931 resultados para Probability Distributions


Relevância:

60.00% 60.00%

Publicador:

Resumo:

In this work, we propose a copula-based method to generate synthetic gene expression data that account for marginal and joint probability distributions features captured from real data. Our method allows us to implant significant genes in the synthetic dataset in a controlled manner, giving the possibility of testing new detection algorithms under more realistic environments.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

In mathematical modeling the estimation of the model parameters is one of the most common problems. The goal is to seek parameters that fit to the measurements as well as possible. There is always error in the measurements which implies uncertainty to the model estimates. In Bayesian statistics all the unknown quantities are presented as probability distributions. If there is knowledge about parameters beforehand, it can be formulated as a prior distribution. The Bays’ rule combines the prior and the measurements to posterior distribution. Mathematical models are typically nonlinear, to produce statistics for them requires efficient sampling algorithms. In this thesis both Metropolis-Hastings (MH), Adaptive Metropolis (AM) algorithms and Gibbs sampling are introduced. In the thesis different ways to present prior distributions are introduced. The main issue is in the measurement error estimation and how to obtain prior knowledge for variance or covariance. Variance and covariance sampling is combined with the algorithms above. The examples of the hyperprior models are applied to estimation of model parameters and error in an outlier case.

Relevância:

60.00% 60.00%

Publicador:

Resumo:

The Gulf of Finland is said to be one of the densest operated sea areas in the world. It is a shallow and economically vulnerable sea area with dense passenger and cargo traffic of which petroleum transports have a share of over 50 %. The winter conditions add to the risks of maritime traffic in the Gulf of Finland. It is widely believed that the growth of maritime transportation will continue also in the future. The Gulf of Finland is surrounded by three very different national economies with, different maritime transportation structures. Finland is a country of high GDP/per capita with a diversified economic structure. The number of ports is large and the maritime transportation consists of many types of cargoes: raw materials, industrial products, consumer goods, coal and petroleum products, and the Russian transit traffic of e.g. new cars and consumer goods. Russia is a large country with huge growth potential; in recent years, the expansion of petroleum exports has lead to a strong economic growth, which is also apparent in the growth of maritime transports. Russia has been expanding its port activities in the Gulf of Finland and it is officially aiming to transport its own imports and exports through the Russian ports in the future; now they are being transported to great extend through the Finnish, Estonian and other Baltic ports. Russia has five ports in the Gulf of Finland. Estonia has also experienced fast economic growth, but the growth has been slowing down already during the past couples of years. The size of its economy is small compared to Russia, which means the transported tonnes cannot be very massive. However, relatively large amounts of the Russian petroleum exports have been transported through the Estonian ports. The future of the Russian transit traffic in Estonia looks nevertheless uncertain and it remains to be seen how it will develop and if Estonia is able to find replacing cargoes if the Russian transit traffic will come to an end in the Estonian ports. Estonia’s own import and export consists of forestry products, metals or other raw materials and consumer goods. Estonia has many ports on the shores of the Gulf of Finland, but the port of Tallinn dominates the cargo volumes. In 2007, 263 M tonnes of cargoes were transported in the maritime traffic in the Gulf of Finland, of which the share of petroleum products was 56 %. 23 % of the cargoes were loaded or unloaded in the Finnish ports, 60 % in the Russian ports and 17 % in the Estonian ports. The largest ports were Primorsk (74.2 M tonnes) St. Petersburg (59.5 M tonnes), Tallinn (35.9 M tonnes), Sköldvik (19.8 M tonnes), Vysotsk (16.5 M tonnes) and Helsinki (13.4 M) tonnes. Approximately 53 600 ship calls were made in the ports of the Gulf of Finland. The densest traffic was found in the ports of St. Petersburg (14 651 ship calls), Helsinki (11 727 ship calls) and Tallinn (10 614 ship calls) in 2007. The transportation scenarios are usually based on the assumption that the amount of transports follows the development of the economy, although also other factors influence the development of transportation, e.g. government policy, environmental aspects, and social and behavioural trends. The relationship between the development of transportation and the economy is usually analyzed in terms of the development of GDP and trade. When the GDP grows to a certain level, especially the international transports increase because countries of high GDP produce, consume and thus transport more. An effective transportation system is also a precondition for the economic development. In this study, the following factors were taken into consideration when formulating the future scenarios: maritime transportation in the Gulf of Finland 2007, economic development, development of key industries, development of infrastructure and environmental aspects in relation to maritime transportation. The basic starting points for the three alternative scenarios were: • the slow growth scenario: economic recession • the average growth scenario: economy will recover quickly from current instability • the strong growth scenario: the most optimistic views on development will realize According to the slow growth scenario, the total tonnes for the maritime transportation in the Gulf of Finland would be 322.4 M tonnes in 2015, which would mean a growth of 23 % compared to 2007. In the average growth scenario, the total tonnes were estimated to be 431.6 M tonnes – a growth of 64 %, and in the strong growth scenario 507.2 M tonnes – a growth of 93%. These tonnes were further divided into petroleum products and other cargoes by country, into export, import and domestic traffic by country, and between the ports. For petroleum products, the share of crude oil and oil products was estimated and the number of tanker calls in 2015 was calculated for each scenario. However, the future development of maritime transportation in the GoF is dependent on so many societal and economic variables that it is not realistic to predict one exact point estimate value for the cargo tonnes for a certain scenario. Plenty of uncertainty is related both to the degree in which the scenario will come true as well as to the cause-effect relations between the different variables. For these reasons, probability distributions for each scenario were formulated by an expert group. As a result, a range for the total tonnes of each scenario was formulated and they are as follows: the slow growth scenario: 280.8 – 363 M tonnes (expectation value 322.4 M tonnes)

