Biclustering is a technique for clustering rows and columns of a data matrix simultaneously. Over the past few years, we have seen its applications in biology-related fields, as well as in many data mining projects. As opposed to classical clustering methods, biclustering groups objects that are similar only on a subset of variables. Many biclustering algorithms on continuous data have emerged over the last decade. In this dissertation, we will focus on two Bayesian biclustering algorithms we developed for discrete data, more specifically categorical data and ordinal data. / Statistics

Der technologische Fortschritt ermöglicht es heute, die moleculare Konfiguration einzelner Zellen oder ganzer Gewebeproben zu untersuchen. Solche in großen Mengen produzierten hochdimensionalen Omics-Daten aus der Molekularbiologie lassen sich zu immer niedrigeren Kosten erzeugen und werden so immer häufiger auch in klinischen Fragestellungen eingesetzt. Personalisierte Diagnose oder auch die Vorhersage eines Behandlungserfolges auf der Basis solcher Hochdurchsatzdaten stellen eine moderne Anwendung von Techniken aus dem maschinellen Lernen dar. In der Praxis werden klinische Parameter, wie etwa der Gesundheitszustand oder die Nebenwirkungen einer Therapie, häufig auf einer ordinalen Skala erhoben (beispielsweise gut, normal, schlecht). Es ist verbreitet, Klassifikationsproblme mit ordinal skaliertem Endpunkt wie generelle Mehrklassenproblme zu behandeln und somit die Information, die in der Ordnung zwischen den Klassen enthalten ist, zu ignorieren. Allerdings kann das Vernachlässigen dieser Information zu einer verminderten Klassifikationsgüte führen oder sogar eine ungünstige ungeordnete Klassifikation erzeugen. Klassische Ansätze, einen ordinal skalierten Endpunkt direkt zu modellieren, wie beispielsweise mit einem kumulativen Linkmodell, lassen sich typischerweise nicht auf hochdimensionale Daten anwenden. Wir präsentieren in dieser Arbeit hierarchical twoing (hi2) als einen Algorithmus für die Klassifikation hochdimensionler Daten in ordinal Skalierte Kategorien. hi2 nutzt die Mächtigkeit der sehr gut verstandenen binären Klassifikation, um auch in ordinale Kategorien zu klassifizieren. Eine Opensource-Implementierung von hi2 ist online verfügbar. In einer Vergleichsstudie zur Klassifikation von echten wie von simulierten Daten mit ordinalem Endpunkt produzieren etablierte Methoden, die speziell für geordnete Kategorien entworfen wurden, nicht generell bessere Ergebnisse als state-of-the-art nicht-ordinale Klassifikatoren. Die Fähigkeit eines Algorithmus, mit hochdimensionalen Daten umzugehen, dominiert die Klassifikationsleisting. Wir zeigen, dass unser Algorithmus hi2 konsistent gute Ergebnisse erzielt und in vielen Fällen besser abschneidet als die anderen Methoden.

Den här uppsatsen är en deskriptiv tvärsnittsstudie som analyserar kommunalpolitiker och väljare 2012 i Sverige. Syftet var att undersöka om det fanns en skillnad mellan kommunpolitiker och väljare i deras inställning till förslaget om att ta emot färre flyktingar i Sverige. Vi har även estimerat hur mycket av skillnaden som kan förklaras utav bristande social representation. För att estimera detta har vi använt kumulativ ordinal regression där vi konstruerade olika modeller utifrån antagandet om proportionella odds.  Slutsatsen är att det rådde en påtaglig skillnad mellan kommunpolitiker och väljare, där väljare tenderade att tycka att förslaget var bättre än politikerna. Bristande social representation kan förklara skillnaden mellan politiker och väljare endast marginellt. Vi undersökte även hur det skiljde sig mellan kommunpolitiker och dess sympatisörer i partier som även fanns representerade i riksdagen. Slutsatserna av analysen är att samma mönster finns inom alla partier förutom Sverigedemokraterna, som tvärtom har kommunpolitiker som tycker förslaget är bättre än deras väljare. Storleken på skillnaden varierar mellan olika partier och dess väljare.

