To see the other types of publications on this topic, follow the link: Test des composantes de la variance.
Dissertations / Theses on the topic 'Test des composantes de la variance'
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 'Test des composantes de la variance.'
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
Guédon, Tom. "Tests des composantes de la variance dans les modèles à effets mixtes pour des petits échantillons. Application à l'étude de la variabilité génotypique chez Arabidopsis thaliana." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPASM046.
Full textAbstract:
Les modèles à effets mixtes permettent d'analyser des données présentant une structure hiérarchique, telles que les données longitudinales qui sont des mesures collectées sur un même individu au cours du temps. Ces modèles prennent en compte la variabilité au sein des mesures effectuées sur chaque individu (variabilité intra-individuelle) et entre différents individus (variabilité inter-individuelle), grâce à deux types d'effets : les effets fixes, communs à tous les individus de la population, et les effets aléatoires, variables d'un individu à l'autre. Ces derniers sont modélisés par des variables latentes non observées, qui portent la variabilité inter-individuelle de la population. Identifier les paramètres du modèle à la source de cette variabilité est une question importante, en particulier pour l'étude de la variabilité génotypique en amélioration des plantes. Cet objectif peut être formulé comme un test statistique de nullité des variances des effets aléatoires et la statistique du rapport de vraisemblances peut être considérée. Dans ce contexte, ce test présente cependant plusieurs défis. Théoriquement, la nullité des variances testées pose problème car ces variances se trouvent à la frontière de l'espace des paramètres. Les résultats classiques des méthodes basées sur le maximum de vraisemblance ne sont pas valides. Par ailleurs, la matrice d'information de Fisher est singulière dans ce cadre. De plus, si des variances non testées sont nulles, les tests asymptotiques ne sont plus applicables. Dans ce travail de thèse, une procédure de test du rapport de vraisemblances de nullité des composantes de la variance dans les modèles à effets mixtes est proposée, basée sur le Bootstrap paramétrique. La consistance de cette procédure de test sous l'hypothèse nulle est démontrée, pour un choix judicieux du paramètre utilisé pour simuler les échantillons Bootstrap. Une étape de seuillage de ce paramètre est proposée pour pallier les problèmes de frontière et de singularité de la matrice d'Information de Fisher. D'un point de vue computationnel, les modèles à effets mixtes étant des modèles à variables latentes, leur vraisemblance est la plupart du temps non explicite, ce qui rend difficile l'estimation de la statistique du rapport de vraisemblances. Estimer cette statistique revient à estimer un ratio de constantes de normalisation de densités de probabilité. Une nouvelle procédure d'estimation de ce ratio, basée sur une approximation stochastique, est proposée. Elle consiste à trouver le zéro d'une fonction définie par une espérance. Ce nouvel estimateur est consistant et asymptotiquement gaussien. Il présente de très bonnes performances théoriques et pratiques et peut s'intégrer dans une procédure d'estimation de paramètres dans un modèle à variables latentes. Pour finir, motivé par l'analyse de la variabilité génotypique pour l'amélioration des plantes, une étude de 48 génotypes d'Arabidopsis thaliana est présentée. Un modèle mécaniste complexe décrivant les échanges de carbone et d'azote entre la plante et son environnement est intégré à un modèle à effets mixtes afin d'identifier des paramètres biologiques portant une partie de la variabilité génotypique observée<br>Mixed-effects models allow for the analysis of data with a hierarchical structure, such as longitudinal data which are measurements collected on the same individual over time. These models take into account variability within measurements for each individual (intra-individual variability) and between different individuals (inter-individual variability) through two types of effects: fixed effects, which are common to all individuals in the population, and random effects, which vary from one individual to another. The latter are modeled by unobserved latent variables that account for the inter-individual variability in the population. Identifying the model parameters that are the source of this variability is an important issue, especially for studying genotypic variability in plant breeding. This objective can be formulated as a statistical test of the nullity of the random effects variances and the likelihood ratio statistic can be considered. In this context, however, the test presents several challenges. Theoretically, the nullity of the tested variances is problematic because these variances are on the boundary of the parameter space. Classical results of methods based on maximum likelihood are not valid anymore. Moreover, the Fisher information matrix is singular in this context. Additionally, if non-tested variances are null, asymptotic tests are no longer applicable. In this thesis work, a likelihood ratio test procedure for the nullity of variance components in mixed-effects models is proposed, based on parametric Bootstrap. The consistency of this test procedure under the null hypothesis are demonstrated, provided that a judicious choice is made for the parameter used for simulating the Bootstrap samples. A shrinkage step for this parameter is proposed to address boundary issues and the singularity of the Fisher Information matrix. From a computational perspective, since mixed-effects models are latent variable models, their likelihood is often not explicit, making the estimation of the likelihood ratio statistic challenging. Estimating this statistic amounts to estimating a ratio of normalization constants of probability densities. A new estimation procedure for this ratio, based on stochastic approximation, is proposed. It involves finding the zero of a function defined by an expectation. This new estimator is consistent and asymptotically Gaussian. It demonstrates very good theoretical and practical performances and can be integrated into a parameter estimation procedure in a latent variable model. Finally, motivated by the analysis of genotypic variability for plant breeding, a study of 48 genotypes of Arabidopsis thaliana is presented. A complex mechanistic model describing carbon and nitrogen exchanges between the plant and its environment is integrated into a mixed-effects model to identify which biological parameters are responsible for the observed genotypic variability
2
Hur, Chang Soo. "Variance bound test : a new approach." The Ohio State University, 1985. http://rave.ohiolink.edu/etdc/view?acc_num=osu1269522789.
Full text
3
Jatta, Abdullah. "Test of Causality in Conditional Variance Hafner and Herwatz Test for Causality." Thesis, Örebro universitet, Handelshögskolan vid Örebro Universitet, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-47701.
Full text
4
Shen, Paul. "Empirical Likelihood Tests For Constant Variance In The Two-Sample Problem." Bowling Green State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1544187568883762.
Full text
5
Herbert, William J. "Understanding variance of proficiency test performance in Cincinnati's neighborhood elementary schools." Cincinnati, Ohio : University of Cincinnati, 2006. http://www.ohiolink.edu/etd/view.cgi?acc%5Fnum=ucin1148329452.
Full text
6
HERBERT, WILLIAM J. "UNDERSTANDING VARIANCE OF PROFICIENCY TEST PERFORMANCE IN CINCINNATI'S NEIGHBORHOOD ELEMENTARY SCHOOLS." University of Cincinnati / OhioLINK, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1148329452.
Full text
7
Mnassri, Baligh. "Analyse de données multivariées et surveillance des processus industriels par analyse en composantes principales." Phd thesis, Aix-Marseille Université, 2012. http://tel.archives-ouvertes.fr/tel-00749282.
Full textAbstract:
Ce mémoire de thèse présente une étude fondamentale enrichie par des contributions qui sont articulées autour de la modélisation de processus ainsi qu'un diagnostic de défauts en utilisant l'analyse en composantes principales (ACP). <br /> Dans l'objectif d'un choix optimal du modèle ACP, une étude comparative de quelques critères connus dans la littérature nous a permis de conclure que le problème rencontré est souvent lié à une ignorance des variables indépendantes et quasi-indépendantes. Dans ce cadre, nous avons réalisé deux démonstrations mettant en évidence les limitations de deux critères en particulier la variance non reconstruite (VNR). En s'appuyant sur le principe d'une telle variance, nous avons proposé trois nouveaux critères. Parmi eux, deux ont été considérés comme étant empiriques car seule l'expérience permettra de prouver leur efficacité. Le troisième critère noté VNRVI représente un remède à la limitation du critère VNR. Une étude de sa consistance théorique a permis d'établir les conditions garantissant l'optimalité de son choix. Les résultats de simulation ont validé une telle théorie en prouvant ainsi que le critère VNRVI étant plus efficace que ceux étudiés dans cette thèse.<br /> Dans le cadre d'un diagnostic de défauts par ACP, l'approche de reconstruction des indices de détection ainsi que celle des contributions ont été utilisées. A travers une étude de généralisation, nous avons étendu le concept d'isolabilité de défauts par reconstruction à tout indice quadratique. Une telle généralisation nous a permis d'élaborer une analyse théorique d'isolabilité de défauts par reconstruction de la distance combinée versus celles des indices SPE et T2 de Hotelling en mettant en avant l'avantage de l'utilisation d'une telle distance. D'autre part, nous avons proposé une nouvelle méthode de contribution par décomposition partielle de l'indice SPE. Cette approche garantit un diagnostic correct de défauts simples ayant de grandes amplitudes. Nous avons également étendu une méthode de contribution classiquement connue par la RBC au cas multidimensionnel. Ainsi, la nouvelle forme garantit un diagnostic correct de défauts multiples de grandes amplitudes. En considérant la complexité de défauts, nous avons exploité la nouvelle approche de contribution RBC afin de proposer une nouvelle qui s'appelle RBCr. Cette dernière s'appuie sur un seuil de tolérance pour l'isolation de défauts. Une analyse de diagnosticabilité basée sur la RBCr montre que celle-ci garantit l'identification des défauts détectables. Ces derniers sont garantis isolables si leurs amplitudes satisfont les mêmes conditions d'isolabilité établies pour l'approche de reconstruction des indices.
8
Xiao, Yan. "Evaluating Variance of the Model Credibility Index." Digital Archive @ GSU, 2007. http://digitalarchive.gsu.edu/math_theses/39.
Full textAbstract:
Model credibility index is defined to be a sample size under which the power of rejection equals 0.5. It applies goodness-of-fit testing thinking and uses a one-number summary statistic as an assessment tool in a false model world. The estimation of the model credibility index involves a bootstrap resampling technique. To assess the consistency of the estimator of model credibility index, we instead study the variance of the power achieved at a fixed sample size. An improved subsampling method is proposed to obtain an unbiased estimator of the variance of power. We present two examples to interpret the mechanics of building model credibility index and estimate its error in model selection. One example is two-way independent model by Pearson Chi-square test, and another example is multi-dimensional logistic regression model using likelihood ratio test.
9
Ma, Tingting. "Isotropy test and variance estimation for high order statistics of spatial point process." HKBU Institutional Repository, 2011. https://repository.hkbu.edu.hk/etd_ra/1297.
Full text
10
Amiri, Saeid. "On variance estimation and a goodness-of-fit test using the bootstrap method /." Uppsala : Dept. of Energy and Technology, Swedish University of Agricultural Sciences, 2009. http://epsilon.slu.se/11451466.pdf.