  • the average growth scenario: 404.1 – 465.1 M tonnes (expectation value 431.6 M tonnes)
  • the strong growth scenario: 445.4 – 575.4 M tonnes (expectation value 507.2 M tonnes) Three alternatives scenarios were evaluated to realize most likely with the following probability distribution:
  • the slow growth scenario: 35 %
  • the average growth scenario: 50 %
  • the strong growth scenario: 15 %. In other words, expert group evaluated the average growth scenario to be the most likely to realize, second likely was the slow growth scenario, and the strong growth scenario was evaluated to be the most unlikely to realize. In sum, it can be stated that the development of maritime transportation in the Gulf of Finland is dominated by the development of Russia, because Russia dominates the cargo volumes. Maritime transportation in Finland is expected to be more stable and, in any case, such a growth potential cannot be seen in Finland. The development of maritime transportation in Estonia is rather challenging to forecast at the moment but, on the other hand, the transported tonnes in the Estonian ports are relatively small. The shares of export and import of the maritime transportation are not expected to change radically in the reference period. Petroleum products will dominate the transports also in the future and the share of oil products will probably increase compared to the share of crude oil. In regard to the other cargoes, the transports of raw materials and bulk goods will probably be replaced to some extend by cargoes of high-value, which adds especially to the container transports. But in overall, substantial changes are not expected in the commodity groups transported by sea. The growth potential of the ports concentrates on the Russian ports, especially Primorsk and Ust-Luga, if investments will come true as planned. It is likely that the larger ports do better in the competition than the small ones due to the economies of scale and to the concentration of cargo flows. The average ship sizes will probably grow, but the growth potential is rather limited because of geographical conditions and of the maritime transportation structure in the Gulf of Finland. Climate change and other environmental aspects are becoming more central e.g. in transportation politics. These issues can affect the maritime transportation in the Gulf of Finland through, for instance, strict environmental requirements concerning the emissions from shipping, or the port investments. If environmental requirements raise costs, it can affect the demand of transportation. In the near future, the development of the maritime transportation in the Gulf of Finland is mainly dependent on the current economic instability. If it will lead to a longer lasting recession, the growth of the transported tonnes will slow down. But if the instability does not last long, it can be expected that the economic growth will continue and along with it also the growth of transported tonnes.

  • Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    Pitkäaikaisten rakennusurakoiden tarjouslaskennassa on ennakoitava hintojen muutoksia useiden vuosien päähän, kun tarjoukset on tehtävä kiinteillä hinnoilla. Kustannusten ennakointi ja hintariskienhallinta on kriittinen tekijä rakennusalan yrityksen kilpailukyvylle. Tämän tutkielman tavoitteena on kehittää YIT Rakennus Oy:n Infrapalveluille toimintamalli ja työkalu, joiden avulla hintariskejä voidaan hallita tarjouslaskennassa sekä hankintatoimessa. Ratkaisuksi kehitettiin kustannusten ennakointi -malli, jossa panosryhmien hintojen kehitystä ennustetaan asiantuntijaryhmissä säännöllisesti. Kustannusten ennakointi -mallin käyttöönotto vaatii ennustettavien panosryhmien määrittelyä. Lisäksi on nimettävä asiantuntijaryhmä sekä valittava aikajänne, jolle ennuste tehdään. Ennusteisiin sisältyvä epävarmuus saadaan esiin Monte Carlo simulaatiolla, ja urakan hintariskiä voidaan siten arvioida todennäköisyysjakaumien ja herkkyysanalyysin avulla. Valmiita ennusteita hyödynnetään tarjouslaskennassa sekä hankintatoimessa taktiikoiden ja strategioiden valinnassa.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    The energy reform, which is happening all over the world, is caused by the common concern of the future of the humankind in our shared planet. In order to keep the effects of the global warming inside of a certain limit, the use of fossil fuels must be reduced. The marginal costs of the renewable sources, RES are quite high, since they are new technology. In order to induce the implementation of RES to the power grid and lower the marginal costs, subsidies were developed in order to make the use of RES more profitable. From the RES perspective the current market is developed to favor conventional generation, which mainly uses fossil fuels. Intermittent generation, like wind power, is penalized in the electricity market since it is intermittent and thus diffi-cult to control. Therefore, the need of regulation and thus the regulation costs to the producer differ, depending on what kind of generation market participant owns. In this thesis it is studied if there is a way for market participant, who has wind power to use the special characteristics of electricity market Nord Pool and thus reach the gap between conventional generation and the intermittent generation only by placing bids to the market. Thus, an optimal bid is introduced, which purpose is to minimize the regulation costs and thus lower the marginal costs of wind power. In order to make real life simulations in Nord Pool, a wind power forecast model was created. The simulations were done in years 2009 and 2010 by using a real wind power data provided by Hyötytuuli, market data from Nord Pool and wind forecast data provided by Finnish Meteorological Institute. The optimal bid needs probability intervals and therefore the methodology to create probability distributions is introduced in this thesis. In the end of the thesis it is shown that the optimal bidding improves the position of wind power producer in the electricity market.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    This paper provides new versions of Harsanyi’s social aggregation theorem that are formulated in terms of prospects rather than lotteries. Strengthening an earlier result, fixed-population ex-ante utilitarianism is characterized in a multi-profile setting with fixed probabilities. In addition, we extend the social aggregation theorem to social-evaluation problems under uncertainty with a variable population and generalize our approach to uncertain alternatives, which consist of compound vectors of probability distributions and prospects.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    This paper presents a new theory of random consumer demand. The primitive is a collection of probability distributions, rather than a binary preference. Various assumptions constrain these distributions, including analogues of common assumptions about preferences such as transitivity, monotonicity and convexity. Two results establish a complete representation of theoretically consistent random demand. The purpose of this theory of random consumer demand is application to empirical consumer demand problems. To this end, the theory has several desirable properties. It is intrinsically stochastic, so the econometrician can apply it directly without adding extrinsic randomness in the form of residuals. Random demand is parsimoniously represented by a single function on the consumption set. Finally, we have a practical method for statistical inference based on the theory, described in McCausland (2004), a companion paper.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    Dans le domaine des neurosciences computationnelles, l'hypothèse a été émise que le système visuel, depuis la rétine et jusqu'au cortex visuel primaire au moins, ajuste continuellement un modèle probabiliste avec des variables latentes, à son flux de perceptions. Ni le modèle exact, ni la méthode exacte utilisée pour l'ajustement ne sont connus, mais les algorithmes existants qui permettent l'ajustement de tels modèles ont besoin de faire une estimation conditionnelle des variables latentes. Cela nous peut nous aider à comprendre pourquoi le système visuel pourrait ajuster un tel modèle; si le modèle est approprié, ces estimé conditionnels peuvent aussi former une excellente représentation, qui permettent d'analyser le contenu sémantique des images perçues. Le travail présenté ici utilise la performance en classification d'images (discrimination entre des types d'objets communs) comme base pour comparer des modèles du système visuel, et des algorithmes pour ajuster ces modèles (vus comme des densités de probabilité) à des images. Cette thèse (a) montre que des modèles basés sur les cellules complexes de l'aire visuelle V1 généralisent mieux à partir d'exemples d'entraînement étiquetés que les réseaux de neurones conventionnels, dont les unités cachées sont plus semblables aux cellules simples de V1; (b) présente une nouvelle interprétation des modèles du système visuels basés sur des cellules complexes, comme distributions de probabilités, ainsi que de nouveaux algorithmes pour les ajuster à des données; et (c) montre que ces modèles forment des représentations qui sont meilleures pour la classification d'images, après avoir été entraînés comme des modèles de probabilités. Deux innovations techniques additionnelles, qui ont rendu ce travail possible, sont également décrites : un algorithme de recherche aléatoire pour sélectionner des hyper-paramètres, et un compilateur pour des expressions mathématiques matricielles, qui peut optimiser ces expressions pour processeur central (CPU) et graphique (GPU).

