Time-to-event data, a common occurrence in medical research, is also pertinent in the ecological context, exemplified by leaf desiccation studies using innovative optical vulnerability techniques. Such data can unveil valuable insights into the influence of various factors on the event of interest. Leveraging both spatial and temporal information, spatial survival modeling can unravel the intricate spatiotemporal dynamics governing event occurrences. Existing spatial survival models often assume the availability of the censoring type for censored cases. Various approaches have been employed to address scenarios where a "subset" of cases lacks a known "censoring indicator" (i.e., whether they are right-censored or uncensored). This uncertainty in the subset pertains to missing information regarding the censoring status. However, our study specifically centers on situations where the missing information extends to "all" censored cases, rendering them devoid of a known censoring "type" indicator (i.e., whether they are right-censored or left-censored). The genesis of this challenge emerged from leaf hydraulic data, specifically embolism data, where the observation of embolism events is limited to instances when leaf veins transition from water-filled to air-filled during the observation period. Although it is known that all veins eventually embolize when the entire plant dries up, the critical information of whether a censored leaf vein embolized before or after the observation period is absent. In other words, the censoring type indicator is missing. To address this challenge, we developed a Gibbs sampler for a Bayesian spatial survival model, aiming to recover the missing censoring type indicator. This model incorporates the essential embolism formation mechanism theory, accounting for dynamic patterns observed in the embolism data. The model assumes spatial smoothness between connected leaf veins and incorporates vein thickness information. Our Gibbs sampler effectively infers the missing censoring type indicator, as demonstrated on both simulated and real-world embolism data. In applying our model to real data, we not only confirm patterns aligning with existing phytological literature but also unveil novel insights previously unexplored due to limitations in available statistical tools. Additionally, our results suggest the potential for building hierarchical models with species-level parameters focusing solely on the temporal component. Overall, our study illustrates that the proposed Gibbs sampler for the spatial survival model successfully addresses the challenge of missing censoring type indicators, offering valuable insights into the underlying spatiotemporal dynamics.

In the case of repetitive experiments of a similar type, where the parameters vary randomly from experiment to experiment, the Empirical Bayes method often leads to estimators which have smaller mean squared errors than the classical estimators. Suppose there is an unobservable random variable θ, where θ ~ G(θ), usually called a prior distribution. The Bayes estimator of θ cannot be obtained in general unless G(θ) is known. In the empirical Bayes method we do not assume that G(θ) is known, but the sequence of past estimates is used to estimate θ. This dissertation involves the empirical Bayes estimates of various time series parameters: The autoregressive model, moving average model, mixed autoregressive-moving average, regression with time series errors, regression with unobservable variables, serial correlation, multiple time series and spectral density function. In each case, empirical Bayes estimators are obtained using the asymptotic distributions of the usual estimators. By Monte Carlo simulation the empirical Bayes estimator of first order autoregressive parameter, ρ, was shown to have smaller mean squared errors than the conditional maximum likelihood estimator for 11 past experiences. / Doctor of Philosophy

This dissertation examines the emerging practice of consumer neuroscience and neuromarketing, combined called CNNM. CNNM utilizes tools and technologies to measure brain activity and human behavior coupled with scientific theories for explaining behavior and cognition. Consumer neuroscience is one of the newest areas of application of neuroscience and related techniques, and is of significant social consequence for its possible deployment in the market place to both study and shape consumer behavior. Concerns arise in terms of consumer influence and manipulation, but there are also concerns regarding the actual efficacy and utility of the technologies and the application of behavioral theories. The dissertation's three essays each examine a facet of CNNM. Using historical sources, conference participation, and ethical analyses, the dissertation forms a multi-prong effort at a better understanding of CNNM through the use of science and technology studies (STS) methods. The first essay is an historical review of the usage of technologies to measure brain activity and behavior, parallel to the development of psychological theories created to account for human decisionmaking. This essay presents a new conception of "closure" and "momentum" as envisioned by social construction of technology and technological momentum theories, arriving at a new concept for inclusion called "convergence" which offers a multi-factor explanation for the acceptance and technical implementation of unsettled science. The second essay analyzes four discourses discovered during the review of approximately seventy presentations and interviews given by experts in the field of CNNM. Using and adapting actor-network theory, the essay seeks to describe the creation of expertise and group formation in the field of CNNM researchers. The third essay draws on a variety of ethical analyses to expand understanding of the ethical concerns regarding CNNM. It raises questions that go beyond the actual efficacy of CNNM by applying some of the theories of Michel Foucault relating to the accumulation of power via expertise. This essay also points in the direction for actionable steps at ameliorating some of the ethical concerns involving CNNM. CNNM is a useful technique for understanding consumer behavior and, by extension, human behavior and neuroscience more generally. At the same time, it has been routinely misunderstood and occasionally vilified (for concerns about both efficacy and non-efficacy). This dissertation develops some of the specific historical movements that created the field, surveys and analyzes some of the foremost experts and how they maneuvered in their social network to achieve that status, and identifies novel ethical issues and some solutions to those ethical issues. / Ph. D. / Consumer neuroscience, or neuromarketing, (CNNM) is a new and emerging field which uses different devices to measure brain activity and behavior. For many years, scientists and marketers have been seeking to understand and explain decisions and, more specifically, consumer decisions. It has only been in the most recent decades that technology and scientific theories have been working in a close fashion to help understand human decision and consumer behavior. In three essays, this dissertation uses tools from science and technology studies (STS) to better understand CNNM. In Essay One, I track the parallel history of the technologies to measure brain activity and behavior with scientific theories put forward to explain them. In Essay Two, I analyze the content of presentations given by experts in the field to understand how CNNM expertise is formed. In Essay Three, I explore the ethical concerns and propose some new ways of solving some of the ethical problems (such as power, influence, and expertise.) CNNM is an important social phenomenon because of its possibilities of helping marketers, but it is also important for its part in developing areas of technology and scientific theories. The dissertation represents some new approaches at helping to understand its complexities and consequences.