Full text
11
Samarakoon, Nishantha Anura. "Conditional variance function checking in heteroscedastic regression models." Diss., Kansas State University, 2011. http://hdl.handle.net/2097/10744.
Full textAbstract:
Doctor of Philosophy<br>Department of Statistics<br>Weixing Song<br>The regression model has been given a considerable amount of attention and played a
significant role in data analysis. The usual assumption in regression analysis is that the
variances of the error terms are constant across the data. Occasionally, this assumption of
homoscedasticity on the variance is violated; and the data generated from real world applications
exhibit heteroscedasticity. The practical importance of detecting heteroscedasticity
in regression analysis is widely recognized in many applications because efficient inference
for the regression function requires unequal variance to be taken into account. The goal of
this thesis is to propose new testing procedures to assess the adequacy of fitting parametric
variance function in heteroscedastic regression models.
The proposed tests are established in Chapter 2 using certain minimized L[subscript]2 distance
between a nonparametric and a parametric variance function estimators. The asymptotic
distribution of the test statistics corresponding to the minimum distance estimator under
the fixed model and that of the corresponding minimum distance estimators are shown to
be normal. These estimators turn out to be [sqrt]n consistent. The asymptotic power of the
proposed test against some local nonparametric alternatives is also investigated. Numerical
simulation studies are employed to evaluate the nite sample performance of the test in one
dimensional and two dimensional cases.
The minimum distance method in Chapter 2 requires the calculation of the integrals
in the test statistics. These integrals usually do not have a tractable form. Therefore,
some numerical integration methods are needed to approximate the integrations. Chapter
3 discusses a nonparametric empirical smoothing lack-of-fit test for the functional form
of the variance in regression models that do not involve evaluation of integrals. empirical
smoothing lack-of-fit test can be treated as a nontrivial modification of Zheng (1996)'s
nonparametric smoothing test and Koul and Ni (2004)'s minimum distance test for the
mean function in the classic regression models. The asymptotic normality of the proposed
test under the null hypothesis is established. Consistency at some fixed alternatives and
asymptotic power under some local alternatives are also discussed. Simulation studies are
conducted to assess the nite sample performance of the test. The simulation studies show
that the proposed empirical smoothing test is more powerful and computationally more
efficient than the minimum distance test and Wang and Zhou (2006)'s test.
12
Lee, Mou Chin. "An empirical test of variance gamma options pricing model on Hang Seng index options." HKBU Institutional Repository, 2000. http://repository.hkbu.edu.hk/etd_ra/263.
Full text
13
Patrick, Joshua Daniel. "Simulations to analyze Type I error and power in the ANOVA F test and nonparametric alternatives." [Pensacola, Fla.] : University of West Florida, 2009. http://purl.fcla.edu/fcla/etd/WFE0000158.
Full text
14
Liu, Hangcheng. "Comparing Welch's ANOVA, a Kruskal-Wallis test and traditional ANOVA in case of Heterogeneity of Variance." VCU Scholars Compass, 2015. http://scholarscompass.vcu.edu/etd/3985.
Full textAbstract:
Analysis of variance (ANOVA) is a robust test against the normality assumption, but it may be inappropriate when the assumption of homogeneity of variance has been violated. Welch ANOVA and the Kruskal-Wallis test (a non-parametric method) can be applicable for this case. In this study we compare the three methods in empirical type I error rate and power, when heterogeneity of variance occurs and find out which method is the most suitable with which cases including balanced/unbalanced, small/large sample size, and/or with normal/non-normal distributions.
15
Paranagama, Dilan C. "Correlation and variance stabilization in the two group comparison case in high dimensional data under dependencies." Diss., Kansas State University, 2011. http://hdl.handle.net/2097/13132.
Full textAbstract:
Doctor of Philosophy<br>Department of Statistics<br>Gary L. Gadbury<br>Multiple testing research has undergone renewed focus in recent years as advances in high throughput technologies have produced data on unprecedented scales. Much of the focus has been on false discovery rates (FDR) and related quantities that are estimated (or controlled for) in large scale multiple testing situations. Recent papers by Efron have directly addressed this issue and incorporated measures to account for high-dimensional correlation structure when estimating false discovery rates and when estimating a density. Other authors also have proposed methods to control or estimate FDR under dependencies with certain assumptions. However, not much focus is given to the stability of the results obtained under dependencies in the literature. This work begins by demonstrating the effect of dependence structure on the variance of the number of discoveries and the false discovery proportion (FDP). A variance of the number of discoveries is shown and the density of a test statistic, conditioned on the status (reject or failure to reject) of a different correlated test, is derived. A closed form solution to the correlation between test statistics is also derived. This correlation is a combination of correlations and variances of the data within groups being compared. It is shown that these correlations among the test statistics affect the conditional density and alters the threshold for significance of a correlated test, causing instability in the results. The concept of performing tests within networks, Conditional Network Testing (CNT) is introduced. This method is based on the conditional density mentioned above and uses the correlation between test statistics to construct networks. A method to simulate realistic data with preserved dependence structures is also presented. CNT is evaluated using simple simulations and the proposed simulation method. In addition, existing methods that controls false discovery rates are used on t-tests and CNT for comparing performance. It was shown that the false discovery proportion and type I error proportions are smaller when using CNT versus using t-tests and, in general, results are more stable when applied to CNT. Finally, applications and steps to further improve CNT are discussed.
16
Su, Xun, and Mei Ting Cheung. "Day-of-the-week eects in stock market data." Thesis, KTH, Matematisk statistik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-103863.
Full textAbstract:
The purpose of this thesis is to investigate day-of-the-week effects for stock index returns. The investigations include analysis of means and variances as well as return-distribution properties such as skewness and tail behavior. Moreover, the existences of conditional day-of-the-week effects, depending on the outcome of returns from the previous week, are analyzed. Particular emphasis is put on determining useful testing procedures for differences in variance in return data from different weekdays. Two time series models, AR and GARCH(1,1), are used to find out if any weekday's mean return is different from other days. The investigations are repeated for two-day re- turns and for returns of diversified portfolios made up of several stock index returns.
17
Korsell, Nicklas. "Statistical Properties of Preliminary Test Estimators." Doctoral thesis, Uppsala : Acta Universitatis Upsaliensis, 2006. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-7155.
Full text
18
Le, Bail Karine. "Etude statistique de la stabilité des stations de géodésie spatiale. Application à DORIS." Phd thesis, Observatoire de Paris, 2004. http://tel.archives-ouvertes.fr/tel-00011406.
Full textAbstract:
DORIS (Détermination d'Orbite et Radio positionnement Intégré sur Satellite) est un des systèmes permanents d'observation de la Terre avec le Global Positioning System (GPS) et la télémétrie laser sur satellite (SLR). La richesse des mesures collectées par ces systèmes permet de représenter le déplacement des stations au sol sous forme de séries temporelles de coordonnées. Au delà de la modélisation déterministe habituelle des phénomènes géophysiques, un nouveau domaine de recherche en géodésie s'est ouvert il y a quelques années, visant à la validation et à l'interprétation de ces séries temporelles.Dans la première partie du mémoire on décrit l'intégration de la fonction de mesure DORIS dans le logiciel de traitement GPS de l'Université de Berne.La partie principale des recherches effectuées concerne l'étude et la mise en oeuvre d'une méthode d'analyse de séries géodésiques 3D allant au delà des approches classiques que sont la répétitivité ou la recherche de périodicités et de ruptures. La méthode fait appel à des outils empruntés à d'autres disciplines : l'Analyse en Composantes Principales aux statistiques des sondages, et la variance d'Allan à la métrologie du temps et des fréquences. Elle est testée sur un certain nombre de jeux de séries temporelles de coordonnées de stations DORIS et GPS. On obtient une batterie de diagnostics qualifiant le spectre des mouvements de station et celui des erreurs de mesure. Ces diagnostics permettent la description déterministe et statistique du mouvement des stations obtenu par les analyses de géodésie spatiale. Ils conduisent aussi à une différenciation des systèmes de positionnement DORIS et GPS par leur signature spectrale.
19
Gassem, Anis. "Test d'ajustement d'un processus de diffusion ergotique à changement de régime." Le Mans, 2010. http://cyberdoc.univ-lemans.fr/theses/2010/2010LEMA1016.pdf.
Full textAbstract:
Nous considérons les tests d'ajustement de type Cramér-von Mises pour tester l'hypothèse que le processus de diffusion observé est un switching diffusion, c'est-à-dire un processus de diffusion à changement de régime dont la dérive est de type signe. Ces tests sont basés sur la fonction de répartition empirique et la densité empirique. Il est montré que les distributions limites des tests statistiques proposés sont définis par des fonctionnelles de type intégrale des processus Gaussiens continus. Nous établissons les développements de Karhunen-Loève des processus limites correspondants. Ces développements nous permettent de simplifier le problème du calcul des seuils. Nous étudions le comportement de ces statistiques sous les alternatives et nous montrons que ces tests sont consistants. Pour traiter les hypothèses de base composite nous avons besoin de connaître le comportement asymptotique des estimateurs statistiques des paramètres inconnus, c'est pourquoi nous considérons le problème de l'estimation des paramètres pour le processus de diffusion à changement de régime. Nous supposons que le paramètre inconnu est à deux dimensions et nous décrivons les propriétés asymptotiques de l'estimateur de maximum de vraisemblance et de l'estimateur bayésien dans ce cas. L'utilisation de ces estimateurs nous ramène à construire les tests de type Cramér-von Mises correspondants et à étudier leurs distributions limites. Enfin, nous considérons deux tests de type Cramér-von Mises de processus de diffusion ergodiques dans le cas général. Il est montré que pour le choix de certaines des fonctions de poids ces tests sont asymptotiquement distribution-free. Pour certains cas particuliers, nous établissons les expressions explicites des distributions limites de ces statistiques par le calcul direct de la transformée de Laplace<br>We consider the Cramér-von Mises goodness-of-fit type tests to test the hypothesis that the observed diffusion process is switching diffusion, i. E. , this process has sign-type trend coefficient. These tests are based on empirical distribution and empirical density functions. It is shown that the limit distributions of the proposed test statistics are defined by the integral type functionals of continuous Gaussian processes. We provide the Karhunen-Loéve expansion of the corresponding limiting processes. This expansion allows us to simplify the problem of the calculation of the thresholds. We study the behavior of these statistics under alternatives and we show that these tests are consistent. To treat the composite basic hypotheses we need to know the asymptotic behavior of statistical estimators of the unknown parameters. That is why we consider the problem of parameter estimation for switching diffusion process. We suppose that the unknown parameter is two-dimensional and we describe the asymptotic properties of the maximum likelihood and Bayesian estimators in this case. Using these estimators we construct the corresponding Cramér-von Mises type tests and study their limit distributions. Finally we consider two Cramér-von Mises type tests for ergodic diffusion process in the general case. It is shown that for a certain choice of weight functions these tests are asymptotically distribution-free. For some particular cases, we provide the explicit expressions of the limit distributions of these statistics via direct calculation of Laplace transforms
20
Jung, Yoonsung. "Tests for unequal treatment variances in crossover designs." Diss., Manhattan, Kan. : Kansas State University, 2009. http://hdl.handle.net/2097/1581.