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    La tâche de maintenance ainsi que la compréhension des programmes orientés objet (OO) deviennent de plus en plus coûteuses. L’analyse des liens de dépendance peut être une solution pour faciliter ces tâches d’ingénierie. Cependant, analyser les liens de dépendance est une tâche à la fois importante et difficile. Nous proposons une approche pour l'étude des liens de dépendance internes pour des programmes OO, dans un cadre probabiliste, où les entrées du programme peuvent être modélisées comme un vecteur aléatoire, ou comme une chaîne de Markov. Dans ce cadre, les métriques de couplage deviennent des variables aléatoires dont les distributions de probabilité peuvent être étudiées en utilisant les techniques de simulation Monte-Carlo. Les distributions obtenues constituent un point d’entrée pour comprendre les liens de dépendance internes entre les éléments du programme, ainsi que leur comportement général. Ce travail est valable dans le cas où les valeurs prises par la métrique dépendent des entrées du programme et que ces entrées ne sont pas fixées à priori. Nous illustrons notre approche par deux études de cas.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    Les méthodes de Monte Carlo par chaîne de Markov (MCMC) sont des outils très populaires pour l’échantillonnage de lois de probabilité complexes et/ou en grandes dimensions. Étant donné leur facilité d’application, ces méthodes sont largement répandues dans plusieurs communautés scientifiques et bien certainement en statistique, particulièrement en analyse bayésienne. Depuis l’apparition de la première méthode MCMC en 1953, le nombre de ces algorithmes a considérablement augmenté et ce sujet continue d’être une aire de recherche active. Un nouvel algorithme MCMC avec ajustement directionnel a été récemment développé par Bédard et al. (IJSS, 9 :2008) et certaines de ses propriétés restent partiellement méconnues. L’objectif de ce mémoire est de tenter d’établir l’impact d’un paramètre clé de cette méthode sur la performance globale de l’approche. Un second objectif est de comparer cet algorithme à d’autres méthodes MCMC plus versatiles afin de juger de sa performance de façon relative.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    Les méthodes de Monte Carlo par chaînes de Markov (MCCM) sont des méthodes servant à échantillonner à partir de distributions de probabilité. Ces techniques se basent sur le parcours de chaînes de Markov ayant pour lois stationnaires les distributions à échantillonner. Étant donné leur facilité d’application, elles constituent une des approches les plus utilisées dans la communauté statistique, et tout particulièrement en analyse bayésienne. Ce sont des outils très populaires pour l’échantillonnage de lois de probabilité complexes et/ou en grandes dimensions. Depuis l’apparition de la première méthode MCCM en 1953 (la méthode de Metropolis, voir [10]), l’intérêt pour ces méthodes, ainsi que l’éventail d’algorithmes disponibles ne cessent de s’accroître d’une année à l’autre. Bien que l’algorithme Metropolis-Hastings (voir [8]) puisse être considéré comme l’un des algorithmes de Monte Carlo par chaînes de Markov les plus généraux, il est aussi l’un des plus simples à comprendre et à expliquer, ce qui en fait un algorithme idéal pour débuter. Il a été sujet de développement par plusieurs chercheurs. L’algorithme Metropolis à essais multiples (MTM), introduit dans la littérature statistique par [9], est considéré comme un développement intéressant dans ce domaine, mais malheureusement son implémentation est très coûteuse (en termes de temps). Récemment, un nouvel algorithme a été développé par [1]. Il s’agit de l’algorithme Metropolis à essais multiples revisité (MTM revisité), qui définit la méthode MTM standard mentionnée précédemment dans le cadre de l’algorithme Metropolis-Hastings sur un espace étendu. L’objectif de ce travail est, en premier lieu, de présenter les méthodes MCCM, et par la suite d’étudier et d’analyser les algorithmes Metropolis-Hastings ainsi que le MTM standard afin de permettre aux lecteurs une meilleure compréhension de l’implémentation de ces méthodes. Un deuxième objectif est d’étudier les perspectives ainsi que les inconvénients de l’algorithme MTM revisité afin de voir s’il répond aux attentes de la communauté statistique. Enfin, nous tentons de combattre le problème de sédentarité de l’algorithme MTM revisité, ce qui donne lieu à un tout nouvel algorithme. Ce nouvel algorithme performe bien lorsque le nombre de candidats générés à chaque itérations est petit, mais sa performance se dégrade à mesure que ce nombre de candidats croît.