The two and k-sample tests of equality of the survival distributions against the alternatives including cross-effects of survival functions, proportional and monotone hazard ratios, are given for the right censored data. The asymptotic power against approaching alternatives is investigated. The tests are applied to the well known chemio and radio therapy data of the Gastrointestinal Tumor Study Group. The P-values for both proposed tests are much smaller then in the case of other known tests. Differently from the test of Stablein and Koutrouvelis the new tests can be applied not only for singly but also to randomly censored data.

The purpose of this analysis is to evaluate the usefulness of Fourier Transform Infrared (FTIR) spectroscopy in the detection of Herpes Simplex Virus 1 (hsv1) infection at an early stage. The raw absorption values were standardized to eliminate inter-sampling error. Wilcoxon-Mann-Whitney (WMW) statistic's Z score was calculated to select significant spectral regions. Partial least squares modeling was performed because of multicollinearity. Kolmogorov-Smirnov statistic showed models for healthy tissues from different time groups were not from same distribution. The additional 24 hour dataset was evaluated using the following methods. Variables were selected by WMW Z score. Difference of Composites statistic, DC, was created as a disease indicator and evaluated using area under the ROC curve, specificities, and confidence intervals using bootstrap algorithm. The specificity of DC was high, however the confidence intervals were large. Future studies are required with larger sample sizes to test this statistic's usefulness.

This thesis presents several statistical analysis on a cooperative project with Dr. Pallas and Yuting Mao from Biology Department of Georgia State University. This research concludes the impact of cauterize size of animals’ midbrain on auditory and visual response in brains. Besides some already commonly used statistical analysis method, such as MANOVA and Frequency Test, a unique combination of Permutation Test, Kolmogorov-Smirnov Test and Wilcoxon Rank Sum Test is applied to our non-parametric data. Some simulation results show the Permutation Test we used has very good powers, and fits the need for this study. The result confirms part of the Biology Department’s hypothesis statistically and enhances more complete understanding of the experiments and the potential impact of helping patients with Acquired Brain Injury.

Identifying previously unknown adverse drug reactions becomes more important as the number of drugs and the extent of their use increases. The aim of this Master’s thesis project was to evaluate the performance of a novel approach for highlighting potential adverse drug reactions, also known as signal detection. The approach was based on deviating time-to-onset patterns and was implemented as a two-sample Kolmogorov-Smirnov test for non-vaccine data in the safety report database, VigiBase. The method was outperformed by both disproportionality analysis and the multivariate predictive model vigiRank. Performance estimates indicate that deviating time-to-onset patterns is not a suitable approach for signal detection for non-vaccine data in VigiBase.

Measuring the research performance of a university is important to the universities themselves, governments, and students alike. Among other metrics, the number of publications is easy to obtain, and due to the large number of publications each university produces during one year, it suggests to be one accurate metric. However, the number of publications depends largely on the size of the institution, suggesting, if not addressed, that larger universities are better. Thus, one might intuitively try to normalize by size and use publications per researcher instead. A better institution would allow individual researchers to have more publications each year. However, publications, like many other things, might follow a power-law distribution, where most researchers have few, and only a few researchers have very many publications. These power-law distributions violate the assumptions the central limit the orem makes, for example, having a well-defined mean or variance. Specifically, one can not normalize or use averages from power-law distributed data, making the comparison of university publications impossible if they indeed follow a power-law distribution. While it has been shown that some scientific domains or universities show this power-law distribution, it is not known if Swedish universities also show this phenomenon. Thus, here we collect publication data for Swedish universities and determine whether or not, they are power-law distributed. Interestingly, if they are, one might use the slope of the power-law distribution as a proxy to determine research output. If the slope is steep, it suggests that the ratio between highly published authors and those with few publications is small. Where as a flatter slope suggests that a university has more highly published authors than a university with a steeper slope. Thus, the second objective here is to assess if the slope of the distribution can be determined or to which extent this is possible. This study will show that eight of the fifteen Swedish universities considered follow a power-law distribution (Kolmogorov-Smirnov statistic<0.05), while the remaining seven do not. The key determinant is the total number of publications. The difficulty here is that often the total number of publications is so small that one can not reject a power-law distribution, and it is also impossible to determine the slope of the distribution with any accuracy in those cases. While this study suggests that in principle, the slopes of the power-law distributions can be used as a comparative metric, it also showed that for half of Sweden’s universities, the data is insufficient for this type of analysis.

No description available.