Full text
21
Ruiz-Gazen, Anne. "Estimation robuste d'une matrice de dispersion et projections révélatrices." Toulouse 3, 1993. http://www.theses.fr/1993TOU30008.
Full textAbstract:
L'auteur s'interesse au probleme des valeurs aberrantes dans un echantillon multidimensionnel et developpe des solutions dans deux parties complementaires correspondant a deux approches differentes de la question. La premiere partie consiste en l'etude d'un estimateur de dispersion robuste. L'objectif est d'accommoder les eventuelles valeurs aberrantes, c'est-a-dire de rendre les techniques statistiques, associees a l'estimation d'une matrice de dispersion, insensibles a la presence de valeurs aberrantes. Dans la deuxieme partie, une methode de projections revelatrices, basee sur la comparaison d'un estimateur de dispersion non-robuste avec un estimateur robuste, est proposee et ses proprietes sont developpees dans le cadre de modeles probabilistes de contamination. Cette methode d'analyse exploratoire de donnees permet, a partir d'une representation graphique, non seulement d'identifier les eventuelles valeurs aberrantes, mais aussi de les cartographier. Les techniques sont illustrees par plusieurs exemples reels ou simules
22
Söderberg, Gustav, and Rikard Nyström. "Insider Trading - An Efficiency Contributor?" Thesis, Umeå universitet, Företagsekonomi, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-73596.
Full textAbstract:
This research has studied the relationship between insider trading activity and its effect on the level of informational efficiency. The authors have used insider data from Finansinspektionen and data regarding stock prices, market capitalization and GDP from Thomson Reuters Datastream. The sample includes 193 companies on the Swedish stock exchange for a period of 10 years. A Variance Ratio test employed on moving sub-sample windows was used to establish the level of time-varying informational efficiency, which subsequently was used in an OLS-regression as a dependent variable. The result of the regression implies a negative effect on firm price information efficiency by insider purchasing, while selling has a positive effect. This can be concluded using a confidence level of 99%. The results are interesting since they imply an asymmetrical effect of insider trading on informational efficiency, while current insider legislation treats buying and selling by insiders equal. Thus, the results are of interest in future adjustments of laws regulating insider trading.
23
d'Estampes, Ludovic. "Traitement statistique des processus alpha-stables: mesures de dépendance et identification des ar stables. Test séquentiels tronqués." Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2003. http://tel.archives-ouvertes.fr/tel-00005216.
Full textAbstract:
Dans ce travail, nous étudions de manière approfondie les lois $\al$-stables (lois à variance infinie). Dans le premier chapitre, nous rappelons les différentes propriétés des lois $\al$-stables univariées (stabilité, calcul des moments, simulation). Nous introduisons ensuite les lois symétriques $\al$-stables (\SaS) multivariées. Après avoir parlé de la mesure spectrale et de son intérêt pour caractériser l'indépendance, nous nous concentrons sur les mesures de dépendance. Constatant que le coefficient de covariation, largement utilisé actuellement, admet certaines limites, nous construisons dans le deuxième chapitre une nouvelle mesure de dépendance, appelée coefficient de covariation symétrique. Ce dernier nous permet, entre autres, de découvrir quelques spécificités des vecteurs \SaS. En effet, contrairement aux vecteurs gaussiens, on peut obtenir pour certains vecteurs \SaS\ à la fois une dépendance positive et une dépendance négative. Après avoir conclu le chapitre par l'étude de la loi asymptotique de l'estimateur du coefficient de covariation, nous abordons, dans le troisième chapitre, les processus autorégressifs à innovations stables. Nous présentons les différentes méthodes d'identification de l'ordre d'un processus AR: autocorrélation partielle (Brockwell et Davis) et statistiques quadratiques asymptotiquement invariantes basées sur les rangs (Garel et Hallin). De nombreuses simulations, effectuées en Matlab et Fortran, nous permettent de comparer ces méthodes et de constater l'importance du rôle joué par les statistiques de rang dans ce domaine. Pour finir, un problème de test séquentiel, développé dans le cadre d'un contrat industriel, nous permet d'introduire la notion de niveau de confiance après décision.
24
Rumelhard, Mélina. "Réponses de l'epithélium respiratoire à l'exposition aux particules atmosphériques fines PM 2,5 : rôle respectif des composantes organiques, métalliques et biologiques." Paris 7, 2007. http://www.theses.fr/2007PA077165.
Full textAbstract:
Les particules atmosphériques (PM) seraient associées à des effets néfastes sur la santé tels qu'une inflammation des voies aériennes ou un remodelage et une carcinogénèse pulmonaires à long terme. Les PM2> (diamètre ≤2,5μm) sont un mélange complexe dont la composition dépend de leur source d'émission et des conditions climatiques. Des cellules épithéliales respiratoires exposées à des PM2,5 sécrètent des cytokines pro-inflammatoires et de Pamphiréguline, un ligand du récepteur à l'EGF (EGFR) impliqué dans la réparatior cellulaire. Le but de cette étude a été 1) de déterminer l'expression génique et protéique de 4 ligands de l'EGFR par des cellules épithéliales respiratoires exposées à des PM2,5 urbaines et de préciser la contribution des composants des PM2,5 et 2) d'étudier les effets autocrines et paracrines des sécrétions épithéliales induites par les PM2,5 sur les cellules épithéliales et conjonctives bronchiques. Les PM2,5 induisent l'expression de Pamphiréguline, de l'HB-EGF et du TGFα avec une participation majeure des composés organiques. La technique des milieux conditionnés a montré que les sécrétions épithéliales induites par les PM2,5 augmentent la sécrétion du biomarqueur pro-inflammatoire GM-CSF via une régulation autocrine par des ligands de l'EGFR alors qu'il n'y a pas de régulation de l'effet mitogène des PM2,5 sur les cellules épithéliales bronchiques ou les fïbroblastes pulmonaires. Ces données révèlent l'implication des ligands de l'EGFR dans la réponse pro-inflammatoire induite par les PM2,5 et potentiellement dans le remodelage bronchique exacerbé dans les voies aériennes des patients atteints de maladies respiratoires chroniques<br>Exposure to ambient particulate matter (PM) is known to be responsible for adverse health effects such as airway inflammation and probably bronchial remodeling and pulmonary carcinogenicity for longer exposures. Urban PM2,5 (PM with an aerodynamic diameter ≤2,5 μm) is a complex mixture which composition relies on the emission source and atmospheric conditions encountered by particles. Exposure of respiratory epithelial cells to PM2,5 induces the release of pro-inflammatory cytokines and chemokines, and amphiregulin, a ligand of the epidermal growth factor receptor (EGFR) involved in cellular repair and chronic respiratory diseases. The aim of this study was 1) to determine the expression of 4 EGFR ligands mRNA and proteins by respiratory epithelial cells exposed to urban PM2,5 and to precise the contribution of PM components and 2) to investigate the autocrine and paracrine effects of PM2,5-induced epithelial cell secretions on bronchial epithelial and connective tissue cells. PM2 5 induces the mRNA expression and/or secretion of amphiregulin, HB-EGF and TGFα with a major contribution of organic components. Using the experimental strategy of conditioned media, we established that PM2,5-induced epithelial cell secretions increase the release of the pro- inflammatory biomarker GM-CSF with an autocrine regulation by EGFR ligands, while there isn't any autocrine or paracrine régulation of the PM2,5-mitogen effect on bronchial epithelial cells or pulmonary fibroblasts. These results highlight the involvement of EGFR ligands in PM2,5-induced pro-inflammatory response and potentially in bronchial remodeling exacerbated in chronic respiratory patients airways
25
Liu, Xi. "Bayesian Designing and Analysis of Simple Step-Stress Accelerated Life Test with Weibull Lifetime Distribution." Ohio University / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1283365980.
Full text
26
Sabatier, Robert. "Méthodes factorielles en analyse des données : approximation et prise en compte de variables concomitantes." Montpellier 2, 1987. http://www.theses.fr/1987MON20256.
Full textAbstract:
On demontre un theoreme d'approximation general pour une application lineaire dans les espaces vectoriels euclidiens de dimension finie. Applique a l'analyse factorielle, on en deduit de nouvelles methodes permettant la prise en compte d'une structure sur les unites statistiques. Les structures envisagees sont de type factoriel, temporel ou de graphe
27
Drut, Bastien. "Investissement socialement responsable et sélection de portefeuille." Thesis, Paris 10, 2011. http://www.theses.fr/2011PA100131/document.
Full textAbstract:
Cette thèse s’attèle à déterminer les conséquences théoriques et empiriques de la considération d’indicateurs socialement responsables dans la sélection de portefeuille traditionnelle. Le premier chapitre étudie la significativité de la perte d’efficience moyenne-variance d’un portefeuille d’obligations souveraines lorsque l’on introduit une contrainte sur la notation socialement responsable moyenne des Etats. En utilisant un échantillon d’obligations d’Etats développés sur la période 1995-2008, nous montrons qu’il est possible d’augmenter sensiblement la notation socialement responsable moyenne sans perdre significativement en termes de diversification. Le second chapitre propose une analyse théorique de l’effet sur la frontière efficiente d’une contrainte sur la notation socialement responsable du portefeuille. Nous mettons en évidence les différents cas de figure pouvant se produire en fonction de la corrélation entre les rendements attendus et les notations socialement responsables et de l’aversion au risque de l’investisseur. Enfin, puisque la question de l’efficience des portefeuilles investis en fonction de critères socialement responsables fait débat dans la littérature financière, un dernier chapitre propose un nouveau test d’efficience moyenne-variance dans le cas réaliste où aucun actif sans risque n’est disponible<br>This thesis aims at determining the theoretical and empirical consequences of the consideration of socially responsible indicators in the traditional portfolio selection. The first chapter studies the significance of the mean-variance efficiency loss of a sovereign bond portfolio when introducing a constraint on the average socially responsible ratings of the governments. By using a sample of developed sovereign bonds on the period 1995-2008, we show that it is possible to increase sensibly the average socially responsible rating without significantly losing in terms of diversification. The second chapter proposes a theoretical analysis of the impact on the efficient frontier of a constraint on the socially responsible ratings of the portfolio. We highlight that different cases may arise depending on the correlation between the expected returns and the socially responsible ratings and on the investor’s risk aversion. Lastly, as the issue of the efficiency of socially responsible portfolios is a central point in the financial literature, the last chapter proposes a new mean-variance efficiency test in the realistic case where there is no available risk-free asset
28
Zou, Shanshan. "Empirical analysis on random walk behavior of foreign exchange rates." Thesis, Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/33836.
