The maximum spacing (MSP) method, introduced by Cheng and Amin (1983) and independently by Ranneby (1984), is a general estimation method for continuous univariate distributions. The MSP method, which is closely related to the maximum likelihood (ML) method, can be derived from an approximation based on simple spacings of the Kullback-Leibler information. It is known to give consistent and asymptotically efficient estimates under general conditions and works also in situations where the ML method fails, e.g. for the three parameter Weibull model. In this thesis it is proved under general conditions that MSP estimates of parameters in the Euclidian metric are strongly consistent. The ideas behind the MSP method are extended and a class of estimation methods is introduced. These methods, called generalized MSP methods, are derived from approxima­tions based on sum-functions of rath order spacings of certain information mea­sures, i.e. the ^-divergences introduced by Csiszår (1963). It is shown under general conditions that generalized MSP methods give consistent estimates. In particular, it is proved that generalized MSP methods give L1 consistent esti­mates in any family of distributions with unimodal densities, without any further conditions on the distributions. Other properties such as distributional robust­ness are also discussed. Several limit theorems for sum-functions of rath order spacings are given, for ra fixed as well as for the case when ra is allowed to in­crease to infinity with the sample size. These results provide a strongly consistent nonparametric estimator of entropy, as well as a characterization of the uniform distribution. Further, it is shown that Cressie's (1976) goodness of fit test is strongly consistent against all continuous alternatives. / digitalisering@umu

Computer networks are becoming increasingly large and complex; more so with the recent penetration of the internet into all walks of life. It is essential to be able to monitor and to analyse networks in a timely and efficient manner; to extract important metrics and measurements and to do so in a way which does not unduly disturb or affect the performance of the network under test. Network tomography is one possible method to accomplish these aims. Drawing upon the principles of statistical inference, it is often possible to determine the statistical properties of either the links or the paths of the network, whichever is desired, by measuring at the most convenient points thus reducing the effort required. In particular, bottleneck-link detection methods in which estimates of the delay distributions on network links are inferred from measurements made at end-points on network paths, are examined as a means to determine which links of the network are experiencing the highest delay. Initially two published methods, one based upon a single Gaussian distribution and the other based upon the method-of-moments, are examined by comparing their performance using three metrics: robustness to scaling, bottleneck detection accuracy and computational complexity. Whilst there are many published algorithms, there is little literature in which said algorithms are objectively compared. In this thesis, two network topologies are considered, each with three configurations in order to determine performance in six scenarios. Two new estimation methods are then introduced, both based on Gaussian mixture models which are believed to offer an advantage over existing methods in certain scenarios. Computationally, a mixture model algorithm is much more complex than a simple parametric algorithm but the flexibility in modelling an arbitrary distribution is vastly increased. Better model accuracy potentially leads to more accurate estimation and detection of the bottleneck. The concept of increasing flexibility is again considered by using a Pearson type-1 distribution as an alternative to the single Gaussian distribution. This increases the flexibility but with a reduced complexity when compared with mixture model approaches which necessitate the use of iterative approximation methods. A hybrid approach is also considered where the method-of-moments is combined with the Pearson type-1 method in order to circumvent problems with the output stage of the former. This algorithm has a higher variance than the method-of-moments but the output stage is more convenient for manipulation. Also considered is a new approach to detection algorithms which is not dependant on any a-priori parameter selection and makes use of the Kullback-Leibler divergence. The results show that it accomplishes its aim but is not robust enough to replace the current algorithms. Delay estimation is then cast in a different role, as an integral part of an algorithm to correlate input and output streams in an anonymising network such as the onion router (TOR). TOR is used by users in an attempt to conceal network traffic from observation. Breaking the encryption protocols used is not possible without significant effort but by correlating the un-encrypted input and output streams from the TOR network, it is possible to provide a degree of certainty about the ownership of traffic streams. The delay model is essential as the network is treated as providing a pseudo-random delay to each packet; having an accurate model allows the algorithm to better correlate the streams.

