacta en la calidad de
vida de la población y crea una imagen del país hacia el exterior ahí radica la necesidad
de poder generar pronósticos eficientes y precisos de él al emplear herramientas de
predicción que permitan hacer un análisis amplio del comportamiento de esta variable
con fines de tomar medidas ante efectos negativos además de aprovechar los positivos
cuando estos se den.
En el análisis y pronóstico del tipo de cambio existen estudios basados en técnicas
de series de tiempo junto a modelos paramétricos tales como: regresiones, modelos
multivariados y de panel pero muy pocos se aventuran en el terreno no para-métrico
como el de la inteligencia artificial específicamente las redes neuronales artificiales
(RNA) las cuales tienen ventajas como: aprendizaje, auto organización, tolerancia a
fallos, flexibilidad y por ello es posible crear una herramienta basada en RNA con mayor
certidumbre a los métodos tradicionales, con ellas, se pueden observar los periodos con
mayores fluctuaciones así como los componentes que determinan el comportamiento
del tipo de cambio
41
Drakenward, Ellinor, and Emelie Zhao. "Modeling risk and price of all risk insurances with General Linear Models." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-275696.
Full textAbstract:
Denna kandidatexamen ligger inom området matematisk statistik. I samarbete med försäkringsbolaget Hedvig syftar denna avhandling till att utforska en ny metod för hantering av Hedvigs försäkringsdata genom att bygga en prissättningsmodell för alla riskförsäkringar med generaliserade linjära modeller. Två generaliserade linjära modeller byggdes, där den första förutspår frekvensen för ett anspråk och den andra förutspår svårighetsgraden. De ursprungliga uppgifterna delades in i 9 förklarande variabler. Båda modellerna inkluderade fem förklarande variabler i början och reducerades sedan. Minskningen resulterade i att fyra av fem egenskaper var förklarande signifikanta i frekvensmodellen och endast en av de fem var förklarande signifikanta i svårighetsmodellen. Var och en av modellerna erhöll relativa risker för nivåerna av deras förklarande variabler. De relativa riskerna resulterade i en total risk för varje nivå. Genom multiplicering av en skapad basnivå med en uppsättning kombination av riskparametrar kan premien för en vald kund erhållas.<br>Det här kandidatexamensarbetet ligger inom ämnet matematisk statistik. Jag samarbete med försäkringsbolaget Hedvig, avser uppsatsen att undersöka en ny metod att hantera Hedvigs försäkringsdata genom att bygga en prissättningsmodell för drulleförsäkring med hjälp av generaliserade linjära modeller. Två modeller skapades varav den första förutsättningen frekvensen av ett försäkringsanspråk och den andra förutsäger storleken. Originaldatan var indelad i 9 förklarande variabler. Båda modellerna innehöll till en början fem förklarande variabler, vilka sedan reducerades till fyra respektive en variabler i de motsvarande modellerna. Från varje modell kunde sedan de relativa riskerna tas fram för varje kategori av de förklarande variablerna. Tillsammans bildades sedan totalrisken för alla grupper.
42
Leodolter, Johannes. "A Statistical Analysis of the Lake Levels at Lake Neusiedl." Austrian Statistical Society, 2008. http://epub.wu.ac.at/5634/1/296%2D1009%2D1%2DSM.pdf.
Full textAbstract:
A long record of daily data is used to study the lake levels of Lake Neusiedl, a large steppe lake at the eastern border of Austria. Daily lake level changes are modeled as functions of precipitation, temperature, and wind conditions. The occurrence and the amount of daily precipitation
are modeled with logistic regressions and generalized linear models.
43
Bracken, Jason. "A Consensus Model for Predicting the Distribution of the Threatened Plant Telephus Spurge (Euphorbia Telephioides)." Miami University / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=miami1480622681613979.