Dans les études de fiabilité, il est possible que les durées de vie s'expriment par des valeurs entières. C'est le cas par exemple pour des appareils fonctionnant à la sollicitation. Le but de cette thèse est de revisiter les concepts classiques de la fiabilité des systèmes non réparables, quand on suppose que le temps est discret. Les grandeurs usuelles de la fiabilité en temps discret sont définies, ainsi que les principales notions de vieillissement. Nous passons ensuite en revue les principaux modèles de fiabilité que nous avons classés en trois familles à la suite de notre étude bibliographique. Après avoir mis en évidence qu'un certain nombre de différences entre les notions de fiabilité usuelles en temps continu et leurs équivalents en temps discret sont dues à la définition du taux de défaillance en temps discret, nous proposons une nouvelle définition qui résout les problèmes rencontrés. L'estimation non paramétrique des fonctions pouvant caractériser le vieillissement est traitée et nous donnons des résultats d'estimation ponctuelle, par intervalle et bande de confiance pour le taux de défaillance (usuel). L'estimation paramétrique des modèles de fiabilité est également abordée, avec une section importante consacrée à la loi géométrique dont les estimateurs sont explicites, contrairement à la plupart des autres lois discrètes. Un état de l'art des tests d'adéquation statistiques aux lois discrètes est présenté. Nous proposons un test basé sur la transformation de Smirnov généralisée dont la puissance est étudiée pour tester l'adéquation aux lois géométrique et Weibull de type I.

由於商業、工業和民生各方面大量的用電需求，使得電費在某些季節會特別昂貴。又因為電力的生產和儲存都有限，故電力公司為了能更有效率的分配總電力，要求消費者事先訂定各自用戶的契約容量，做為每個月分配電力的最大標準。對於消費者而言，相較於較高的契約容量，選取較低的契約容量通常負擔的基本電費也較低，但是當用電量超過契約容量時則必須支付高額罰金。因此消費者為了盡可能使長期的用電消費降低，選擇一個合適且最佳的契約容量是很重要的課題。在本文中以隨機模型”具飄移項之布朗運動”作為分析用電量趨勢的模型，並介紹如何做模型的驗證以及參數的估計，接著建構出總電費的期望值估計式以尋找最佳的契約容量。最後，以政治大學的實際用電量資料作為本文的研究實例，並提出選擇契約容量之建議方針。

En France, la vidéo surveillance est actuellement présenté comme un élément clef de la prévention des crimes, et le nombre de caméras installées dans les lieux publiques a triplé en 2009, passant de 20 000 à 60 000. Malgré le débat généré dans l’opinion publique, il semblerait qu’aucun gouvernement ne souhaite freiner l’utilisation de ces mesures de surveillance. Si l’on met de côté le débat social, d’un point de vue strictement scientifique, ces systèmes de surveillance offrent des bases de données riches et de vrai perspective de recherche en multimédia. Dans ce manuscrit, nous nous sommes concentré sur le développement de méthodes de suivi d’objets multiples non-rigides dans un environnement multi-caméra à l’aide de filtrage à particules. Nous d´ecrirons, dans un premier temps, une méthode de suivi multi-résolution par filtrage à particules avec contrôle de consistance. Cette méthode fut appliquée au suivi d’un seul objet non rigide dans des vidéos dont le nombre d’images pas seconde étaient faible et variable. Elle est etendue pour suivre des objets multiples par filtrage à particules avec double contrôles de consistance. Elle est notamment appliquée pour le défi de TRECVID 2009. An analyse d’événements est finalement ajoutée. Notre méthode de suivi est ensuite étendue d’une seule caméra vers de multiples caméras. Elle fut utilisée pour le suivi d’un objet non-rigide par interaction de caméras. Enfin, une méthode de suivi par filtrage à particules d’objets multiples avec analyse d’événement a été définie pour le suivi de deux objets non-rigides dans un environnement à deux caméras. Notre système peut êre facilement adaptées à de nombreux types de vidéo surveillance car aucune information sur les scènes n’est pré-requise. / The video surveillance is believed to play a so important role in the crime prevention that only in France, the number of cameras installed at public thoroughfare was tripled in the year 2009, from 20 000 to 60 000. Even though its increasing use has triggered a large debate about security versus privacy, it seems that no government has a willingness to stop the surveillance popularity. However, if we just put aside this social anxiety, from the scientific point of view, millions of surveillance systems do offer us a rich database and an exciting motivation for the multimedia research. We focus on the multiple non-rigid object tracking based on the Particle Filter method in multiple camera environments in this dissertation. The method of Multi-resolution Particle Filter Tracking with Consistency Check is firstly introduced as the basis of our tracking system. It is especially used for single non-rigid object tracking in videos of low and variable frame rate. It is then extended to track multiple non-rigid objects, denoted as Multi-object Particle Filter Tracking with Dual Consistency Check. It is in particularly applied to the challenge TRECVID 2009. An automatic semantic event detection and identification is integrated at last. Our tracking method is later extended from mono-camera to multi-camera environments. It is used for the single non-rigid object tracking with the interaction of cameras. Finally, a system named Multi-object Particle Filter Tracking with Event analysis is designed for tracking two non-rigid objects in two-camera environments. Our tracking system can be easily applied to various video surveillance systems since no prior knowledge of the scene is required.

This diploma thesis focuses on the statistical examination of properties of plant protection products at Agro-Artikel, s.r.o. Using the empirical distribution function, it focuses on the sales price and the shelf life of the products, tests the hypotheses about the properties of the products and the dependencies between them. The thesis also explores the results of the questionnaire survey and offers recommendations for the introduction of new products.