Disease maps are geographical maps that display local estimates of disease risk. When the disease is rare, crude risk estimates can be highly variable, leading to extreme estimates in areas with low population density. Bayesian hierarchical models are commonly used to stabilize the disease map, making them more easily interpretable. By exploiting assumptions about the correlation structure in space and time, the statistical model stabilizes the map by shrinking unstable, extreme risk estimates to the risks in surrounding areas (local spatial smoothing) or to the risks at contiguous time points (temporal smoothing). Extreme estimates that are based on smaller populations are subject to a greater degree of shrinkage, particularly when the risks in adjacent areas or at contiguous time points do not support the extreme value and are more stable themselves. / A common goal in disease mapping studies is to identify areas of elevated risk. The objective of this thesis is to compare the accuracy of several fully Bayesian hierarchical models in discriminating between high-risk and background-risk areas. These models differ according to the various spatial, temporal and space-time interaction terms that are included in the model, which can greatly affect the smoothing of the risk estimates. This was accomplished with simulations based on the cervical cancer rate of Kentucky and at-risk person-years of the state of Kentucky's 120 counties from 1995 to 2002. High-risk areas were 'planted' in the generated maps that otherwise had background relative risks of one. The various disease mapping models were applied and their accuracy in correctly identifying high- and background-risk areas was compared by means of Receiver Operating Characteristic curve methodology. Using data on Multiple Sclerosis (MS) on the island of Sardinia, Italy we apply the more successful models to identify areas of elevated MS risk.

Determining species of individual trees is important for forest management. In this thesis we investigate if it is possible to discriminate between Norway spruce, Scots pine and deciduous trees from airborne laser scanning data by using unique probability density functions estimated for each specie. We estimate the probability density functions in three different ways: by fitting a beta distribution, histogram density estimation and kernel density estimation. All these methods classifies single laser returns (and not segments of laser returns). The resulting classification is compared with a reference method based on features extracted from airborne laser scanning data.We measure how well a method performs by using the overall accuracy, that is the proportion of correctly predicted trees. The highest overall accuracy obtained by the methods we developed in this thesis is obtained by using histogram-density estimation where an overall accuracy of 83.4 percent is achieved. This result can be compared with the best result from the reference method that produced an overall accuracy of 84.1 percent. The fact that we achieve a high level of correctly classified trees indicates that it is possible to use these types of methods for identification of tree species. / Att kunna artbestämma enskilda träd är viktigt inom skogsbruket. I denna uppsats undersöker vi om det är möjligt att skilja mellan gran, tall och lövträd med data från en flygburen laserskanner genom att skatta en unik täthetsfunktion för varje trädslag. Täthetsfunktionerna skattas på tre olika sätt: genom att anpassa en beta-fördelning, skatta täthetsfunktionen med histogram samt skatta täthetsfunktionen med en kernel täthetsskattning. Alla dessa metoder klassificerar varje enskild laserretur (och inte segment av laserreturer). Resultaten från vår klassificering jämförs sedan med en referensmetod som bygger på särdrag från laserskanner data. Vi mäter hur väl metoderna presterar genom att jämföra den totala precisionen, vilket är andelen korrektklassificerade träd. Den högsta totala precisionen för de framtagna metoderna i denna uppsats erhölls med metoden som bygger på täthetsskattning med histogram. Precisionen för denna metod var 83,4 procent rättklassicerade träd. Detta kan jämföras med en rättklassificering på 84,1 procent vilket är det bästa resultatet för referensmetoderna. Att vi erhåller en så pass hög grad av rättklassificerade träd tyder på att de metoder som vi använder oss av är användbara för trädslagsklassificering.

In the present paper we consider Bayesian estimation of a finite mixture of models with random effects which is also known as the heterogeneity model. First, we discuss the properties of various MCMC samplers that are obtained from full conditional Gibbs sampling by grouping and collapsing. Whereas full conditional Gibbs sampling turns out to be sensitive to the parameterization chosen for the mean structure of the model, the alternative sampler is robust in this respect. However, the logical extension of the approach to the sampling of the group variances does not further increase the efficiency of the sampler. Second, we deal with the identifiability problem due to the arbitrary labeling within the model. Finally, a case study involving metric Conjoint analysis serves as a practical illustration. (author's abstract) / Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