From cells to societies, cooperation occurs at all levels of biological organization. In vertebrates, the most complex societies occur in cooperative breeders where some group members (helpers) forego reproduction, sacrificing their immediate direct fitness to assist in raising the offspring of others (breeders). Individuals in cooperative breeding societies can gain indirect fitness benefits from passing on shared genes when they help the offspring of close genetic relatives (kin selection), such that cooperation is expected to correlate with genetic relatedness. However, some cooperatively breeding societies include cooperation between nonrelatives. Cooperatively breeding societies range in complexity, from singular (one breeding pair) to plural (two or more breeding pairs). In the majority of singular breeding societies, helpers are relatives of breeders. Thus, kin selection is thought to underlie helping behavior in singular breeding societies. Plural breeding societies, such as in superb starlings (Lamprotornis superbus) inhabiting the East African savanna in central Kenya, involve multiple territory-sharing families raising offspring with helpers who can assist more than one family simultaneously. The superb starling’s complex and dynamic social system, mixed kin structure, relatively long lives, and stable social groups make them an ideal study species for investigating how patterns of individual decision-making have shaped and maintained cooperative societies. My dissertation research focuses on using long-term data on cooperatively breeding superb starlings to explore how temporally variable environments, such as the East African savanna, influence individual decisions across lifetimes, and subsequently how individual behavior shapes the structure and organization of the society. In Chapter 1, I apply a Bayesian approach to the animal model to estimate how genetic versus nongenetic factors influence among individual variation in the social roles: “breeder”, “helper”, and “non-breeder/non-helper”. Non-breeder/non-helper indicates that the individual maintained membership in the social group but did not breed or help during that season. I then estimated heritability and found, as predicted, overall low heritability of traits responsible for each role. This result is consistent with the findings of other studies on the heritability of social behavior, which tends to be low compared to non-social traits, primarily because the social behavior of an individual is highly influenced by interactions with other individuals. In Chapter 2, I show that superb starlings (i) are nepotistic, and (ii) switch between the social roles of “helper” and “breeder” across their lives. This role switching, which unexpectedly includes breeders going back to helping again, is linked to reciprocal helping between pairs of helpers and breeders, independent of genetic relatedness. Reciprocal helping was long thought to be irrelevant for cooperative breeders because most helping is assumed to be unidirectional, from subordinate helpers to dominant breeders, and reciprocal helping is often measured on short timescales. These long-term reciprocal helping relationships among kin and nonkin alike may be important for the persistence of this population because previous research has demonstrated that enhancing group size by immigration from outside groups, while reducing group kin structure, is necessary to prevent group extinction. Finally, the results of Chapter 3 reveal how social and ecological factors shape role switching across individual lifetimes. Overall, my dissertation highlights the remarkable flexibility of superb starling cooperative behavior and the crucial role of mutual direct fitness benefits from reciprocal helping, which may help promote the stability of cooperative group living among nonkin as well as kin group members, contributing to the resilience of this population within a harsh and unpredictable environment.