Population divergence shaped by natural selection is central to evolutionary ecology research and has been in focus since Darwin formulated “The origin of species”. Still, the process of adaptive divergence among sympatric populations is poorly understood. In this thesis I studied patterns of adaptive divergence among subpopulations of pike (Esox lucius) that are sympatric in the Baltic Sea but become short-term allopatric during spawning and initial juvenile growth in freshwater streams. I also examined causes and consequences of phenotypic variation among individuals within subpopulations to evaluate the contribution of natural selection to population divergence.   I first investigated homing behaviour and population structures of pike to assess the potential for adaptive divergence among sympatric pike that migrate to spawn in different streams. Mark-recapture data suggested that migrating pike displayed homing behaviour and repeatedly returned to the same stream. Analyses of microsatellite data revealed partial reproductive isolation among subpopulations spawning in different streams. These subpopulations, however, were truly sympatric during the life-stage spent in the Baltic Sea.   To address whether short-term allopatry has resulted in adaptive divergence among sympatric subpopulations I combined observational, experimental and molecular approaches. Observational data showed that subpopulations differed in morphological and life-history traits and common-garden experiments suggested that differences were, at least in part, genetically based. Moreover, QST-FST comparisons indicated that genetically based phenotypic differences has been driven by divergent selection, and a reciprocal translocation experiment showed that phenotypic variation represented local adaptations to spawning habitats. Finally, longitudinal and cross-sectional comparisons among individuals revealed associations between phenotypes, performance and fitness components.   In conclusion, my thesis illustrates how short-term allopatry due to migratory behaviour can result in adaptive divergence among sympatric subpopulations. These findings advance the understanding of evolutionary processes at the finest spatiotemporal scale and illustrate that local adaptations can arise in environments with high connectivity.  The results also emphasise that fine spatial scale population structures must be taken into consideration in management and conservation of biodiversity in the Baltic Sea.

We have from our research, conducted in Guardamar del Segura, Spain, discovered that most of the communication between native Spaniards and immigrant Bulgarians is negative non-verbal communication which leads to a division between the two groups. The result of high unemployment and social stress, which the current situation in Spain provides, tend to create stronger ties inside the groups and at the same time enlarge the distance towards other groups. Also, the large amount of nonverbal communication such as observing each other’s behavior leads in this case to negative stereotyping and prejudices that creates and maintain the different group’s relations in the society.

The ß-lactam antibiotics are the most important antibacterial agents in the treatment of infectious diseases. A severe problem in ß-lactam therapy is the emergence of ß-lactam resistant bacteria. Clinical ß-lactam resistance is most often due to the production of ß-lactamases. ß-lactamase genes reside either on plasmids or on the chromosome. The aim of this study was to acquire an understanding of organisation and regulation of chromosomal ß- lactamase genes in different Gram negative species and to elucidate the mechanisms for ampC hyperproduction in the in vivo situation. By DNA hybridization with an ampC probe from Escherichia coli K-12 it was shown that other Gram negative bacteria contained an artpC like chromosomal gene, suggesting a common evolutionary origin. Furthermore, the preceding frd operon that overlaps the ampC gene in E. coli K-12 was found to be much more conserved than the ampC gene in the bacterial species investigated. The ampC and frd opérons in Shigella sonnei and Citrobacter freundii were cloned and characterized by physical mapping. The respective maps were compared to the ampC and frd region in E. coli K-12. The physical map of Sh. sonnei was almost identical to the E. coli K-12 map, whereas in C. freundii only the frd region exhibited any considerable homology. Moreover, in C. freundii, the anpC and frd regions were separated by 1100 basepairs. It is suggested that this DNA is involved in the induction of ß-lactamase production in this organism. A hypothesis for the evolution of the anpC operon in enterobacteria is presented. By isolating and characterizing six ß-lactam resistant clinica], isolates of E. coli hyperproducing the dhrcmosomal ß-lactamase, genetic mechanisms for in vivo evolved resistance was aimed at. These isolates exhibited a 24-48 fold increase in ß-lactamase production. The ß-lactamase produced was found to be biochemically and immunologically identical to the ß-lactamase produced by E. coli K-12. The ampC control region of these six E. coli isolates was DNA-seqenced. The cause of ß-lactamase hyperproduction in five of the clinical E. coli isolates, identical in the DNA segment sequenced, was due to a strong novel ampC promoter displaced 5 bp upstream of the ampC promoter defined in E. coli K-12. The ß-lactamase hyperproduction in the sixth clinical isolate was shown to be caused by two mutations affecting both the promoter and the attenuator in the regulatory region defined by E. coli K- 12. The obtained changes were sufficient to explain the increase in ampC ß- 1 act ama se expression exhibited in these clinical E. coli isolates. Sequence analysis of the ampC control region in Sh. sonnei revealed that it was, with one exception, identical to the one found in the five clinical E. coli ß-lactamase hyperproducers. The only difference was in a position that creates the strong novel ampC promoter in the E. coli hyperproducers. By isolating spontaneous Sh. sonnei mutants with a 40-fold increase in ß-lactamase production carrying the same novel ampC promoter as the clinical E. coli isolates it was concluded that this DNA segment has been transferred in vivo frcm Shigella to E. coli across the species barrier. / <p>Diss. (sammanfattning) Umeå : Umeå universitet, 1983; Härtill 5 uppsatser</p> / digitalisering@umu