El objetivo general de la presente tesis fue determinar el grado en el cual los parásitos de tres especies de peces de ambientes marinos de salinidad variable podían utilizarse como indicadores de alteraciones del medio ambiente e indicadores de biodiversidad. Los objetivos específicos fueron: 1. Identificar los metazoos parásitos de los peces que se utilizaron como modelos de hospedador (Mugil liza Valenciennes, 1836, Micropogonias furnieri Desmarest, 1823 y Jenynsia multidentata Günther, 1866), tanto en sus formas larvales como adultas realizando la descripción en aquellos casos en que fuera necesario. 2. Describir la población de cada parásito y la comunidad parasitaria de cada especie hospedadora evaluando la heterogeneidad espacial y determinar si existían variaciones en los peces provenientes de los diferentes ambientes estudiados y entre tallas. 3. Evaluar, en base a los resultados (ya sea a través del conocimiento de cada helminto en particular o de la estructura comunitaria de helmintos en cada especie hospedadora) la posibilidad del uso de los parásitos como indicadores de distintos niveles de polución ambiental y/o de biodiversidad en los ambientes comparados. Los sitios de muestreo elegidos fueron el Canal Aliviador del Río Salado y Tapera de López/Río Ajo que se encuentran localizados en la región norte y sur de la Bahía de Samborombón respectivamente y sometidos a diferentes condiciones ambientales y riesgos de contaminación. El tercer sitio fue el situado en el estuario de Bahía Blanca el cual tendría condiciones de contaminación más severas. / The general aim of this thesis was to determine the degree in which fish parasites from variable salinity marine environments, can be used as indicators of environmental changes and biodiversity. The specific objectives were: • To identify the metazoan parasites of fish that were used as models of host (Mugil liza Valenciennes, 1836, Micropogonias furnieri Desmarest, 1823 y Jenynsia multidentata Günther, 1866), both larval and adult forms performing its description in cases where necessary. • To describe the population of each community parasite and host species parasitic in evaluating the spatial and temporal heterogeneity and assess whether there are variations in fish from the different environments studied and between sizes. • To assess, based on the results (either through knowledge of each particular helminth or helminth community structure in each host species) the possibility of the use of parasites as indicators of environmental pollution levels and / or biodiversity in the environments compared. The sampling sites chosen were the Salado River Relief Channel and Tapera Lopez/Ajo River that are located in the northern and southern Samborombón Bay respectively and subjected to different environmental conditions and pollution risks. A third site located on the estuary of Bahia Blanca (B.Blanca) which would most severe pollution conditions.

ABSTRACT Much is known about the process of sponsorship selection with respect to the key personnel involved in the buying decision and also about the strategic objectives for sponsorship. However, few investigations have focused on how sponsors assess the relative value of different sponsorship activities. This research project examined sponsorship decision-making with reference to the way managers discuss, think, and act when evaluating a sponsorship property for the first time. It focuses in particular on understanding how sponsors make decisions when selecting a new activity; how perceptions of risk influence their choice behaviours; the relative value they attribute to different sponsorship features; and how individual factors influence their choice of sponsorship domain. This research program considered these issues from three dimensions (1) linguistically (i.e. how firms publicly describe and explain their sponsorship selection procedures to others); (2) cognitively (i.e. how sponsorship experts describe and rationalise the decision process); and (3) conatively (i.e. how sponsorship managers report they behave when making sponsorship selection decisions). First, Study 1 explored the linguistic dimension of sponsorship selection through a content analysis of the sponsorship policies and guidelines of 298 global, national and local firms. The content analysis of these documents was conducted using Leximancer text analysis software. The analysis revealed six attributes were particularly important. These were the cost of sponsorship rights fees; the capacity of the sponsorship to achieve brand marketing objectives; the opportunities for brand exposure; the sharing of values between partners; the type/domain of the sponsorship activity; and its geographic reach. Firms avoided activities likely to damage their corporate or brand image by alienating sections of the community or by violating social norms. Next, Study 2 explored the cognitive dimension of sponsorship through a series of in-depth interviews with 16 sponsors and 20 properties. Interviews revealed that while practitioners supported the importance of attributes similar to those identified in Study 1, they placed more emphasis on the duration of the sponsorship agreement, the partner’s reputation and sponsorship management ability, and on the level of involvement, and less emphasis on shared values and geographic reach. Risk assessment was implicit in their due diligence practices. Risk mitigation strategies included risk avoidance, risk reduction, risk retention, and risk transfer. Study 3 examined the conative dimension of the sponsorship selection process using a full-profile choice-based conjoint (CBC) experiment completed by 196 sponsorship managers. The respondents evaluated 17 sets of fully-randomised fictitious sponsorship proposals constructed using the attributes identified in the previous two studies. Hierarchical Bayes (HB) analysis showed that the degree of fit with brand objectives, the duration of the sponsorship, and the perceived quality of the partner relationship exerted the strongest influence on sponsor preferences. Specifically, sponsors placed the highest value on sponsorships that offered a very high fit with their brand objectives, a one-year agreement, a good partner relationship, were cause-related, had a State-wide reach, involved a title sponsorship, a combination of cash and in-kind payment, and offered print media exposure. Finally, to examine the influence of individual factors (i.e. gender, the level of decision-making authority, and experience in decision-making) on the choice of sponsorship domain (i.e. sport sponsorship, arts sponsorship, cause-related sponsorship, and celebrity endorsement), three sponsorship simulations were conducted as part of Study 3 using Share of Preference modelling. The results showed that cause-related sponsorship was the most strongly preferred domain in each of the three models, whereas celebrity endorsement was the least preferred. While female managers were indifferent to arts or sport sponsorship, male managers showed a strong preference for sport sponsorship over arts sponsorship. Managers were less interested in sport sponsorship than more senior executives. The preferences of managers with the least experience were consistent with those of highly-experienced sponsors. However, managers with 11-15 years experience showed much less interest in sport sponsorship than others. Conceptually, this program of research allowed for the development of a decision-making model that provides the basis for future investigations of sponsorship value. For the practitioner, the results of this research support previous findings about the significance of sponsorship activities having a good fit with the sponsor’s brand objectives. As well, properties with a good reputation for building high-quality sponsorship relationships will find favour with new sponsors.

Zugl.: Karlsruhe, Universiẗat, Diss., 2007.

Thesis (Ph. D.)--University of Washington, 2007. / Vita. Includes bibliographical references (p. 177-191).

München, Techn. Univ., Diss., 2006

Zugl.: Diss.

Zugl.: Bern, Univ., Diss., 2008