Full text
44
Andrade, Renan Siqueira Leite de. "Estudo do comportamento migratório da truta (Salmo trutta L.) no limite sul de sua distribuição." Master's thesis, Universidade de Évora, 2020. http://hdl.handle.net/10174/27971.
Full textAbstract:
A região central de Portugal representa o limite sul da distribuição dos dois ecótipos de Salmo trutta L, o residente (i.e., truta-de-rio) e o anádromo (i.e., truta-marisca). Para além dos constrangimentos a uma escala mais global que as espécies de peixes experienciam, como o aquecimento global, os rios dessa região estão severamente fragmentados pela presença de grandes barragens e pequeno-médios açudes, construídos maioritariamente para a produção de eletricidade e recolha de água para uso doméstico, industrial e para a agricultura. Esforços direcionados ao aumento do conhecimento sobre a truta em resposta às pressões antropogênicas e pela mitigação da fragmentação do habitat existente, têm sido constantemente desenvolvidos nos últimos 8-10 anos no Rio Mondego. Considerado um dos mais importantes rios em Portugal para peixes migradores, uma passagem para peixes de fendas verticais (i.e., 125 metros de comprimento, 23 bacias) foi construída em 2011 no Açude-Ponte de Coimbra e monitorização contínua vem sendo realizada desde 2013 com recurso a censos visuais. Os dados de contagem sobre a truta revelaram que entre 2013 e 2017 mais de 300 trutas utilizaram com sucesso a passagem durante a sua migração para montante. Nos anos estudados, os meses com maior contagem de trutas foram maio (21,1%), junho (52,7%) e julho (14,3%). O padrão circadiano dos movimentos para montante revelou que as trutas migraram pela passagem maioritariamente ao amanhecer e no final do dia. O tamanho das trutas utilizando a passagem com sucesso foi dependente do mês, pois as maiores trutas (CT>300 mm) tendem a usar a passagem mais cedo (em maio), seguida daquelas de menores dimensões (CT<300 mm), que tendem a utilizar a passagem mais tarde na época de migração (julho). Modelos exploratórios revelaram que fatores ambientais como o fotoperíodo e o período do dia, estão significativamente influenciando o uso da passagem para peixes pelas trutas durante todos os anos de estudo; Abstract:
Study of Migration Behavior of Trout (Salmo trutta L.) in the Southern Limit of its Distribution
The central region of Portugal represents the southern limit of the distribution of both ecotypes of Salmo trutta L, the resident (i.e., brown trout) and anadromous (i.e., sea trout). Besides the constraints, such as global warming, that the species experiences, rivers in this region are severely fragmented by the presence of large dams and small-to-medium weirs, built mainly for hydroelectricity production and water abstraction for domestic, industrial and agriculture uses. Efforts towards an increase in the knowledge of trout responses to anthropogenic pressures and for the mitigation of existent habitat fragmentation have been consistently developed for the last 8-10 years in Mondego River. Considered one of the most important rivers in Portugal for migratory fish, a vertical-slot fishway (i.e., 125 meters long, 23 pools) was built in 2011 at the Coimbra dam and monitoring is continuously being conducted since 2013 using visual census. Count data on trout revealed that between 2013 and 2017 more than 300 trouts have successfully used this fish pass during their upstream migration. In the studied years, the months with the highest trout count were May (21.1%), June (52.7%) and July (14.3%). Circadian pattern of upstream movement revealed that trouts migrate through the fish pass mostly in the morning and at the end of the day. Size of trout successfully using the fish pass was month dependent, as larger trouts (CT>300mm) tend to use the fish pass earlier (in May), followed by those with smaller dimensions (CT<300 mm), that tend to use the fish pass later on the migration season (July). Explanatory models revealed that different environmental factors, such as photoperiod and day period, are significantly influencing fish pass use by trout in all the studied years.
45
O'Leary, Brian. "A Vertex-Based Approach to the Statistical and Machine Learning Analyses of Brain Structure." University of Toledo / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1576254162111087.
