Inaug.-Diss.--Strassburg i.E. / Bildungsgang. "... Gelangt hier nur ein teil der arbeit zum abdruck. Die ganze arbeit erscheint gleichzeitig." "Bibliographie": p. [v]-viii.

A common objective in learning a model from data is to recover its network structure, while the model parameters are of minor interest. For example, we may wish to recover regulatory networks from high-throughput data sources. In this paper we examine how Bayesian regularization using a Dirichlet prior over the model parameters affects the learned model structure in a domain with discrete variables. Surprisingly, a weak prior in the sense of smaller equivalent sample size leads to a strong regularization of the model structure (sparse graph) given a sufficiently large data set. In particular, the empty graph is obtained in the limit of a vanishing strength of prior belief. This is diametrically opposite to what one may expect in this limit, namely the complete graph from an (unregularized) maximum likelihood estimate. Since the prior affects the parameters as expected, the prior strength balances a "trade-off" between regularizing the parameters or the structure of the model. We demonstrate the benefits of optimizing this trade-off in the sense of predictive accuracy.

Abstract Orientation: The informal sector serves as an untapped reservoir of skilled individuals practising the motor mechanic trade, who are ready for possible reclamation into the formal sector. Research purpose: The objective of this study was to develop a recognition of prior learning (RPL) strategy to link informal practising motor mechanic artisan training to the formal sector to enhance these artisans’ employability status. Motivation for the study: The current formal sector training initiatives for motor mechanics do not provide for or acknowledge the non-formal learning of the informal sector practising motor mechanics. South African desperately needs a national artisan development programme that includes all the components of artisan growth. Although the national artisan development programme will primarily focus on the development of artisans in the formal sector, the large numbers of persons who are involved in artisan work in the informal sector need to be progressively incorporated into the formal sector process. Research design, approach and method: A qualitative design was used and a purposive snowball sample applied. An exploratory qualitative study was conducted to answer the research question. Semi-structured interviews were applied to solicit data from 16 experts representing the motor mechanic training environment. The data were analysed utilising the ATLAS.ti 7.0 program. Contribution/value-add: This study attempted to conduct ground-breaking research in theory building to improve the employability status of people involved in motor mechanic artisan work in the informal sector. The findings of this study could lead to the development of new theory for SETAs to engage in the training and funding of informal practising motor mechanics. The study conceptualises a focused RPL strategy for motor mechanics that could be systematically applied to integrate the informal and formal sector training for the trade.

This paper discusses characteristics of standard conjugate priors and their induced posteriors in Bayesian inference for von Mises-Fisher distributions, using either the canonical natural exponential family or the more commonly employed polar coordinate parameterizations. We analyze when standard conjugate priors as well as posteriors are proper, and investigate the Jeffreys prior for the von Mises-Fisher family. Finally, we characterize the proper distributions in the standard conjugate family of the (matrixvalued) von Mises-Fisher distributions on Stiefel manifolds.

This research is motivated by an issue frequently encountered in environmental water quality evaluation. Many times, the sample size of water monitoring data is too small to have adequate power. Here, we present a Bayesian power prior approach by incorporating the current data and historical data and/or the data collected at neighboring stations to make stronger statistical inferences on the parameters of interest. The elicitation of power prior distributions is based on the availability of historical data, and is realized by raising the likelihood function of the historical data to a fractional power. The power prior Bayesian analysis has been proven to be a useful class of informative priors in Bayesian inference. In this dissertation, we propose a modified approach to constructing the joint power prior distribution for the parameter of interest and the power parameter. The power parameter, in this modified approach, quantifies the heterogeneity between current and historical data automatically, and hence controls the influence of historical data on the current study in a sensible way. In addition, the modified power prior needs little to ensure its propriety. The properties of the modified power prior and its posterior distribution are examined for the Bernoulli and normal populations. The modified and the original power prior approaches are compared empirically in terms of the mean squared error (MSE) of parameter estimates as well as the behavior of the power parameter. Furthermore, the extension of the modified power prior to multiple historical data sets is discussed, followed by its comparison with the random effects model. Several sets of water quality data are studied in this dissertation to illustrate the implementation of the modified power prior approach with normal and Bernoulli models. Since the power prior method uses information from sources other than current data, it has advantages in terms of power and estimation precision for decisions with small sample sizes, relative to methods that ignore prior information. / Ph. D.