In 1979 Daniel Kahneman and Amos Tversky created the prospect theory. It became an accepted and appropriate theory in explaining decision making under risk. The prospect theory has been one of the most cited articles in economics and Kahneman received the Nobel Prize in Economic Sciences as a result of the creation and development of the theory. Therefore the prospect theory is considered to be more suitable compared to the previously accepted theory, the expected utility theory. Following the prospect theory, researchers have utilized it to describe individual but also corporate management decision making when faced with risk. In this thesis the authors will focus on the latter. Despite the prospect theory being a well-accepted theory, there have been several critics due to its limitations and Audia and Greve (2006) are one of these critics. Their study suggested that corporations under threat, i.e. small firms with low returns, act risk averse. The findings of Audia and Greve (2006) violate the prospect theory when considering small firms that have below target returns. They tested the theory on an industry that has the characteristics of having relatively high proportions of tangible assets. Audia and Greve (2006) also proposed that a similar conclusion could be drawn if tested on an industry characterized by having a high level of intangible assets. This thesis examines the applicability of the prospect theory in the Swedish automotive industry and staffing and recruitment industry. The characteristics of the two industries are that the automotive industry has a high proportion of tangible assets and the staffing and recruitment industry has a high level of intangibles. The authors test if the prospect theory can be used to describe the decision making of both industries but also test the theory on small and large firms. Following the results of this paper we show that the prospect theory can be applied to the Swedish automotive industry and staffing and recruitment industry, characterized by having high levels of tangible assets and intangible assets respectively. The theory can also be used to explain decision making under risk for small firms within both industries and large firms within the automotive industry. Even though the prospect theory was originally tested on individuals, the conclusion can be drawn that the prospect theory once again prevails as an explanation of the decision making in the management of corporations. It can describe the decision making of firms in the two industries having characteristics of different asset tangibility and for firms of different size.

In my Ph.D. dissertation, I have studied problems arising in various aspects of preferences: preference modeling, preference learning, and preference reasoning, when preferences concern outcomes ranging over combinatorial domains. Preferences is a major research component in artificial intelligence (AI) and decision theory, and is closely related to the social choice theory considered by economists and political scientists. In my dissertation, I have exploited emerging connections between preferences in AI and social choice theory. Most of my research is on qualitative preference representations that extend and combine existing formalisms such as conditional preference nets, lexicographic preference trees, answer-set optimization programs, possibilistic logic, and conditional preference networks; on learning problems that aim at discovering qualitative preference models and predictive preference information from practical data; and on preference reasoning problems centered around qualitative preference optimization and aggregation methods. Applications of my research include recommender systems, decision support tools, multi-agent systems, and Internet trading and marketing platforms.