Full textAbstract:
This thesis conducts a comprehensive examination on the random walk behavior of 29 foreign exchange rates over the period of floating exchange regime, using variance-ratio tests. The cross-country and time-series test show that random walk model cannot be rejected on majority, and the random walk behavior is quite volatile across the whole floating exchange regime period. It then goes further to explore possible factors that can explain the probability of rejection/ non-rejections on random walk model using linear as well as nonlinear probability models, and find that the factors such as capital openness and investment-to-trade ratio significantly increases the chance of its exchange rate exhibiting random walk behavior.
29
Fleischhauer, Monika, Sören Enge, Robert Miller, Alexander Strobel, and Anja Strobel. "Neuroticism explains unwanted variance in Implicit Association Tests of personality: possible evidence for an affective valence confound." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2013. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-127607.
Full textAbstract:
Meta-analytic data highlight the value of the Implicit Association Test (IAT) as an indirect measure of personality. Based on evidence suggesting that confounding factors such as cognitive abilities contribute to the IAT effect, this study provides a first investigation of whether basic personality traits explain unwanted variance in the IAT. In a gender-balanced sample of 204 volunteers, the Big-Five dimensions were assessed via self-report, peer-report, and IAT. By means of structural equation modeling (SEM), latent Big-Five personality factors (based on self- and peer-report) were estimated and their predictive value for unwanted variance in the IAT was examined. In a first analysis, unwanted variance was defined in the sense of method-specific variance which may result from differences in task demands between the two IAT block conditions and which can be mirrored by the absolute size of the IAT effects. In a second analysis, unwanted variance was examined in a broader sense defined as those systematic variance components in the raw IAT scores that are not explained by the latent implicit personality factors. In contrast to the absolute IAT scores, this also considers biases associated with the direction of IAT effects (i.e., whether they are positive or negative in sign), biases that might result, for example, from the IAT's stimulus or category features. None of the explicit Big-Five factors was predictive for method-specific variance in the IATs (first analysis). However, when considering unwanted variance that goes beyond pure method-specific variance (second analysis), a substantial effect of neuroticism occurred that may have been driven by the affective valence of IAT attribute categories and the facilitated processing of negative stimuli, typically associated with neuroticism. The findings thus point to the necessity of using attribute category labels and stimuli of similar affective valence in personality IATs to avoid confounding due to recoding.
30
Messer, Michael [Verfasser], Gaby [Akademischer Betreuer] Schneider, Anton [Akademischer Betreuer] Wakolbinger, and Roland [Akademischer Betreuer] Fried. "A multiple filter test for the detection of rate changes in renewal processes with varying variance / Michael Messer. Gutachter: Gaby Schneider ; Anton Wakolbinger ; Roland Fried." Frankfurt am Main : Univ.-Bibliothek Frankfurt am Main, 2014. http://d-nb.info/1053468296/34.
Full text
31
Bourredjem, Abderrahmane. "Contribution à l'inférence sur le coefficient de corrélation intraclasse de concordance dans les études de fiabilité inter-juges." Electronic Thesis or Diss., Bourgogne Franche-Comté, 2023. http://www.theses.fr/2023UBFCK078.
Full textAbstract:
La fiabilité d'une mesure fait référence à sa reproductibilité lorsqu'elle est répétée de manière aléatoire sur le même sujet et constitue une propriété métrologique clé pour toutes les mesures. Le coefficient de corrélation intra-classe de concordance à deux voies (ICCa) est un paramètre statistique utilisé pour quantifier la fiabilité inter-observateurs des mesures continues (ou qualitatives ordinales). Il constitue un indice de fiabilité central recommandé par les agences réglementaires. Néanmoins, ses estimateurs sont biaisés et de nombreuses solutions ont été essayées pour améliorer son intervalle de confiance (IC). Les travaux les plus récents indiquent qu'aucune méthode ne fonctionne bien en cas de non-normalité des données, difficilement détectable à partir des observations, et lorsque le nombre de sujets ou d'évaluateurs est limité, ce qui est plutôt le cas en pratique. De plus, aucune transformation de stabilisation de la variance (VST) ni aucun test de comparaison statistique ne sont disponibles pour l'ICCa. L'objectif de cette thèse est donc de contribuer au développement de méthodes palliant le manque d'outils inférentiels pour l'ICCa. Dans un premier temps, nous proposons de nouvelles méthodes asymptotiques pour l'intervalle de confiance de l'ICCa, le calcul de la taille de l'échantillon des sujets et des évaluateurs, et un test de rapport de vraisemblance pour comparer deux ICCa. Ensuite, dans un deuxième travail, nous développons trois VST, améliorant les propriétés de l'intervalle de confiance pour les études de fiabilité inter-évaluateurs de taille modérée, et la synthèse de plusieurs ICCa dans le contexte de méta-analyses. Enfin, dans un troisième travail, des méthodes de rééchantillonnage spécifiques sont proposées, en combinaison avec la meilleure VST, pour améliorer les performances de l'intervalle de confiance de l'ICCa sans l'hypothèse de normalité et avec de petits échantillons. Il s'agit d'un travail de méthodologie biostatistique, avec des évaluations par simulation des méthodes introduites, et des applications à plusieurs jeux de données réelles issues d'études de fiabilité inter-évaluateurs et de méta-analyses<br>Measurement's reliability refers to its reproducibility when it is randomly repeated on the same subject and is a key metrological property for each measurement validation. The two-way intra-class correlation coefficient of agreement (ICCa) is a statistical parameter used to quantify the inter-rater reliability of continuous (or ordinal qualitative) measurements. It constitute a central reliability index recommended by the regulatory agencies. Nevertheless, its estimators are biased and a lot of solutions have been tried facing to its confidence interval (CI) problem. The latest works indicate that no method works well with a hard-to-detect violation of normality and when the number of subjects OR raters is limited, which is rather the case in practice. Furthermore, no variance stabilizing transformation (VST) nor statistical comparative test are available for the ICCa. The aim of this thesis is therefore to contribute to the development of methods that remedy the lack of the inferential tools for the ICCa. At a first step, we propose new asymptotic methods for the ICCa confidence interval, the calculation of the needed sample size of subjects and raters, and a likelihood ratio test to compare two ICCa. Then, in a second work, we develop three VSTs, improving the properties of the confidence interval for inter-rater reliability studies of moderate sample size, and the synthesis of several ICCa in the context of meta-analyses. Finally, in a third work, dedicated resampling methods are proposed, in combination with the best VST, to improve the ICCa confidence interval performances in case of non-normality with small sample size. It is above all a work of biostatistical methodology, with simulation evaluations of the introduced methods, and applications to several real data sets from inter-rater reliability studies and meta-analyses
32
Larsson, Stefan. "Mixing Processes for Ground Improvement by Deep Mixing." Doctoral thesis, KTH, Civil and Architectural Engineering, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-3667.
Full textAbstract:
<p>The thesis is dealing with mixing processes havingapplication to ground improvement by deep mixing. The mainobjectives of the thesis is to make a contribution to knowledgeof the basic mechanisms in mixing binding agents into soil andimprove the knowledge concerning factors that influence theuniformity of stabilised soil.</p><p>A great part of the work consists of a literature surveywith particular emphasis on literature on the processindustries. This review forms a basis for a profounddescription and discussion of the mixing process and factorsaffecting the process in connection with deep mixingmethods.</p><p>The thesis presents a method for a simple field test for thestudy of influential factors in the mixing process. A number offactors in the installation process of lime-cement columns havebeen studied in two field tests using statistical multifactorexperiment design. The effects of retrieval rate, number ofmixing blades, rotation speed, air pressure in the storagetank, and diameter of the binder outlet on the stabilisationeffect and the coefficient of variation determined byhand-operated penetrometer tests for excavated lime-cementcolumns, were studied.</p><p>The literature review, the description of the mixingprocess, and the results from the field tests provide a morebalanced picture of the mixing process and are expected to beuseful in connection to ground improvement projects and thedevelopment of mixing equipments.</p><p>The concept of sufficient mixture quality, i.e. theinteraction between the mixing process and the mechanicalsystem, is discussed in the last section. By means ofgeostatistical methods, the analysis considers thevolume-variability relationship with reference to strengthproperties. According to the analysis, the design values forstrength properties depends on the mechanical system, the scaleof scrutiny, the spatial correlation structure, and the conceptof safety, i.e. the concept of sufficient mixture quality isproblem specific.</p><p><b>Key words:</b>Deep Mixing, Lime cement columns, Mixingmechanisms, Mixture quality, Field test, ANOVA, Variancereduction.</p>
33
Yeung, Kwong. "Perception of teacher emotional support and parental education level : the impacts on students’ math performance." Thesis, University of Leicester, 2010. http://hdl.handle.net/2381/8607.
Full textAbstract:
There is a paucity of research juxtaposing parental education level and teacher emotional support in a single study which examines their relative impacts on students’ academic achievements. Therefore, the first objective of this dissertation is to study the influence of parental education level, in comparison to the influence of teacher emotional support, on students’ math performance, by using more representative data and a rigorous statistical method. The second objective is to identify and examine how some important psychological traits (both affective and cognitive) mediate the effects of social factors on students’ math performance. The third objective is to examine whether those relationships are moderated by gender. Hong Kong’s survey data is extracted from the Program of International Students Assessment (2003) as organized by Organization for Economic Co-operation and Development (OECD), on the math performances of 4,478 students at the age of fifteen. Measurement invariance was first tested, and then followed by Confirmatory Factor Analysis. Two structural models were tested by Structural Equation Modeling using Linear Structural Relations (LISREL) 8.5 which is computer software for SEM. Results indicated that first, parental education level affects children’s math scores by providing home education resources and enhancing children’s math self-efficacy, and second the Self Determination Theory is applicable in supporting the hypothesis that teachers affects their students’ math scores by providing a cooperative learning environment, which in turn, enhances students’ affective and cognitive factors. Three important mediators, namely cooperative learning environment, math self-efficacy, and home education resources are concluded as significant mediating factors upon the effects of parents and teachers on students’ math performance. The perceived support from parents and teachers are not significantly different across gender in Hong Kong. This is consistent with recent studies that differences favoring males in mathematics achievement are disappearing. Theoretical contributions and practical implications are discussed in the final part of the dissertation.