Full text
46
Batista, Douglas Toledo. "Modelos para dados de contagem com superdispersão: uma aplicação em um experimento agronômico." Universidade de São Paulo, 2015. http://www.teses.usp.br/teses/disponiveis/11/11134/tde-21092015-105550/.
Full textAbstract:
O modelo de referência para dados de contagem é o modelo de Poisson. A principal característica do modelo de Poisson é a pressuposição de que a média e a variância são iguais. No entanto, essa relação de média-variância nem sempre ocorre em dados observacionais. Muitas vezes, a variância observada nos dados é maior do que a variância esperada, fenômeno este conhecido como superdispersão. O objetivo deste trabalho constitui-se na aplicação de modelos lineares generalizados, a fim de selecionar um modelo adequado para acomodar de forma satisfatória a superdispersão presente em dados de contagem. Os dados provêm de um experimento que objetivava avaliar e caracterizar os parâmetros envolvidos no florescimento de plantas adultas da laranjeira variedade \"x11\", enxertadas nos limoeiros das variedades \"Cravo\" e \"Swingle\". Primeiramente ajustou-se o modelo de Poisson com função de ligação canônica. Por meio da deviance, estatística X2 de Pearson e do gráfico half-normal plot observou-se forte evidência de superdispersão. Utilizou-se, então, como modelos alternativos ao Poisson, os modelos Binomial Negativo e Quase-Poisson. Verificou que o modelo Quase-Poisson foi o que melhor se ajustou aos dados, permitindo fazer inferências mais precisas e interpretações práticas para os parâmetros do modelo.<br>The reference model for count data is the Poisson model. The main feature of Poisson model is the assumption that mean and variance are equal. However, this mean-variance relationship rarely occurs in observational data. Often, the observed variance is greater than the expected variance, a phenomenon known as overdispersion. The aim of this work is the application of generalized linear models, in order to select an appropriated model to satisfactorily accommodate the overdispersion present in the data. The data come from an experiment that aimed to evaluate and characterize the parameters involved in the flowering of orange adult plants of the variety \"x11\" grafted on \"Cravo\" and \"Swingle\". First, the data were submitted to adjust by Poisson model with canonical link function. Using deviance, generalized Pearson chi-squared statistic and half-normal plots, it was possible to notice strong evidence of overdispersion. Thus, alternative models to Poisson were used such as the negative binomial and Quasi-Poisson models. The Quasi-Poisson model presented the best fit to the data, allowing more accurate inferences and practices interpretations for the parameters.
47
Martins, Fernando de Farias. "Preferência de umidade na oviposição de grilos de serrapilheira (orthoptera: grylloidea): experimentos de campo e laboratório." Universidade Estadual do Oeste do Paraná, 2017. http://tede.unioeste.br/handle/tede/3478.