Thesis (PhD)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: Multi-state models are used in this dissertation to model panel data, also known as longitudinal or cross-sectional time-series data. These are data sets which include units that are observed across two or more points in time. These models have been used extensively in medical studies where the disease states of patients are recorded over time. A theoretical overview of the current multi-state Markov models when applied to panel data is presented and based on this theory, a simulation procedure is developed to generate panel data sets for given Markov models. Through the use of this procedure a simulation study is undertaken to investigate the properties of the standard likelihood approach when fitting Markov models and then to assess its shortcomings. One of the main shortcomings highlighted by the simulation study, is the unstable estimates obtained by the standard likelihood models, especially when fitted to small data sets. A Bayesian approach is introduced to develop multi-state models that can overcome these unstable estimates by incorporating prior knowledge into the modelling process. Two Bayesian techniques are developed and presented, and their properties are assessed through the use of extensive simulation studies. Firstly, Bayesian multi-state models are developed by specifying prior distributions for the transition rates, constructing a likelihood using standard Markov theory and then obtaining the posterior distributions of the transition rates. A selected few priors are used in these models. Secondly, Bayesian multi-state imputation techniques are presented that make use of suitable prior information to impute missing observations in the panel data sets. Once imputed, standard likelihood-based Markov models are fitted to the imputed data sets to estimate the transition rates. Two different Bayesian imputation techniques are presented. The first approach makes use of the Dirichlet distribution and imputes the unknown states at all time points with missing observations. The second approach uses a Dirichlet process to estimate the time at which a transition occurred between two known observations and then a state is imputed at that estimated transition time. The simulation studies show that these Bayesian methods resulted in more stable results, even when small samples are available. / AFRIKAANSE OPSOMMING: Meerstadium-modelle word in hierdie verhandeling gebruik om paneeldata, ook bekend as longitudinale of deursnee tydreeksdata, te modelleer. Hierdie is datastelle wat eenhede insluit wat oor twee of meer punte in tyd waargeneem word. Hierdie tipe modelle word dikwels in mediese studies gebruik indien verskillende stadiums van ’n siekte oor tyd waargeneem word. ’n Teoretiese oorsig van die huidige meerstadium Markov-modelle toegepas op paneeldata word gegee. Gebaseer op hierdie teorie word ’n simulasieprosedure ontwikkel om paneeldatastelle te simuleer vir gegewe Markov-modelle. Hierdie prosedure word dan gebruik in ’n simulasiestudie om die eienskappe van die standaard aanneemlikheidsbenadering tot die pas vanMarkov modelle te ondersoek en dan enige tekortkominge hieruit te beoordeel. Een van die hoof tekortkominge wat uitgewys word deur die simulasiestudie, is die onstabiele beramings wat verkry word indien dit gepas word op veral klein datastelle. ’n Bayes-benadering tot die modellering van meerstadiumpaneeldata word ontwikkel omhierdie onstabiliteit te oorkom deur a priori-inligting in die modelleringsproses te inkorporeer. Twee Bayes-tegnieke word ontwikkel en aangebied, en hulle eienskappe word ondersoek deur ’n omvattende simulasiestudie. Eerstens word Bayes-meerstadium-modelle ontwikkel deur a priori-verdelings vir die oorgangskoerse te spesifiseer en dan die aanneemlikheidsfunksie te konstrueer deur van standaard Markov-teorie gebruik te maak en die a posteriori-verdelings van die oorgangskoerse te bepaal. ’n Gekose aantal a priori-verdelings word gebruik in hierdie modelle. Tweedens word Bayesmeerstadium invul tegnieke voorgestel wat gebruik maak van a priori-inligting om ontbrekende waardes in die paneeldatastelle in te vul of te imputeer. Nadat die waardes ge-imputeer is, word standaard Markov-modelle gepas op die ge-imputeerde datastel om die oorgangskoerse te beraam. Twee verskillende Bayes-meerstadium imputasie tegnieke word bespreek. Die eerste tegniek maak gebruik van ’n Dirichletverdeling om die ontbrekende stadium te imputeer by alle tydspunte met ’n ontbrekende waarneming. Die tweede benadering gebruik ’n Dirichlet-proses om die oorgangstyd tussen twee waarnemings te beraam en dan die ontbrekende stadium te imputeer op daardie beraamde oorgangstyd. Die simulasiestudies toon dat die Bayes-metodes resultate oplewer wat meer stabiel is, selfs wanneer klein datastelle beskikbaar is.

The overarching purpose of the studies presented in this report is the exploration of the uses of information theory and Bayesian inference applied to neural codes. Two approaches were taken: Starting from first principles, a coding mechanism is proposed, the results are compared to a biological neural code. Secondly, tools from information theory are used to measure the information contained in a biological neural code. Chapter 3: The REC model proposed by Harpur and Prager codes inputs into a sparse, factorial representation, maintaining reconstruction accuracy. Here I propose a modification of the REC model to determine the optimal network dimensionality. The resulting code for unfiltered natural images is accurate, highly sparse and a large fraction of the code elements show localized features. Furthermore, I propose an activation algorithm for the network that is faster and more accurate than a gradient descent based activation method. Moreover, it is demonstrated that asymmetric noise promotes sparseness. Chapter 4: A fast, exact alternative to Bayesian classification is introduced. Computational time is quadratic in both the number of observed data points and the number of degrees of freedom of the underlying model. As an example application, responses of single neurons from high-level visual cortex (area STSa) to rapid sequences of complex visual stimuli are analyzed. Chapter 5: I present an exact Bayesian treatment of a simple, yet sufficiently general probability distribution model. The model complexity, exact values of the expectations of entropies and their variances can be computed with polynomial effort given the data. The expectation of the mutual information becomes thus available, too, and a strict upper bound on its variance. The resulting algorithm is first tested on artificial data. To that end, an information theoretic similarity measure is derived. Second, the algorithm is demonstrated to be useful in neuroscience by studying the information content of the neural responses analyzed in the previous chapter. It is shown that the information throughput of STS neurons is maximized for stimulus durations of approx. 60ms.