Model-based diagnosis compares observations from a system with predictions using a mathematical model to detect and isolate faulty components. Analyzing which faults that can be detected and isolated given the model gives useful information when designing a diagnosis system. This information can be used, for example, to determine which residual generators can be generated or to select a sufficient set of sensors that can be used to detect and isolate the faults. With more information about the system taken into consideration during such an analysis, more accurate estimations can be computed of how good fault detectability and isolability that can be achieved. Model uncertainties and measurement noise are the main reasons for reduced fault detection and isolation performance and can make it difficult to design a diagnosis system that fulfills given performance requirements. By taking information about different uncertainties into consideration early in the development process of a diagnosis system, it is possible to predict how good performance can be achieved by a diagnosis system and avoid bad design choices. This thesis deals with quantitative analysis of fault detectability and isolability performance when taking model uncertainties and measurement noise into consideration. The goal is to analyze fault detectability and isolability performance given a mathematical model of the monitored system before a diagnosis system is developed. A quantitative measure of fault detectability and isolability performance for a given model, called distinguishability, is proposed based on the Kullback-Leibler divergence. The distinguishability measure answers questions like "How difficult is it to isolate a fault fi from another fault fj?. Different properties of the distinguishability measure are analyzed. It is shown for example, that for linear descriptor models with Gaussian noise, distinguishability gives an upper limit for the fault to noise ratio of any linear residual generator. The proposed measure is used for quantitative analysis of a nonlinear mean value model of gas flows in a heavy-duty diesel engine to analyze how fault diagnosability performance varies for different operating points. It is also used to formulate the sensor selection problem, i.e., to find a cheapest set of available sensors that should be used in a system to achieve required fault diagnosability performance. As a case study, quantitative fault diagnosability analysis is used during the design of an engine misfire detection algorithm based on the crankshaft angular velocity measured at the flywheel. Decisions during the development of the misfire detection algorithm are motivated using quantitative analysis of the misfire detectability performance showing, for example, varying detection performance at different operating points and for different cylinders to identify when it is more difficult to detect misfires. This thesis presents a framework for quantitative fault detectability and isolability analysis that is a useful tool during the design of a diagnosis system. The different applications show examples of how quantitate analysis can be applied during a design process either as feedback to an engineer or when formulating different design steps as optimization problems to assure that required performance can be achieved.

The subject of this thesis is the maximization of the information divergence from an exponential family on a finite set, a problem first formulated by Nihat Ay. A special case is the maximization of the mutual information or the multiinformation between different parts of a composite system. My thesis contributes mainly to the mathematical aspects of the optimization problem. A reformulation is found that relates the maximization of the information divergence with the maximization of an entropic quantity, defined on the normal space of the exponential family. This reformulation simplifies calculations in concrete cases and gives theoretical insight about the general problem. A second emphasis of the thesis is on examples that demonstrate how the theoretical results can be applied in particular cases. Third, my thesis contain first results on the characterization of exponential families with a small maximum value of the information divergence.