Full textAbstract:
Submitted by Edineia Teixeira (edineia.teixeira@unioeste.br) on 2018-03-05T18:27:51Z
No. of bitstreams: 2
Fernando_Martins2017.pdf: 3146180 bytes, checksum: a1dcde101c1559cda9b93c488d0f17e9 (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)<br>Made available in DSpace on 2018-03-05T18:27:51Z (GMT). No. of bitstreams: 2
Fernando_Martins2017.pdf: 3146180 bytes, checksum: a1dcde101c1559cda9b93c488d0f17e9 (MD5)
license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5)
Previous issue date: 2017-02-16<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES<br>For species that do not exhibit parental care such as oviparous insects, choosing a favorable oviposition site is of utmost importance for brood success. Niche theory predicts that crickets should show a bell-shaped oviposition response to substrate humidity. However, at least one lab experiment with mole crickets (Orthoptera: Gryllotalpoidea) indicated a linear oviposition responses to substrate humidity. The house cricket Acheta domesticus (Orthoptera: Grylloidea) also shows a linear juvenile body growth response to substrate humidity, which suggests a positive relationship between humidity and oviposition preference. We evaluated the relationship between oviposition frequency and substrate humidity in forest litter-
dwelling species, primarily composed of Ubiquepuella telytokous, using field experiments. We also tested oviposition responses of U. telytokous to substrate humidity in a laboratory experiment. We offered oviposition substrates that varied in humidity from zero percent to maximum substrate water absorption capacity. Oviposition preference was estimated using presence or absence of eggs as a binary response variable, adjusted logistic regression (GAMM) was used to test for non-linear responses, and GLMs were used to test linear responses. We found that oviposition probability increased linearly with substrate humidity for U. telytokous in both field and lab experiments. Our results demonstrate the importance of substrate humidity as an ecological niche requirement for this species. This work bolsters knowledge of litter cricket life history association with humidity, and suggests that litter crickets may be particularly threatened by changes in climate that favor habitat drying.<br>Para espécies que não apresentam cuidados parentais, tais como insetos ovíparos, a escolha de um local de oviposição favorável é de extrema importância para o sucesso da prole. A teoria do nicho prevê que a oviposição de grilos deve mostrar uma resposta em forma de sino à umidade do substrato. Entretanto, pelo menos um experimento de laboratório com paquinhas (Orthoptera: Gryllotalpoidea) indicou uma resposta de oviposição linear em relação a umidade do substrato. O grilo doméstico Acheta domesticus (Orthoptera: Grylloidea) também apresenta um crescimento corporal dos juvenis linear em relação a umidade do substrato, o que sugere uma relação positiva entre umidade e preferência de oviposição. Aqui testamos a relação entre a frequência de oviposição e a umidade do substrato, em espécies de grilos de serrapilheira florestal, primariamente compostas Ubiquepuella telytokous, utilizando experimentos de campo. Também testamos as respostas de oviposição de U. telytokous em experimentos de laboratório. Oferecemos substratos de oviposção que variaram a umidade de zero porcento até a capacidade máxima de absorção do substrato. A preferência de oviposição foi estimada utilizando presença ou ausência de ovos como uma variável resposta binária, regressão logística ajustada (GAMM) para testar respostas não lineares, e GLMs para testar respostas lineares. Verificamos que a probabilidade de oviposição aumenta linearmente com a umidade do substrato para U. telytokous, nos experimentos de campo e laboratório. Nossos resultados demonstram a importância da umidade do substrato como requisito de nicho ecológico para Ubiquepuella telytokous. Este trabalho reforça o conhecimento da associação de história de vida de grilos com a umidade, e sugere que esses organismos podem ser particularmente ameaçados por mudanças climáticas que tornam habitats áridos.
48
Ištok, Martin. "Analýza simultánně měřených EEG/fMRI dat s využitím zpracování EEG signálu." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-221335.
Full textAbstract:
The main objective of this diploma thesis is to describe simultaneous electroencephalography-correlated functional magnetic resonance imaging analysis using EEG data processing. It includes basic characteristics of EEG and fMRI recording and analysis and their combination as simultaneous EEG/fMRI analysis and deals with obstructions during its processing. The thesis includes a design of an experiment used for recording and analysis of simultaneous EEG/fMRI data using EEG source reconstruction for regressor construction. Thesis incorporates a software solution used for extraction of signal describing a source activity interpolated by EEG source reconstruction. The signal is then processed and used to construct a basic regressor. The thesis also deals with the software solution being used for a study focused on intracranial epileptic discharges localization using a simultaneous EEG/fMRI analysis in which it reveals source activity during ongoing epileptic spike and summarizes the results.
49
Varnet, Léo. "Identification des indices acoustiques utilisés lors de la compréhension de la parole dégradée." Thesis, Lyon 1, 2015. http://www.theses.fr/2015LYO10221/document.