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    We generalize the classical expected-utility criterion by weakening transitivity to Suzumura consistency. In the absence of full transitivity, reflexivity and completeness no longer follow as a consequence of the system of axioms employed and a richer class of rankings of probability distributions results. This class is characterized by means of standard expected-utility axioms in addition to Suzumura consistency. An important feature of some members of our new class is that they allow us to soften the negative impact of wellknown paradoxes without abandoning the expected-utility framework altogether.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    clRNG et clProbdist sont deux interfaces de programmation (APIs) que nous avons développées pour la génération de nombres aléatoires uniformes et non uniformes sur des dispositifs de calculs parallèles en utilisant l’environnement OpenCL. La première interface permet de créer au niveau d’un ordinateur central (hôte) des objets de type stream considérés comme des générateurs virtuels parallèles qui peuvent être utilisés aussi bien sur l’hôte que sur les dispositifs parallèles (unités de traitement graphique, CPU multinoyaux, etc.) pour la génération de séquences de nombres aléatoires. La seconde interface permet aussi de générer au niveau de ces unités des variables aléatoires selon différentes lois de probabilité continues et discrètes. Dans ce mémoire, nous allons rappeler des notions de base sur les générateurs de nombres aléatoires, décrire les systèmes hétérogènes ainsi que les techniques de génération parallèle de nombres aléatoires. Nous présenterons aussi les différents modèles composant l’architecture de l’environnement OpenCL et détaillerons les structures des APIs développées. Nous distinguons pour clRNG les fonctions qui permettent la création des streams, les fonctions qui génèrent les variables aléatoires uniformes ainsi que celles qui manipulent les états des streams. clProbDist contient les fonctions de génération de variables aléatoires non uniformes selon la technique d’inversion ainsi que les fonctions qui permettent de retourner différentes statistiques des lois de distribution implémentées. Nous évaluerons ces interfaces de programmation avec deux simulations qui implémentent un exemple simplifié d’un modèle d’inventaire et un exemple d’une option financière. Enfin, nous fournirons les résultats d’expérimentation sur les performances des générateurs implémentés.

    Relevância:

    60.00% 60.00%

    Publicador:

    Resumo:

    The present study focuses attention on defining certain measures of income inequality for the truncated distributions and characterization of probability distributions using the functional form of these measures, extension of some measures of inequality and stability to higher dimensions, characterization of bivariate models using the above concepts and estimation of some measures of inequality using the Bayesian techniques. The thesis defines certain measures of income inequality for the truncated distributions and studies the effect of truncation upon these measures. An important measure used in Reliability theory, to measure the stability of the component is the residual entropy function. This concept can advantageously used as a measure of inequality of truncated distributions. The geometric mean comes up as handy tool in the measurement of income inequality. The geometric vitality function being the geometric mean of the truncated random variable can be advantageously utilized to measure inequality of the truncated distributions. The study includes problem of estimation of the Lorenz curve, Gini-index and variance of logarithms for the Pareto distribution using Bayesian techniques.