34
Herrero, Marie. "Influence des fermentations alcoolique et malolactique sur la composition volatile des cidres à distiller en cours d’élaboration." Caen, 2011. http://www.theses.fr/2011CAEN2028.
Full textAbstract:
Ce travail consistait à caractériser et suivre les changements de la composition chimique des cidres à distiller durant leur élaboration. Pour répondre à cet objectif, pendant deux campagnes de production (2007/2008 et 2008/2009), une centaine d’échantillons de cidre a été prélevée sur 4 cuves différentes se déclinant sous deux AOC et trois savoirs faire (industriel, artisanal et fermier). Les teneurs en sucres ont été déterminées par dosage enzymatique, les acides malique et lactique ont été dosés par CLHP/UV et les composés volatils ont été suivis par CPG/SM après SPE et concentration. De manière générale, les sucres sont consommés rapidement dans le cas de cuves industrielles contrairement aux cuves artisanale et fermière, au frais et de plus petit volume. Des fermentations malolactiques (FML) ont été repérées seulement pour les cuves industrielles et pour la cuve artisanale sur une année. Quand elle a lieu, la FML se déroule très rapidement (moins d’un mois) et de façon simultanée avec la fermentation alcoolique. L’apparition d’une FML se caractérise par l’apparition d’acétates (acétate de 2-phényléthyle et de 3-méthylbutyle) en début de procédé et une présence importante d’acide carboxyliques et de dérivés volatils des acides lactique et succinique plutôt en fin. In fine, des composés comme l’acétoïne, le butanol et l’hexanol sont présents de manière plus importante dans les cidres où une FML n’a pas lieu. En revanche, peu de différences ont été observées pour l’évolution régulière des alcools supérieurs. Un contrôle systématique des pommes et de la température des cuves permettrait d’obtenir une meilleure répétabilité du cidre à distiller<br>This manuscript handles with the characterisation and changes of chemical composition of cider to be distilled, from the fruit juice to the distillation step. For two years (2007/2008 and 2008/2009), about 100 sample of ciders were taken and issued from 4 tanks representing two different French labels and three different cider-making technologies (industrial, small-scale and farm production). Content of sugars was determined by enzymatic method, malic and lactic acids were quantified by HPLC/UV and volatile composition was fallowed by GC/MS after Solid-Phase Extraction and concentration. Sugars consumption was faster for the industrial productions than in farmer’s and home-made’s ones. Malolactic fermentation (MLF) seems to be characteristic of industrial productions and takes place quickly, less than one month is necessary to degrade the initial malic acid content. This transformation was found to be simultaneous to the alcoholic fermentation. The occurrence of MLF is characterized by an important apparition of acetates (2-phenylethyl and 3-methulbutyl acetates) in a first period and a more important concentrations of carboxylic acids and volatile derivatives of lactic and succinic acid in the final. In fine, compounds as acetoin, butanol and hexanol are more concentrated in ciders where a MLF did not occurred. Differences were not significant for higher alcohols; they are changing during the alcoholic fermentation even if their progression seems to be slower when lactic acid bacteria are very active. A control of the quality of apples and the temperature of casks could be enabling a better repeatability of the cider devoted to the distillation of Calvados
35
Tamminen, S. (Satu). "Modelling the rejection probability of a quality test consisting of multiple measurements." Doctoral thesis, Oulun yliopisto, 2014. http://urn.fi/urn:isbn:9789526205205.
Full textAbstract:
Abstract Quality control is an essential part of manufacturing, and the different properties of the products can be tested with standardized methods. If the decision of qualification is based on only one test specimen representing a batch of products, the testing procedure is quite straightforward. However, when the measured property has a high variability within the product, as usual, several test specimens are needed for the quality verification. When a quality property is predicted, the response value of the model that most effectively finds the critical observations should naturally be selected. In this thesis, it has been shown that LIB-transformation (Larger Is Better) is a suitable method for multiple test samples, because it effectively recognizes especially the situations where one of the measurements is very low. The main contribution of this thesis is to show how to model quality of phenomena that consist of several measurement samples for each observation. The process contains several steps, beginning from the selection of the model type. Prediction of the exceedance probability provides more information for the decision making than that of the mean. Especially with the selected application, where the quality property has no optimal value, but the interest is in adequately high value, this approach is more natural. With industrial applications, the assumption of constant variance should be analysed critically. In this thesis, it is shown that exceedance probability modelling can benefit from the use of an additional variance model together with a mean model in prediction. The distribution shape modelling improves the model further, when the response variable may not be Gaussian. As the proposed methods are fundamentally different, the model selection criteria have to be chosen with caution. Different methods for model selection were considered and commented, and EPS (Exceedance Probability Score) was chosen, because it is most suitable for probability predictors. This thesis demonstrates that especially a process with high diversity in its production and more challenging distribution shape gains from the deviation modelling, and the results can be improved further with the distribution shape modelling<br>Tiivistelmä Laadunvalvonnalla on keskeinen rooli teollisessa tuotannossa. Valmistettavan tuotteen erilaisia ominaisuuksia mitataan standardin mukaisilla testausmenetelmillä. Testi on yksinkertainen, jos tuotteen laatu varmistetaan vain yhdellä testikappaleella. Kun testattava ominaisuus voi saada hyvin vaihtelevia tuloksia samastakin tuotteesta, tarvitaan useita testikappaleita laadun varmistamiseen. Tuotteen laatuominaisuuksia ennustettaessa valitaan malliin vastemuuttuja, joka tehokkaimmin tunnistaa laadun kannalta kriittiset havainnot. Tässä väitöskirjassa osoitetaan, että LIB-transformaatio (Large Is Better) tunnistaa tehokkaasti erityisesti tilanteet, joissa yksi mittauksista on hyvin matala. Tämän väitöskirja vastaa kysymykseen, kuinka mallintaa laatua, kun tutkittavasta tuotteesta tarvitaan useita testinäytteitä. Mallinnusprosessi koostuu useista vaiheista alkaen mallityypin valinnasta. Alitusriskin mallinnuksen avulla saadaan enemmän informaatiota päätöksenteon tueksi perinteisen odotusarvomallinnuksen sijaan, etenkin jos laatutekijältä vaaditaan vain riittävän hyvää tasoa optimiarvon sijaan. Teollisissa sovelluksissa ei voida useinkaan olettaa, että vasteen hajonta olisi vakio läpi prosessin. Tässä väitöskirjassa osoitetaan että alitusriskin ennustamistarkkuus paranee, kun odotusarvon lisäksi mallinnetaan myös hajontaa. Jakaumamuodon mallilla voidaan parantaa ennustetarkkuutta silloin, kun vastemuuttuja ei noudata Gaussin jakaumaa. Koska ehdotetut mallit ovat perustaltaan erilaisia, täytyy myös mallin valintakriteeri valita huolella. Työssä osoitetaan, että EPS (Exceedance Probability Score) toimii parhaiten käytetyillä todennäköisyyttä ennustavilla malleilla. Tässä väitöskirjassa osoitetaan, että erityisesti silloin kun tuotantoprosessi on monimuotoinen ja laatumuuttujan jakaumamuoto on haastava, mallinnuttaminen hyötyy hajontamallin käytöstä, ja tuloksia voidaan parantaa jakaumamuodon mallilla
36
Laurent-Chabalier, Sabine. "Impact d'une mauvaise spécification de la variance sur la statistique du test F d'un modèle linéaire : étude de séries temporelles de richesse en sucre de la canne." Montpellier 2, 2007. http://www.theses.fr/2007MON20192.
Full textAbstract:
Ce travail vise à étudier l'impact d'une mauvaise spécification de la variance sur la statistique du test F, pour l'étude de séries temporelles de richesse en sucre de la canne sur l'île de la Réunion. Nous voulons construire un modèle de prédiction des courbes de l'évolution de la richesse de la canne à sucre. Nous considérons le modèle linéaire Y = X + e , où X est une matrice orthogonale supposée de plein rang et e est le vecteur d'erreur de loi normale d'espérance nulle et de matrice de variance-covariance inconnue. Nous proposons d'étudier la statistique du test F, dans le cas d'une mauvaise spécification de cette matrice de variance-covariance en considérant à tort qu'elle est égale à la matrice identité. Nous voulons approcher la loi de cette statistique de test pour un certain type de test d'hypothèse. Pour ceci, nous calculons les quatre premiers moments de la statistique du test F et étu-dions la densité de sa loi. Nous considérons trois formes de matrices : AR(1), ARMA(1,1) et équi-corrélée. Ceci permet de mesurer l'impact de la mauvaise spécification sur l'espérance, la variance et les coefficients d'asymétrie et d'aplatissement de la loi de cette statistique de test
37
Corker, Lloyd A. "A test for Non-Gaussian distributions on the Johannesburg stock exchange and its implications on forecasting models based on historical growth rates." University of Western Cape, 2002. http://hdl.handle.net/11394/7447.
Full textAbstract:
Masters of Commerce<br>If share price fluctuations follow a simple random walk then it implies that forecasting models based on historical growth rates have little ability to forecast acceptable share price movements over a certain period. The simple random walk description of share price dynamics is obtained when a large number of investors have equal probability to buy or sell based on their own opinion. This simple random walk description of the stock market is in essence the Efficient Market Hypothesis, EMT. EMT is the central concept around which financial modelling is based which includes the Black-Scholes model and other important theoretical underpinnings of capital market theory like mean-variance portfolio selection, arbitrage pricing theory (APT), security market line and capital asset pricing model (CAPM). These theories, which postulates that risk can be reduced to zero sets the foundation for option pricing and is a key component in financial
software packages used for pricing and forecasting in the financial industry. The model used by Black and Scholes and other models mentioned above are Gaussian, i.e. they exhibit a random nature. This Gaussian property and the existence of expected returns and continuous time paths (also Gaussian properties) allow the use of stochastic calculus to solve complex Black- Scholes models. However, if the markets are not Gaussian then the idea that risk can be. (educed to zero can lead to a misleading and potentially disastrous sense of security on the financial markets. This study project test the null hypothesis - share prices on the JSE follow a random walk - by means of graphical techniques such as symmetry plots and Quantile-Quantile plots to analyse the test distributions. In both graphical techniques evidence for the rejection of normality was found. Evidenceleading to the rejection of the hypothesis was also found through nonparametric or distribution free methods at a 1% level of significance for Anderson-Darling and Runs test.