Publicly available datasets in health science are often large and observational, in contrast to experimental datasets where a small number of data are collected in controlled experiments. Variables' causal relationships in the observational dataset are yet to be determined. However, there is a significant interest in health science to discover and analyze causal relationships from health data since identified causal relationships will greatly facilitate medical professionals to prevent diseases or to mitigate the negative effects of the disease. Recent advances in Computer Science, particularly in Bayesian networks, has initiated a renewed interest for causality research. Causal relationships can be possibly discovered through learning the network structures from data. However, the number of candidate graphs grows in a more than exponential rate with the increase of variables. Exact learning for obtaining the optimal structure is thus computationally infeasible in practice. As a result, heuristic approaches are imperative to alleviate the difficulty of computations. This research provides effective and efficient learning tools for local causal discoveries and novel methods of learning causal structures with a combination of background knowledge. Specifically in the direction of constraint based structural learning, polynomial-time algorithms for constructing causal structures are designed with first-order conditional independence. Algorithms of efficiently discovering non-causal factors are developed and proved. In addition, when the background knowledge is partially known, methods of graph decomposition are provided so as to reduce the number of conditioned variables. Experiments on both synthetic data and real epidemiological data indicate the provided methods are applicable to large-scale datasets and scalable for causal analysis in health data. Followed by the research methods and experiments, this dissertation gives thoughtful discussions on the reliability of causal discoveries computational health science research, complexity, and implications in health science research.

O principal objetivo do estudo foi utilizar informações de ocorrência do Traumatismo Crânio Encefálico (TCE) que possam inferir/gerar descobertas associadas ao risco de gravidade do paciente, bem como auxiliar na tomada de decisão médica ao definir o melhor prognóstico, indicando quais as possíveis medidas que podem ser escolhidas para a gravidade na lesão sofrida pela vítima. Inicialmente, foram analisadas as estatísticas descritivas dos dados dos pacientes de TCE de um hospital do interior de São Paulo. Participaram desse estudo 50 pacientes. Os resultados mostraram que a maior frequência do trauma é por acidentes de trânsito (62%), seguidos de acidentes por queda (24%). Traumas em pacientes do sexo masculino (88%) são muito mais frequentes do que em pacientes do sexo feminino. Para modelagem, transformou-se a variável resposta \"Abbreviated Injury Scale (AIS)\" em dicotômica, considerando 0 (zero) aos pacientes fora de risco e 1 (um) aos que apresentaram algum tipo de risco. Em seguida, técnicas de aprendizado estatístico foram utilizadas de modo a comparar o desempenho dos classificadores Regressão Logística sendo um caso do Generalized Linear Model (GLM), Random Forest (RF), Support Vector Machine (SVM) e redes probabilísticas Naïve Bayes (NB). O modelo com melhor desempenho (RF) combinou os índices Accuracy (ACC) , Area Under ROC Curve (AUC) , Sensitivity (SEN), Specificity (SPE) e Matthews Correlation Coefficient (MCC), que apresentaram os resultados mais favoráveis no quesito de apoio no auxílio da tomada de decisão médica, possibilitando escolher o estudo clínico mais adequado das vítimas traumatizadas ao considerar o risco de vida do indivíduo. Conforme o modelo selecionado foi possível gerar um ranking para estimar a probabilidade de risco de vida do paciente. Em seguida foi realizado uma comparação de desempenho entre o modelo RF (novo classificador) e os índices Revisited Trauma Score (RTS), Injury Severity Score (ISS) , Índice de Barthel (IB) referente à classificação de risco dos pacientes. / The main objective of this study was to consider the information related to the occurrence of traumatic brain injury (TBI) that can infer new results associated with the patients risk of severity as well as assisting in the medical decision in order to find the best prognosis; this can lead to indicate possible measures that can be chosen for severity in the injury suffered by the victim. Initially, we have presented descriptive statistics from the patients with TBI from a hospital located in the heartland of São Paulo. Fifty patients were recruited for this study. Descriptive analyzes showed that the highest frequency of trauma is due to traffic accidents (62 %) followed by crashes per accident (24 %). The causes related to trauma occur much more often in male patients (88 %) than in female patients. To order model, the response variable Abbreviated Injury Scale (AIS) was considered as dichotomous, where 0 (zero) was to out-of-risk patients and 1 (one) to those who presented some type of risk. Further, statistical learning techniques were used in order to compare the performance of the Logistic Regression as a Generalized Linear Model (GLM), Random Forest (RF), Support Vector Machine (SVM) and Naive Bayes (NB) model. The best performing (RF) model combined the Accuracy (ACC) , Area Under ROC Curve (AUC) , Sensitivity (SEN), Specificity (SPE) e Matthews Correlation Coefficient (MCC), which presented the most favorable results in terms of support in medical decision, making it possible to choose the most appropriate clinical study of traumatized victims based on the individual life risk. According to the selected model it was possible to generate a rank to estimate the probability of life risk of the patient. Then a performance comparison was performed between the RF model (proposed classifier) and the Revisited Trauma Score (RTS), Injury Severity Score (ISS), Barthel index (IB) referring to the risk classification of patients.