Master of Science / Department of Statistics / Thomas M. Loughin / Traditionally, major-league scouts have evaluated young “position players,” those who are not pitchers, using the “Five Tools”: hitting for average, hitting for power, running, throwing, and fielding. However, “sabermetricians,” those who study the science of baseball, e.g. Bill James, have been trying to evaluate position players using quantifiable measures of performance. In this study, a factor analysis was used to determine underlying characteristics of minor-league hitters. The underlying factors were determined to be slugging ability, lead-off hitting ability, “patience” at the plate, and pure-hitting ability. Additionally, an ordinal response was created from the number of at-bats and on-base plus slugging percentage in the majors during the 2002-05 seasons. The underlying characteristics along with other variables such as a player’s age, position, and level in the minors are used in a cumulative logit logistic regression model to predict a player’s probability of notable success in the majors. The model is built upon data from the 2002 minor-league season and data from the 2002, 2003, 2004, and 2005 major-league seasons.

Harvesting woody biomass for biofuel has become an important research topic. In Mississippi, feasibility of utilizing woody biomass for bioenergy lies in the willingness to harvest by non-industrial private forest (NIPF) landowners, who control 71% of forestlands. A mail survey of Mississippi NIPF landowners elicited preferences concerning utilizing logging residues for bioenergy. When presented with hypothetical situations that compared bioenergy utilization attributes along with those of standard harvesting practices, more landowners preferred the bioenergy scenarios, even when more money was offered for standard harvesting. Older landowners with larger landholdings were less likely to prefer bioenergy scenarios. Higher educated landowners who were financially motivated, concerned with climate change, and considered habitat management an important goal were more likely to prefer bioenergy scenarios over standard harvesting. Available markets for logging residues could increase NIPF harvest rates based solely on the different harvesting attributes, which should increase availability of feedstocks for producers.

The research examines the effect of commuting on stress for both motorized and non-motorized commuters and understanding how they cope with it. Understanding this effect can be helpful for decision-makers in the economy, transportation planning, and demographics studies to promote a safe and peaceful experience of travel for all the commuters in the community by designing better transportation systems and developing infrastructure of alternative modes like walking. Moreover, understanding the emotional states of individuals during their journeys and how they navigate and manage the commuting stress feeling, can be beneficial for decision-makers to enhance commuting experiences and feelings. To this end, a bivariate ordinal model was adopted, allowing for an analysis of stress factors and their interactions with key exploratory variables, including income, age, and choice of transportation mode. Interestingly, the results obtained from the context of Santiago, Chile, a region characterized by a predominance of middle and low-income populations according to the research findings, revealed intriguing patterns. The study found that commuting stress influences people in different ways regarding their age. Moreover, commuting stress at higher levels decreases at elevated age levels. This trend remains steady as commuters gain higher economic status and have access to alternative modes of transportation beyond public means. Policymakers and transportation planners should consider the complex interplay of the following clusters according to the result of this research to improve commuting experiences. The first encompasses factors such as income status, choice among different modes of transportation, and age. The second pertains to commuting stress and the importance of stress from commuters' viewpoint. A salient example of the consequence of this interplay, is evident in the research, where normalization a coping strategy implying eliminating some aspects of travel, is employed, showcasing both potential advantages and drawbacks. The findings suggest that promoting active travel options could contribute to a happier commuting experience, emphasizing the importance of understanding coping mechanisms across different commuter groups for the design of effective policies. The implications of these findings extend to the domain of transportation system planning and urban development. By shedding light on the challenges caused by commuting stress and highlighting effective coping mechanisms, this research holds the potential to understand how people deal with commuting stress during their regular trips. Furthermore, the gained insights can inform urban planning initiatives and facilitate the commuting experience by considering commuters' experiences and the associated factors. Ultimately, the integration of these insights into policies and practices has the capacity to cultivate sustainable and resilient communities, which thrive even when facing the inevitable stresses associated with daily commuting. This research makes a two-fold contribution. First, it compiles an extensive array of data including socio-demographics, health metrics, feelings and emotions, built environment, and work commute-related details, all presented in a comprehensive and reproducible data package format. Subsequently, the study delves into the commuting stress analysis and identifies the various coping strategies employed by commuters. The data used for the analysis have been derived from the demographics and health information sections of the dataset. Serving as a reproducible data package, it provides a robust foundation for future research endeavours. Future researchers can have access to the data set as an open source data set allowing them to understand the representativeness of this data package and enable them to replicate various stages where needed. / Thesis / Master of Science (MSc) / Nowadays commuting as a daily travel mostly between work and home is considered as an inevitable part of modern lifestyle. This experience has been indicated to be a source of stress and anxiety as numerous studies have already revealed. Understanding commuting patterns and travel behaviour is important for analyzing stress-related issues, consequences and coping strategies. As @koslowsky2013commuting have mentioned, this is also beneficial to have a perception of commuting patterns, modes of transportation, road congestion and so on for commuting network planning from scratch. Using the relevant stress commuting variables such as experienced stress and assigned importance to this stress can help to this end. This research aimed at providing a comprehensive and reproducible data package of travel behaviour and other aspects of the urban commuting experience of respondents in Santiago, Chile. Each component of this data package serves different aspects for future research such as using demographic information in travel demand modelling, health-related information for improving health, well-being and safety in transportation planning, reasons and planning decisions information for origin-destination modelling, and so on. The research also has been focused on an integrated list of variables chosen from the demographic and health information sections of the data package. This list helps to identify how commuters interact with experiencing stress during their travels. This research also contributes to addressing commuting stress by identifying relevant variables, then figuring out the affected groups and analyzing their coping strategies.