38
GAMA, Alexandre José de Almeida. "Avaliação da caracterização física, química e mineralógica de depósitos de argilas esmectíticas do estado da Paraíba utilizando análise estatística de variância." Universidade Federal de Campina Grande, 2015. http://dspace.sti.ufcg.edu.br:8080/jspui/handle/riufcg/1146.
Full textAbstract:
Submitted by Maria Medeiros (maria.dilva1@ufcg.edu.br) on 2018-07-11T14:46:24Z
No. of bitstreams: 1
ALEXANDRE JOSÉ DE ALMEIDA GAMA - DISSERTAÇÃO (PPGCEMat) 2015.pdf: 1539873 bytes, checksum: 92e9d943e2b70ee7294f6924bed931a2 (MD5)<br>Made available in DSpace on 2018-07-11T14:46:24Z (GMT). No. of bitstreams: 1
ALEXANDRE JOSÉ DE ALMEIDA GAMA - DISSERTAÇÃO (PPGCEMat) 2015.pdf: 1539873 bytes, checksum: 92e9d943e2b70ee7294f6924bed931a2 (MD5)
Previous issue date: 2015-08-18<br>Atualmente mais de 80% das argilas bentoníticas beneficiadas no Brasil na forma sódica para uso em diversas aplicações industriais são provenientes dos depósitos do município de Boa Vista - PB. Estes jazimentos, que vem sendo lavrados há mais de 50 anos, encontram-se atualmente na fase de exaustão principalmente as argilas de variedades mais nobres, resultando em um sério prejuízo para qualidade do produto final. Recentemente, foram descobertos novos jazimentos situados nos municípios de Cubati, Pedra Lavrada, Sossego, Olivedos, na Paraíba, havendo necessidade de realizar estudo sistemáticos visando desenvolver toda sua potencialidade industrial. Assim sendo, este trabalho teve como objetivo o tratamento de dados obtidos por análise química e análise granulométrica. A caracterização física, química e mineralógica foi realizada através das seguintes técnicas: granulometria por difração a laser (GL), composição química por fluorescência de raios X (EDX) e difração de raios X (DRX). Em seguida foram realizadas análises de variância e teste de Tukey, usando software estatístico MINITAB® 17.0. Os resultados evidenciaram que a composição química das argilas bentoníticas dos novos depósitos apresentaram valores similares e diferentes em relação à do município de Boa Vista. Em analogia aos dados da literatura, as argilas estudadas apresentaram valores inferiores às importadas. Os resultados da análise de variância e teste de Tukey mostraram que os teores de óxido de sílica, de alumínio, de magnésio e de cálcio são significativamente diferentes ao nível de 95% de confiança. Os resultados mostraram que os locais de origem influenciaram na composição química das argilas.<br>The most part of industrialized bentonite clay produced in Brazil comes from Boa Vista - PB. However, the bentonite deposit is in the exhaustion phase because it has been mined over 50 years, which results in a low quality product. Recently, three new deposits have been discovered. These deposits are located in the following cities: Cubati, Pedra Lavrada, Sossego and Olivedos, in the state of Paraíba. Thus it needs a systematic study to develop all its industrial potential. Therefore, this study aims to evaluate the chemical and mineralogical composition, as well as particle size distribution and average diameter. From these deposits of smectite clays by statistical analysis. The physical, chemical and mineralogical characterization was performed using. Particle size by laser diffraction (GL), X-ray diffraction (XRD) and chemical composition by X-ray fluorescence (EDX) techniques. Then analyzes were carried out apruying statistics analysis of variance and Tukey test using the software racked camed MINITAB 17.0. The results showed that the chemical composition of bentonite clay of the new deposits which similar and different values in relation to the city of Boa Vista. When the data was analysed the results showed lower values compared with the imported clays. The results of the analysis of variance and Tukey test showed that the silica, aluminum, magnesium and calcium are significantly different at 95% level. Finally, the local has influence on the quality of the mineralogical clays.
39
Pfefferová, Alena. "Účinnost plánovaného experimentu." Master's thesis, Vysoké učení technické v Brně. Fakulta strojního inženýrství, 2008. http://www.nusl.cz/ntk/nusl-228265.
Full textAbstract:
Diplomová práce se zabývá plánováním a analýzou experimentu. Je zde zkoumán vliv počtu centrálních bodů v plánu experimentu na nalezení významných faktorů procesu. Pro určení tohoto vlivu je použita metoda Monte Carlo, pomocí které hledáme míru nalezení významných faktorů procesu. Simulace experimentu je vytvořena v programu MATLAB, kde se především využívá Statistics toolbox pro generování náhodných čísel. V závěru je zhodnoceno a graficky ukázáno, jak je určení významnosti faktoru procesu závislé na počtu uvažovaných faktorů experimentu a na počtu měření v centrálním bodě.
40
Vaz, Sónia Melania Oliveira. "How efficient is the Portuguese Stock Market?" Master's thesis, Instituto Superior de Economia e Gestão, 2012. http://hdl.handle.net/10400.5/10329.
Full textAbstract:
Mestrado em Finanças<br>Esta Dissertação testa a hipótese de eficiência fraca do mercado aplicada a seis índices de mercado Europeus (França, Alemanha, Reino Unido, Grécia, Portugal e Espanha) no período de Janeiro de 2007 a Janeiro de 2012. Para tal, testámos as correlações, realizámos o teste runs, o teste de raízes unitárias bem como teste de variâncias (variance ratio test). Adicionalmente analisámos se seria possível prever os retornos do PSI-20 recorrendo a data mining e, mais concretamente, aos algoritmos de data mining: k-NN e Redes Neuronais. Os nossos resultados evidenciam que no período de Janeiro de 2007 a Setembro de 2008 os índices de referência de França, Alemanha e Espanha, cumpriram a maioria dos critérios referentes à hipótese de eficiência fraca de mercado. Os nossos resultados evidenciam ainda que esta situação se verifica depois para os índices dos seis países considerados, no período de Setembro de 2008 a Janeiro de 2012. Relativamente à previsão dos retornos do PSI-20, desenhámos uma estratégia baseada nas previsões dadas pelo k-NN e Redes Neuronais e concluímos que, ao implementá-la obteríamos retornos consideravelmente elevados face aos alcançados através de uma simples estratégia de buy-and-hold, comprometendo assim a hipótese de eficiência fraca de mercado.<br>This dissertation reports the results of tests on the weak-form market efficiency applied to six European market indexes (France, Germany, UK, Greece, Portugal and Spain) from January 2007 to January 2012. For this matter we use a serial correlation test, a runs test, an augmented Dickey-Fuller test and the multiple variance ratio test. In addition we also analyze if it would be possible to forecast the PSI-20 returns resorting data mining, more specifically using k-NN and Neural Network. Our findings show that from January 1997 to September 2008 France, Germany and Spain meet most of the criteria for the weak-form market efficiency hypothesis, a situation that occurs afterwards for all six European market indexes from September 2008 to January 2012. Regarding the forecast of PSI-20 returns we designed a strategy based on the forecast of k-NN and Neural Network and concluded that by implementing it we would obtain relevant higher returns than the ones achieved by a buy-and-hold strategy, which compromises the weak-form market efficiency.
41
Park, Sungwook. "Three essays on long run movements of real exchange rates." Columbus, Ohio : Ohio State University, 2007. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=osu1180465881.
Full text
42
Idrissi, Imane. "Contribution au Diagnotic des Défauts de la Machine Asynchrone Doublement Alimentée de l'Eolienne à Vitesse Variable." Thesis, Normandie, 2019. http://www.theses.fr/2019NORMR033/document.
Full textAbstract:
Actuellement, les machines Asynchrones à Double Alimentation (MADA) sont omniprésentes dans le secteur éolien, grâce à leur simplicité de construction, leur faible coût d’achat et leur robustesse mécanique ainsi que le nombre faible d’interventions pour la maintenance. Cependant, comme toute autre machine électrique, ces génératrices sont sujettes aux défauts de différent ordre (électrique, mécanique, électromagnétique…) ou de différents types (capteur, actionneur ou composants du système). C’est pourquoi, il est primordial de concevoir une approche de diagnostic permettant de manière anticipée, de détecter, localiser et identifier tout défaut ou anomalie pouvant altérer le fonctionnement sain de ce type de machine. Motivés par les points forts des méthodes de diagnostic de défauts à base d’observateurs, nous proposons d’une part, dans cette thèse, une approche de détection, localisation et identification des défauts de la MADA d’une éolienne à vitesse variable, à base des observateurs de Kalman, performants et largement utilisés. Les erreurs d’estimation d’état du filtre de Kalman linéaire et de ses variantes non-linéaires, à noter : le Filtre de Kalman Etendu (EKF) et le Filtre de Kalman sans-Parfum (UKF), sont utilisés comme résidus sensibles aux défauts. En vue d’éviter les fausses alarmes et de découpler les défauts des perturbations et des bruits, l’analyse des résidus générés est réalisée par des tests statistiques tels que : Test de Page Hinkley (PH) et Test DCS (Dynamic Cumulative Sum). Pour la localisation des défauts multiples et simultanés, la Structure d’Observateurs Dédiés (DOS) et la Structure d’Observateurs Généralisés (GOS) sont appliquées. De plus, l’amplitude du défaut est déterminée dans l’étape d’identification de défaut. Les défauts capteurs, actionneurs et composants de la MADA, sont traités dans ce travail de recherche. D’autre part, une étude comparative entre les différents observateurs de Kalman, est élaborée. La comparaison porte sur les critères suivants : le temps de calcul, la précision et la vitesse de convergence des estimations<br>Actually, the Doubly Fed Induction Generators (DFIG) are omnipresent in the wind power market, owing to their construction simplicity, their low purchase cost and their mechanical robustness. However, as any other electrical machine, these generators are subject to defects of different order (electrical, mechanical, electromagnetic ...) or of different type (sensor, actuator or system). That’s why, it is important to design an effective diagnostic approach, able to early detect, locate and identify any defect or abnormal behavior, which could undermine the healthy operation of this machine On the one hand, motivated by the observer-based fault diagnosis methods strengths, we proposed, in this thesis, a diagnostic approach for the faults detection, localization and identification of the DFIG used in variable speed wind turbine. This approach is based on the use of the efficient and widely used Kalman observers. The state estimation errors of the linear Kalman filter and the non-linear Kalman filters, named: The Extended Kalman Filter (EKF) and the Unscented Kalman Filter (UKF) are used as faults sensitive residuals. In order to avoid false alarms and to decouple faults from disturbances and noises, the faults detection is carried out by the analysis of the residuals generated, by the mean of statistical tests such as: Hinkley Page Test (PH) and DCS Test (Dynamic) Cumulative Sum). For the localization step in case of multiple and simultaneous faults, the Dedicated Observer scheme (DOS) and the Generalized Observer scheme (GOS) are applied. In addition, the fault level is determined in the fault identification step. Sensor faults, actuator and system faults of DFIG, are treated in this research work. On the other hand, a comparative study between the three Kalman observers proposed is performed. The comparison was done in terms of (1) the computation time, (2) the estimation accuracy, and (3) the convergence speed
43
Jonsson, Robin, and Jessica Radeschnig. "Momentum Investment Strategies with Portfolio Optimization : A Study on Nasdaq OMX Stockholm Large Cap." Thesis, Mälardalens högskola, Akademin för utbildning, kultur och kommunikation, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-24848.