Full textAbstract:
Bien qu’il existe un large consensus de la communauté scientifique quant au rôle des indices acoustiques dans la compréhension de la parole, les mécanismes exacts permettant la transformation d’un flux acoustique continu en unités linguistiques élémentaires demeurent aujourd’hui largement méconnus. Ceci est en partie dû à l’absence d’une méthodologie efficace pour l’identification et la caractérisation des primitives auditives de la parole. Depuis les premières études de l’interface acoustico-phonétique par les Haskins Laboratories dans les années 50, différentes approches ont été proposées ; cependant, toutes sont fondamentalement limitées par l’artificialité des stimuli utilisés, les contraintes du protocole expérimental et le poids des connaissances a priori nécessaires. Le présent travail de thèse s’est intéressé { la mise en oeuvre d’une nouvelle méthode tirant parti de la situation de compréhension de parole dégradée pour mettre en évidence les indices acoustiques utilisés par l’auditeur.Dans un premier temps, nous nous sommes appuyés sur la littérature dans le domaine visuel en adaptant la méthode des Images de Classification à une tâche auditive de catégorisation de phonèmes dans le bruit. En reliant la réponse de l’auditeur { chaque essai à la configuration précise du bruit lors de cet essai, au moyen d’un Modèle Linéaire Généralisé, il est possible d’estimer le poids des différentes régions temps-fréquence dans la décision. Nous avons illustré l’efficacité de notre méthode, appelée Image de Classification Auditive, à travers deux exemples : une catégorisation /aba/-/ada/, et une catégorisation /da/-/ga/ en contexte /al/ ou /aʁ/. Notre analyse a confirmé l’implication des attaques des formants F2 et F3, déjà suggérée par de précédentes études, mais a également permis de révéler des indices inattendus. Dans un second temps, nous avons employé cette technique pour comparer les résultats de participants musiciens experts (N=19) ou dyslexiques (N=18) avec ceux de participants contrôles. Ceci nous a permis d’étudier les spécificités des stratégies d’écoute de ces différents groupes.L’ensemble des résultats suggèrent que les Images de Classification Auditives pourraient constituer une nouvelle approche, plus précise et plus naturelle, pour explorer et décrire les mécanismes { l’oeuvre au niveau de l’interface acoustico-phonétique<br>There is today a broad consensus in the scientific community regarding the involvement of acoustic cues in speech perception. Up to now, however, the precise mechanisms underlying the transformation from continuous acoustic stream into discrete linguistic units remain largely undetermined. This is partly due to the lack of an effective method for identifying and characterizing the auditory primitives of speech. Since the earliest studies on the acoustic–phonetic interface by the Haskins Laboratories in the 50’s, a number of approaches have been proposed; they are nevertheless inherently limited by the non-naturalness of the stimuli used, the constraints of the experimental apparatus, and the a priori knowledge needed. The present thesis aimed at introducing a new method capitalizing on the speech-in-noise situation for revealing the acoustic cues used by the listeners.As a first step, we adapted the Classification Image technique, developed in the visual domain, to a phoneme categorization task in noise. The technique relies on a Generalized Linear Model to link each participant’s response to the specific configuration of noise, on a trial-by-trail basis, thereby estimating the perceptual weighting of the different time-frequency regions for the decision. We illustrated the effectiveness of our Auditory Classification Image method through 2 examples: a /aba/-/ada/ categorization and a /da/-/ga/ categorization in context /al/ or /aʁ/. Our analysis confirmed that the F2 and F3 onsets were crucial for the tasks, as suggested in previous studies, but also revealed unexpected cues. In a second step, we relied on this new method to compare the results of musical experts (N=19) or dyslexics participants (N=18) to those of controls. This enabled us to explore the specificities of each group’s listening strategies.All the results taken together show that the Auditory Classification Image method may be a more precise and more straightforward approach to investigate the mechanisms at work at the acoustic-phonetic interface
50
Lu, Rong. "Statistical Methods for Functional Genomics Studies Using Observational Data." The Ohio State University, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=osu1467830759.
Full text