No description available.

Explains properties of mathematical sets, algebra of sets, and set order types.

Yes / The assessment of image quality in medical imaging often requires observers to rate images for some metric or detectability task. These subjective results are used in optimization, radiation dose reduction or system comparison studies and may be compared to objective measures from a computer vision algorithm performing the same task. One popular scoring approach is to use a Likert scale, then assign consecutive numbers to the categories. The mean of these response values is then taken and used for comparison with the objective or second subjective response. Agreement is often assessed using correlation coefficients. We highlight a number of weaknesses in this common approach, including inappropriate analyses of ordinal data and the inability to properly account for correlations caused by repeated images or observers. We suggest alternative data collection and analysis techniques such as amendments to the scale and multilevel proportional odds models. We detail the suitability of each approach depending upon the data structure and demonstrate each method using a medical imaging example. Whilst others have raised some of these issues, we evaluated the entire study from data collection to analysis, suggested sources for software and further reading, and provided a checklist plus flowchart for use with any ordinal data. We hope that raised awareness of the limitations of the current approaches will encourage greater method consideration and the utilization of a more appropriate analysis. More accurate comparisons between measures in medical imaging will lead to a more robust contribution to the imaging literature and ultimately improved patient care. / EU-funded PANORAMA project, funded by grants from Belgium, Italy, France, Netherlands, UK and the ENIAC Joint Undertaking.

För alpina skidåkare mäter man prestationer i så kallad FIS-ranking. Vi undersöker några metoder för hur man kan analysera data där responsen består av ranger som dessa. Vid situationer då responsdata utgörs av urval av ranger finns ingen självklar analysmetod. Det vi undersöker är skillnaderna vid användandet av olika regressionsanpassningar så som linjär, logistisk och ordinal logistisk regression för att analysera data av denna typ. Vidare används bootstrap för att bilda konfidensintervall. Det visar sig att för våra datamaterial ger metoderna liknande resultat när det gäller att hitta betydelsefulla förklarande variabler. Man kan därmed utgående från denna undersökning, inte se några skäl till varför man ska använda de mer avancerade modellerna. / Alpine skiers measure their performance in FIS ranking. We will investigate some methods on how to analyze data where response data is based on ranks like this. In situations where response data is based on ranks there is no obvious method of analysis. Here, we examine differences in the use of linear, logistic and ordinal logistic regression to analyze data of this type. Bootstrap is used to make confidence intervals. For our data these methods give similar results when it comes to finding important explanatory variables. Based on this survey we cannot see any reason why one should use the more advanced models.