Full textAbstract:
This report covers a study testing the possibility of adding portfolio optimization by mean-variance analysis as a tool to extend the concept of momentum strategies in contrast to naive allocation formed by Jegadeesh & Titman (1993). Further these active investment strategies are compared with a passive benchmark as well as a randomly selected portfolio over the entire study-period. The study showed that the naive allocation model outperformed the mean-variance model both economically as well as statistically. No indication where obtained for a lagged return effect when letting a mean-variance model choose weights for a quarterly holding period and the resulting investment recommendation is to follow a naive investment strategy within a momentum framework.
44
Oliveira, Junior Braz Costa de. "Modelos de análise de dados de provas de ganho em peso de bovinos da raça Nelore /." Jaboticabal : [s.n.], 2009. http://hdl.handle.net/11449/92614.
Full textAbstract:
Resumo: dados de prova de ganho em peso (PGP) em confinamento, visando aumento na resposta à seleção pela inclusão de informações de parentesco nas estimativas dos parâmetros genéticos, assim como na acurácia dos valores genéticos estimados e na classificação final dos animais. As características analisadas foram o peso ao final da PGP (P378), o ganho em peso após o período de adaptação (G112), um índice considerando P378 e G112 (IPGP), além do peso inicial e dois pesos intermediários. Foram utilizadas 18.825 mensurações de pesos de 4.758 animais. Os modelos de dimensão finita considerados incluíram os efeitos fixos de mês e ano de nascimento (1977 a 2006) e classe de idade da mãe ao parto (2 a ≥12 anos), além do efeito linear da idade do animal no início da PGP como covariável. Quanto aos efeitos genéticos, foram considerados dois modelos, um só com o efeito genético direto e outro incluindo o efeito de ambiente permanente materno. Os modelos de regressão aleatória incluíram, como aleatórios, os efeitos genéticos aditivos direto, de ambiente permanente direto e materno e, como fixos, os efeitos de grupo de contemporâneos, a classe de idade da vaca ao parto e o polinômio ortogonal de Legendre da idade do animal (regressão quadrática), como covariáveis. Para comparar os resultados obtidos pelos modelos de regressão aleatória, foram conduzidas análises multicaracterísticas. Um total de 13 modelos de regressão aleatória, aplicando polinômios de segunda a quinta ordem foram considerados para modelar os efeitos genéticos aditivos direto e de ambiente permanente direto e materno. O resíduo foi modelado considerando 1, 3, 4, 6 e 9 classes de variâncias. O modelo contendo 4 classes de variâncias foi o que melhor descreveu o comportamento da trajetória para o efeito... (Resumo completo, clicar acesso eletrônico abaixo)<br>Abstract: This work was carried through with the objective of study different analysis forms of datasets regarding weight gain test (PGP) in feedlot, aiming improve in selection response through the inclusion of kinship information on estimates of genetic parameters, as well as in the estimated breeding values accuracy and in the final classification of the animals. We analyzed the characteristics weight at the end of PGP (P378), the weight gain after adaptation period (G112), an index considering P378 and G112 (IPGP), as well as the initial weight and two intermediate weights. 18,825 records of weights from 4.758 animals had been used. The considered models of finite dimension had included the fixed effects of year of birth (1977 to 2006) and cow age at birth class (2 ≥12 years), as well as the linear effect of the age of the animal at the PGP beginning as covariate. In spite the genetic analyses, we considered two models: one only with the direct genetic effect and another one including the maternal permanent environment effect. The random regression models included, as random, the additive direct genetic effect, the permanent direct and maternal environment effect, and, as fixed effects, the contemporary group, age of cow at birth class and the Legendre orthogonal polynomial of the animal age (quadratic regression), as covariates. In order to compare the achieved results for the models of random regression, we precede multicharacteristic analysis. A total of 15 models of random regression, applying polynomials of second to fifth order had been considered to fit the additive direct genetic effect and direct and maternal permanent environment effects. The residual was fitted considering 1, 3, 4, 6 and 9 variance classes. The model containing 4 variance classes was the ones that better described the trajectory... (Complete abstract click electronic access below)<br>Orientadora: Lúcia Galvão de Albuquerque<br>Coorientadora: Maria Eugênia Zerlotti Mercadante<br>Banca: Danísio Prado Munari<br>Banca: Lenira El Faro Zadra<br>Mestre
45
Le, Mapihan Katell. "Caractérisation et classification des phases stationnaires utilisées pour l'analyse CPL de produits pharmaceutiques." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2004. http://pastel.archives-ouvertes.fr/pastel-00000908.
Full textAbstract:
Lors du développement d'une nouvelle méthode de séparation, choisir la colonne CPL appropriée parmi les plus de 600 disponibles commercialement constitue un challenge d'autant plus difficile à relever que le mélange à séparer implique des produits basiques, rendant nécessaire le besoin d'une caractérisation et d'une classification objectives des phases stationnaires. Aucun des tests proposés dans la littérature n'étant apparu satisfaisant, nous avons développé et caractérisé notre propre procédure chromatographique en faisant appel notamment à l'outil chimiométrique. Notre méthodologie permet d'établir des cartographies interprétées des phases stationnaires testées, à la fois en fonction de la nature et de la teneur en solvant organique utilisé. Les classifications obtenues mettent aussi en évidence des différences notables de comportement chromatographiques et de mécanismes de rétention suivant les colonnes testées, différences qui sont relatées de façon synthétique par la construction de leur carte d'identité.
46
Briquet, Laurent. "Explorations psychométriques et psychoprojectives chez les auteurs d'infractions à caractère sexuel en psychologie légale : contribution sémiologique à l'identification de nouvelles composantes intrapsychiques et de nouvelles prises en charge psychothérapiques." Thesis, Bourgogne Franche-Comté, 2018. http://www.theses.fr/2018UBFCC006.
Full textAbstract:
La prise en charge des auteurs d’infractions à caractère sexuel bouscule les professionnels du soin dans les limites de leurs compétences thérapeutiques et pose par voie de conséquence la récurrente question des chances de réinsertion sociale de ces sujets dans la société.La méconnaissance du fonctionnement intrapsychique de ces patients, l’absence de formation des professionnels à la sexualité normale et pathologique, l’effet de renforcement sur les pulsions partielles produit par internet, ou encore la spécificité du cadre thérapeutique sous contrainte sont autant d’éléments qui nous placent définitivement hors d’un champ habituel de prise en charge en santé mentale. En tentant de prendre en compte l’ensemble de ces spécificités et en explorant de façon standardisée les dimensions psychosociales, psychométriques et psycho-projectives de ces auteurs d’infraction à caractère sexuel, cette recherche vise à mettre en lumière d’une part les variables intrapsychiques qui permettraient d’améliorer les échelles d’évaluation de la dangerosité sexuelle et d’autre part les caractéristiques psychothérapiques susceptibles de répondre aux dysfonctionnements psychiques spécifiques de cette population<br>The management of sexual offenders disrupts care professionals within the limits of their therapeutic skills and consequently raises the recurring question of the chances of reintegration in society.The lack of understanding of the intrapsychic functioning of these patients, the lack of training of professionals in normal and pathological sexuality, the reinforcing effect on partial drives produced by the internet, or the specificity of the court-ordered therapy’s framework are all elements which definitely puts us out of the usual mental health care field.By attempting to take into account all these specificities and by exploring in a standardized way the psychosocial, psychometric and psycho-projective dimensions of these sex offenders, this research attempts to highlight on the one hand the intrapsychic variables that would improve scales of sexual dangerosity and secondly the psychotherapeutic characteristics likely to respond to the specific psychological dysfunctions of this population
47
Rezazadeh, Baei Seyed Faridoddin [Verfasser], Hermann H. [Akademischer Betreuer] Swalve, Lutz [Akademischer Betreuer] Schüler, and Sven [Akademischer Betreuer] König. "Impact of dealing with outliers on variance estimations and genetic evaluations with milk yield test-day models in German Holstein cows / Seyed Faridoddin Rezazadeh Baei. Betreuer: Hermann H. Swalve ; Lutz Schüler ; Sven König." Halle, Saale : Universitäts- und Landesbibliothek Sachsen-Anhalt, 2009. http://d-nb.info/1024894517/34.
Full text
48
Oliveira, Junior Braz Costa de [UNESP]. "Modelos de análise de dados de provas de ganho em peso de bovinos da raça Nelore." Universidade Estadual Paulista (UNESP), 2009. http://hdl.handle.net/11449/92614.