Abstract This research is to explore the high school student potential misconceptions on evolution, based on the two-tier diagnostic test and diagnostic interview. Through a proper teaching design, the researcher has developed an untraditional teaching method. The effects of the untraditional teaching method and the traditional teaching method were compared. With the retest of two-tier diagnostic test, a survey was conducted to evaluate the students¡¦ achievement resulting from the teaching strategy designed by the researcher. The survey can also be consulted and used in the improvement of future teaching activities. This research adopted a Quasi-experimental research method. Data included the analysis of quantity and the description of quality. The research tool is a two-tier diagnostic questionable. The sample groups consist of two classes in the grade-10 and two classes in the grade-12 with 35 students in each class, taught by the researcher. The results of this research indicate that (1) in general , the students are in lack of the structural knowledge of evolution in their prior learning especially¡§the relationship between organism and organism¡¨and the concept of human selection; (2) the comparison of learning results brought about between the untraditional teaching method and traditional teaching method, apparently shows that the experimental group students are far better than the control group students in understanding the connection of evolutional concepts and the abundance of conceptive maps; (3) the difference of student learning process of the two teaching methods , compared by the quiz results on each unit, are not significantly different between the two groups of students; and (4) as far as the teaching of the concept of evolution is concerned, the improved teaching method design is appreciated by the experiment group students and is highly expected by the control group students.

No description available.

Entrepreneurial opportunities are found in literature to be discovered,recognized, and created by entrepreneurs. This thesis aims to explore andexplain the influences upon entrepreneurs in terms of knowledge, and knowledgesources, in the opportunity identification stage. However, even though it isfound in literature that knowledge is a main influencer in the first stage ofthe entrepreneurial process, the approaches to explain the influences onentrepreneurs for entrepreneurial opportunities are not consistent, whichcreates confusion about the sources of knowledge that influence entrepreneurs,in combination with the type of knowledge. In order to further explore andexplain the area, research is done, and cases are formed by interviewingentrepreneurs from eleven companies. The results from the interviews are thencompared, and related back to the literature findings. In the analysis it isfound that sources such as work-experience, education, hobbies, and role modelshelp entrepreneurs to gain knowledge in the industry where he or she havestarted a venture from an opportunity. These sources of knowledge havecontributed to market pull knowledge, and it is also found that there is arelationship between prior knowledge and alertness, which has to do with theability to find useful knowledge.

Research Doctorate - Doctor of Philosophy (PhD) / Interval estimation of the Binomial parameter è, representing the true probability of a success, is a problem of long standing in statistical inference. The landmark work is by Bayes (1763) who applied the uniform prior to derive the Beta posterior that is the normalised Binomial likelihood function. It is not well known that Bayes favoured this ‘noninformative’ prior as a result of considering the observable random variable x as opposed to the unknown parameter è, which is an important difference. In this thesis we develop additional arguments in favour of the uniform prior for estimation of è. We start by describing the frequentist and Bayesian approaches to interval estimation. It is well known that for common continuous models, while different in interpretation, frequentist and Bayesian intervals are often identical, which is directly related to the existence of a pivotal quantity. The Binomial model, and its Poisson sister also, lack a pivotal quantity, despite having sufficient statistics. Lack of a pivotal quantity is the reason why there is no consensus on one particular estimation method, more so than its discreteness: frequentist (unconditional) coverage depends on è. Exact methods guarantee minimum coverage to be at least equal to nominal and approximate methods aim for mean coverage to be close to nominal. We agree with what seems like the majority of frequentists, that exact methods are too conservative in practice, and show additional undesirable properties. This includes more recent ‘short’ exact intervals. We argue that Bayesian intervals based on noninformative priors are preferable to the family of frequentist approximate intervals, some of which are wider than exact intervals for particular data values. A particular property of the interval based on the uniform prior is that its mean coverage is exactly equal to nominal. However, once committed to the Bayesian approach there is no denying that the current preferred choice, by ‘objective’ Bayesians, is the U-shaped Jeffreys prior which results from various methods aimed at finding noninformative priors. The most successful such method seems to be reference analysis which has led to sensible priors in previously unsolved problems, concerning multiparameter models that include ‘nuisance’ parameters. However, we argue that there is a class of models for which the Jeffreys/reference prior may be suboptimal and that in the case of the Binomial distribution the requirement of a uniform prior predictive distribution leads to a more reasonable ‘consensus’ prior.

This thesis investigates the improvements that can be made to Bayesian passive sonar tracking in the context of active-passive sonar data fusion. Performance improvements are achieved by exploiting the prior information available within a typical Bayesian data fusion framework. The algorithms developed are tested against both simulated data and data measured during the SEABAR 07 sea trial. Results show that the proposed approaches achieve improved detection, decreased estimation error, and the ability to track quiet targets in the presence of loud interferers. / text