Diss. (sammanfattning) Uppsala : Uppsala universitet, 2006. / Härtill 5 uppsatser.

Predation by northern pike is believed to have initiated a divergence in whitefish into several different morphs, differing in size, habitat use and growth rate.  The development of a small pelagic zooplankton feeding morph is expected to have large impacts on the zooplankton community. In this study the effect of a changing predation regime on Bosmina, before and after introduction of pike in Valsjön, was investigated.  By looking at the change in carapace length (and indication of the level of predation pressure from fish) and mucro index (an indication of the level of invertebrate predation) of Bosmina remains in lake sediment the changing predation pressure from invertebrates and fish could be investigated. These features proved to be good proxys for the level of defense against fish and invertebrate predation.  However, other species than whitefish, and unknown interactions seems to have affected the zooplankton community. This makes it hard to tell which effect is due to diversification in whitefish and which is not. Also it is not clear that it is pike that has induced the divergence in the whitefish population. Other species like brown trout might also have been involved.

Resumo: A variabilidade genética é um dos fatores mais importantes para o melhoramento de plantas, a partir do qual será conduzido todo o processo seletivo. Essa variabilidade pode ser ampliada através da utilização de cruzamentos múltiplos e melhor explorada sob diferentes métodos de condução das populações segregantes. O objetivo do presente trabalho foi detectar variabilidade através de estimativas de parâmetros genéticos em genótipos derivados do avanço de gerações por três diferentes métodos de condução: Single Seed Descent (SSD), Single Pod Descent (SPD) e Genealógico (Pedigree). O experimento foi conduzido em casa de vegetação climatizada e na área experimental do Departamento de Produção Vegetal da Faculdade de Ciências Agrárias e Veterinárias, Unesp-Jaboticabal. O delineamento utilizado foi o de blocos aumentados, onde foram avaliados 324 genótipos de soja na geração F7 previamente desenvolvidos no Programa de Melhoramento de Soja da FCAV/UNESP, oriundos de cruzamentos biparentais, quádruplos e óctuplos. Foram obtidas estimativas de variâncias, herdabilidades e ganhos genéticos para os três tipos de cruzamentos nos três métodos. Pela análise de divergência foram agrupados os genótipos mais similares para cada método. Os métodos SSD e SPD foram os mais promissores para aumentos de variabilidade nos três tipos de cruzamentos. O método genealógico promoveu as maiores estimativas de herdabilidade e os maiores ganhos genéticos. Os genótipos de cruzamentos quádruplos foram os que mais se agruparam / Abstract: Genetic variability is one of the most important factors for plant breeding, which lead the selective process. This variability can be enlarged by multiple crosses and explored under different breeding methods on segregate populations. Thus, the aim of this work was to detect variability using genetic parameters estimates in genotypes obtained by different methods: Single Seed Descent (SSD), Single Pod Descent (SPD) e Pedigree. The experiment was conducted in a greenhouse, under controlled conditions, and in the experimental field of Crop Production Department at Faculdade de Ciências Agrárias e Veterinárias, Unesp-Jaboticabal. Augmented blocks was used as the experimental design. 324 soybean genotypes in generation F7 from FCAV Soybean Breeding Program, derived from 2-way, 4-way and 8-way crosses, were evaluated. Variance, heritability and genetic gains estimates were obtained for the three types of crosses on three methods. By divergence analysis, most similar genotypes were grouped for each method. SSD and SPD methods were the most promising for variability increases. Pedigree method has promoted the higher estimates for heritability and genetic gains. Genotypes from four-way crosses were highly grouped / Orientadora: Maria Aparecida Pessôa da Cruz Centurion / Coorientador: Marcelo Marchi Costa / Banca: João Carlos de Oliveira / Banca: Ivana Marino Bárbaro / Mestre