Full textAbstract:
Made available in DSpace on 2014-06-11T19:26:07Z (GMT). No. of bitstreams: 0
Previous issue date: 2009-07-31Bitstream added on 2014-06-13T18:54:04Z : No. of bitstreams: 1
oliveirajunior_bc_me_jabo.pdf: 377876 bytes, checksum: 959f8b30ee240eb826bbd8afca79e17a (MD5)<br>Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)<br>Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)<br>dados de prova de ganho em peso (PGP) em confinamento, visando aumento na resposta à seleção pela inclusão de informações de parentesco nas estimativas dos parâmetros genéticos, assim como na acurácia dos valores genéticos estimados e na classificação final dos animais. As características analisadas foram o peso ao final da PGP (P378), o ganho em peso após o período de adaptação (G112), um índice considerando P378 e G112 (IPGP), além do peso inicial e dois pesos intermediários. Foram utilizadas 18.825 mensurações de pesos de 4.758 animais. Os modelos de dimensão finita considerados incluíram os efeitos fixos de mês e ano de nascimento (1977 a 2006) e classe de idade da mãe ao parto (2 a ≥12 anos), além do efeito linear da idade do animal no início da PGP como covariável. Quanto aos efeitos genéticos, foram considerados dois modelos, um só com o efeito genético direto e outro incluindo o efeito de ambiente permanente materno. Os modelos de regressão aleatória incluíram, como aleatórios, os efeitos genéticos aditivos direto, de ambiente permanente direto e materno e, como fixos, os efeitos de grupo de contemporâneos, a classe de idade da vaca ao parto e o polinômio ortogonal de Legendre da idade do animal (regressão quadrática), como covariáveis. Para comparar os resultados obtidos pelos modelos de regressão aleatória, foram conduzidas análises multicaracterísticas. Um total de 13 modelos de regressão aleatória, aplicando polinômios de segunda a quinta ordem foram considerados para modelar os efeitos genéticos aditivos direto e de ambiente permanente direto e materno. O resíduo foi modelado considerando 1, 3, 4, 6 e 9 classes de variâncias. O modelo contendo 4 classes de variâncias foi o que melhor descreveu o comportamento da trajetória para o efeito...<br>This work was carried through with the objective of study different analysis forms of datasets regarding weight gain test (PGP) in feedlot, aiming improve in selection response through the inclusion of kinship information on estimates of genetic parameters, as well as in the estimated breeding values accuracy and in the final classification of the animals. We analyzed the characteristics weight at the end of PGP (P378), the weight gain after adaptation period (G112), an index considering P378 and G112 (IPGP), as well as the initial weight and two intermediate weights. 18,825 records of weights from 4.758 animals had been used. The considered models of finite dimension had included the fixed effects of year of birth (1977 to 2006) and cow age at birth class (2 ≥12 years), as well as the linear effect of the age of the animal at the PGP beginning as covariate. In spite the genetic analyses, we considered two models: one only with the direct genetic effect and another one including the maternal permanent environment effect. The random regression models included, as random, the additive direct genetic effect, the permanent direct and maternal environment effect, and, as fixed effects, the contemporary group, age of cow at birth class and the Legendre orthogonal polynomial of the animal age (quadratic regression), as covariates. In order to compare the achieved results for the models of random regression, we precede multicharacteristic analysis. A total of 15 models of random regression, applying polynomials of second to fifth order had been considered to fit the additive direct genetic effect and direct and maternal permanent environment effects. The residual was fitted considering 1, 3, 4, 6 and 9 variance classes. The model containing 4 variance classes was the ones that better described the trajectory... (Complete abstract click electronic access below)
49
Melo, Claudio Manoel Rodrigues de. "Componentes de variância e valores genéticos para as produções de leite do dia do controle e da lactação na raça holandesa com diferentes modelos estatísticos." Universidade de São Paulo, 2003. http://www.teses.usp.br/teses/disponiveis/11/11139/tde-20082003-143346/.
Full textAbstract:
Foram utilizados 263.390 registros de produção de leite do dia do controle (PDC) de 32.448 primeiras lactações de vacas da raça Holandesa obtidas no período de 1991 a 2001 para estimar componentes de variância e parâmetros genéticos, usando diferentes modelos estatísticos e a metodologia REML. Compararam-se as estimativas de valores genético (EVG) dos modelos de repetibilidade (MR) e de regressão aleatória (MRA) com às do modelo para as produções da lactação (P305). Nos MRA utilizaram-se duas curvas para descrever a trajetória da lactação: a polinomial logarítmica de Ali e Schaeffer (AS) e a exponencial de Wilmink (W), sob duas formas: a padrão e com uma modificação para reduzir a amplitude das covariáveis e contornar problemas de convergência (W Ú ). No ajuste da curva AS considerou-se heterogeneidade de variâncias residuais (VR) entre classes de dias em lactação (cDEL). A estimativa de herdabilidade para as P305 (0,27) foi menor do que àquelas para as PDC obtidas com MR, incluindo ou não a curva AS como sub modelo (0,30 e 0,43, repectivamente). As herdabilidades para as PDC por análises uni-caráter (0,22-0,36) e bi-caráter (0,23-0,33) foram menores no início e fim da lactação. As correlações genéticas entre produções de controles consecutivos foram superiores às estimadas entre controles do ínicio e do fim da lactação. As estimativas de herdabilidade por MRA com as curva AS (0,29-0,42) e W Ú (0,33-0,40) foram semelhantes, mas aquelas estimadas com a curva W (0,25-0,65) foram maiores do que as estimadas com as outras curvas pricipalmente no fim da lactação. Com os MRA as correlações genéticas foram próximas da unidade entre produções de controles consecutivos, mas reduziram com o aumento do intervalo entre controles. As estimativas de VR entre cDEL foram muito semelhantes variando de 4,15 a 5,11 para a curvas AS. Os desvios padrão (DP) para as EVG para produção de leite dos touros foram semelhantes entre os modelos AS, W Ú e MR. Entretando, os DP para as EVG foram maiores nos modelos para PDC do que no modelo a P305. As correlações entre as EVG para touros com o modelo P305 e os demais modelos aumentaram com o aumento no número de filhas e variaram de 0,66 (P305-W) a 0,92 (P305-AS e P305- W Ú ). As estimativas de tendência genética foram maiores para os MRA e menores para o MR se comparadas à estimativa obtida pelo modelo para P305. As estimativas de herdabilidade superiores para as PDC e as altas correlações (0,86-0,99) entre estas e a P305 indicam um potêncial de uso das PDC nas avaliações genéticas. Correlações genéticas heterogêneas (0,64-1,00) entre as PDC, medidas ao longo da lactação, não confimam a suposição de que elas são medidas repetidas do mesmo caráter. O MRA com a curva AS e VR homogênea foi o de melhor ajuste entre os avaliados, mas o modelo W Ú resultou em estimativas de herdabilidade mais estáveis ao longo da lactação. Na comparação dos resultados dos modelos conclui-se que o MRA com a curva AS e homonogeneidade de VR é a melhor alternativa, dentre as estudadas, para avaliação genética para produção de leite de gado Holandês no Brasil.<br>Covariance components and genetic parameters for milk yield from 263,390 test-day records of 32,448 first lactation Holstein cows were estimated using animal models by REML. Test-day repeatability (RM) and random regression (RR) models were compared to a 305-d lactation model (P305) to estimate breeding values. Random regression involved the five-parameter logarithmic Ali and Schaeffer function (AS) and the three-parameter exponential Wilmink function in standard (W) and modified (W*, to reduce the range of covariates and avoid convergence problems) form to model the shape of the lactation curve. Heterogeneous error variance (EV) for classes of days in milk (cDIM) was considered in adjusting the AS function. Heritability for milk yield by P305 (0.27) was smaller than those estimated for daily milk yield by RM including or not including a logarithmic sub-model (0.30 and 0.43, respectively). Heritability estimates for univariate (0.22-0.36) and bivariate models (0.23-0.33) for test-day milk yields were smallest during early and late lactation. Genetic correlations were higher for daily milk yield between consecutive test-days than between test-days at the beginning and end of lactation. Heritability estimates for AS (0.29-0.42) and W* (0.33-0.40) RR models were similar, but heritability estimates obtained for W (0.25-0.65) were higher than those estimated by other functions, particularly at the end of lactation. Genetic correlations between daily milk yield on consecutive test-days were close to unity, but they decreased with an increase of the interval between test-days. Estimates of EV for cDIM were quite similar, rating from 4.15 to 5.11 for the AS function. Standard deviations (SD) of bullss EBVs for milk yield were similar for AS, W* models and RM. However, SD of EBVs for bulls and cows were larger for test-day models than for P305 and for bulls they differed by -33.64 to 321.95 from the P305 depending on progeny number. SD of EBVs for bulls and cows for the W model were the largest ones. Correlation between EBVs among P305 and the other models for bulls increased as progeny number increased and ranged from 0.66 (W-P305) to 0.92 (AS-P305, W*-P305). Genetic trends were larger for RR models and smaller for RM than for P305. Larger heritability estimates for test-day models and large genetic correlations between test-day and lactation milk yields (0.86-0.99) indicated a potential use of test-day records in genetic evaluations. Heterogeneous genetic correlations (0.64-1.00) for test-day milk yields across lactation did not support the assumption that test-day records are repeated measures of the same trait. The AS homogeneous EV model was the most parsimonious and the best fit among those evaluated, but the W* model resulted in more stable heritability estimates for daily milk yield across lactation. RR models provide more information than the RM and describe the shape of the lactation curve from which EBVs for persistency can be derived. These results indicated AS as an alternative model for genetic evaluation for milk yield using test-day records of Holstein cattle in Brazil.
50
Fadda, Emilienne. "Evaluation des composantes de l'énergie de surface par la technique des angles de contact : application à la mise au point et au controle de procédés en microélectronique." Université Joseph Fourier (Grenoble), 1995. http://www.theses.fr/1995GRE10222.
Full textAbstract:
Les differentes etapes des procedes de la microelectronique se traduisent par des modifications physico-chimiques de materiaux organiques et inorganiques. Pour l'etude des surfaces et des interfaces, hormis les methodes optiques, il existe peu de techniques de caracterisation simples, rapides, non destructives et utilisables aisement en salle blanche, dans un contexte de production. La mesure des angles de contact presente potentiellement ces avantages. Elle permet de determiner les differentes composantes de l'energie de surface et donc d'acceder aux interactions de van der waals et aux interactions acido-basiques presentes en surface. Pour identifier les modifications de surface revelees par les angles de contact et, afin de valider cette technique, il est necessaire de correler ces informations avec d'autres techniques de caracterisation, comme l'afm, l'xps et l'ir. Il est alors possible de mieux comprendre les phenomenes mis en jeu lors des procedes et donc d'optimiser les etapes. Le travail de these porte principalement sur l'etude des etapes de photolithographie qui est l'un des points critiques en microelectronique. Tout d'abord, les materiaux de base (polymeres, solvants) utilises ont ete analyses afin de determiner la sensibilite de la technique de caracterisation. Les differentes etapes de la lithographie (depot du film, insolation et developpement) ont ensuite ete etudiees. Dans cette etude, les mecanismes de fonctionnement des resines positives (i-line et duv) ont ete abordes. Pour terminer, la possibilite d'integrer la technique de mesure des angles de contact comme controle en ligne des etapes de lithographie a ete evaluee. D'autres exemples empruntes aux procedes de microelectronique comme le depot de couches epitaxiees ou la realisation d'interconnexions ont permis de confirmer les potentialites de la technique pour le controle en ligne des procedes