Bayesian synthetic likelihood

Having the ability to work with complex models can be highly beneficial, but the computational cost of doing so is often large. Complex models often have intractable likelihoods, so methods that directly use the likelihood function are infeasible. In these situations, the benefits of working with likelihood-free methods become apparent. Likelihood-free methods, such as parametric Bayesian indirect likelihood that uses the likelihood of an alternative parametric auxiliary model, have been explored throughout the literature as a good alternative when the model of interest is complex. One of these methods is called the synthetic likelihood (SL), which assumes a multivariate normal approximation to the likelihood of a summary statistic of interest. This paper explores the accuracy and computational efficiency of the Bayesian version of the synthetic likelihood (BSL) approach in comparison to a competitor known as approximate Bayesian computation (ABC) and its sensitivity to its tuning parameters and assumptions. We relate BSL to pseudo-marginal methods and propose to use an alternative SL that uses an unbiased estimator of the exact working normal likelihood when the summary statistic has a multivariate normal distribution. Several applications of varying complexity are considered to illustrate the findings of this paper.

Bayesian fisheries stock assessment: integrating and updating knowledge

In this thesis the use of the Bayesian approach to statistical inference in fisheries stock assessment is studied. The work was conducted in collaboration of the Finnish Game and Fisheries Research Institute by using the problem of monitoring and prediction of the juvenile salmon population in the River Tornionjoki as an example application. The River Tornionjoki is the largest salmon river flowing into the Baltic Sea. This thesis tackles the issues of model formulation and model checking as well as computational problems related to Bayesian modelling in the context of fisheries stock assessment. Each article of the thesis provides a novel method either for extracting information from data obtained via a particular type of sampling system or for integrating the information about the fish stock from multiple sources in terms of a population dynamics model. Mark-recapture and removal sampling schemes and a random catch sampling method are covered for the estimation of the population size. In addition, a method for estimating the stock composition of a salmon catch based on DNA samples is also presented. For most of the articles, Markov chain Monte Carlo (MCMC) simulation has been used as a tool to approximate the posterior distribution. Problems arising from the sampling method are also briefly discussed and potential solutions for these problems are proposed. Special emphasis in the discussion is given to the philosophical foundation of the Bayesian approach in the context of fisheries stock assessment. It is argued that the role of subjective prior knowledge needed in practically all parts of a Bayesian model should be recognized and consequently fully utilised in the process of model formulation.

Discovering hidden structures in molecular data using a Bayesian partition model approach

Advancements in the analysis techniques have led to a rapid accumulation of biological data in databases. Such data often are in the form of sequences of observations, examples including DNA sequences and amino acid sequences of proteins. The scale and quality of the data give promises of answering various biologically relevant questions in more detail than what has been possible before. For example, one may wish to identify areas in an amino acid sequence, which are important for the function of the corresponding protein, or investigate how characteristics on the level of DNA sequence affect the adaptation of a bacterial species to its environment. Many of the interesting questions are intimately associated with the understanding of the evolutionary relationships among the items under consideration. The aim of this work is to develop novel statistical models and computational techniques to meet with the challenge of deriving meaning from the increasing amounts of data. Our main concern is on modeling the evolutionary relationships based on the observed molecular data. We operate within a Bayesian statistical framework, which allows a probabilistic quantification of the uncertainties related to a particular solution. As the basis of our modeling approach we utilize a partition model, which is used to describe the structure of data by appropriately dividing the data items into clusters of related items. Generalizations and modifications of the partition model are developed and applied to various problems. Large-scale data sets provide also a computational challenge. The models used to describe the data must be realistic enough to capture the essential features of the current modeling task but, at the same time, simple enough to make it possible to carry out the inference in practice. The partition model fulfills these two requirements. The problem-specific features can be taken into account by modifying the prior probability distributions of the model parameters. The computational efficiency stems from the ability to integrate out the parameters of the partition model analytically, which enables the use of efficient stochastic search algorithms.

Diagnostic Molecular Markers for Phosphine Resistance in U.S. Populations of Tribolium castaneum and Rhyzopertha dominica

Stored product beetles that are resistant to the fumigant pesticide phosphine (hydrogen phosphide) gas have been reported for more than 40 years in many places worldwide. Traditionally, determination of phosphine resistance in stored product beetles is based on a discriminating dose bioassay that can take up to two weeks to evaluate. We developed a diagnostic cleaved amplified polymorphic sequence method, CAPS, to detect individuals with alleles for strong resistance to phosphine in populations of the red flour beetle, Tribolium castaneum, and the lesser grain borer, Rhyzopertha dominica, according to a single nucleotide mutation in the dihydrolipoamide dehydrogenase (DLD) gene. We initially isolated and sequenced the DLD genes from susceptible and strongly resistant populations of both species. The corresponding amino acid sequences were then deduced. A single amino acid mutation in DLD in populations of T.castaneum and R.dominica with strong resistance was identified as P45S in T.castaneum and P49S in R.dominica, both collected from northern Oklahoma, USA. PCR products containing these mutations were digested by the restriction enzymes MboI and BstNI, which revealed presence or absence, respectively of the resistant (R) allele and allowed inference of genotypes with that allele. Seven populations of T.castaneum from Kansas were subjected to discriminating dose bioassays for the weak and strong resistance phenotypes. Application of CAPS to these seven populations confirmed the R allele was in high frequency in the strongly resistant populations, and was absent or at a lower frequency in populations with weak resistance, which suggests that these populations with a low frequency of the R allele have the potential for selection of the strong resistance phenotype. CAPS markers for strong phosphine resistance will help to detect and confirm resistant beetles and can facilitate resistance management actions against a given pest population.

Atypical correlation of otolith strontium : calcium and barium : calcium across a marine–freshwater life history transition of a diadromous fish

Variation in strontium (Sr) and barium (Ba) within otoliths is invaluable to studies of fish diadromy. Typically, otolith Sr : Ca is positively related to salinity, and the ratios of Ba and Sr to calcium (Ca) vary in opposite directions in relation to salinity. In this study of jungle perch, Kuhlia rupestris, otolith Sr : Ca and Ba : Ca, however, showed the same rapid increase as late-larval stages transitioned directly from a marine to freshwater environment. This transition was indicated by a microstructural check mark on otoliths at 35–45 days age. As expected ambient Sr was lower in the fresh than the marine water, however, low Ca levels (0.4 mg L–1) of the freshwater resulted in the Sr : Ca being substantially higher than the marine water. Importantly, the otolith Sr : Ba ratio showed the expected pattern of a decrease from the marine to freshwater stage, illustrating that Sr : Ba provided a more reliable inference of diadromous behaviour based on prior expectations of their relationship to salinity, than did Sr : Ca. The results demonstrate that Ca variation in freshwaters can potentially be an important influence on otolith element : Ca ratios and that inferences of marine–freshwater habitat use from otolith Sr : Ca alone can be problematic without an understanding of water chemistry.

Joint Regression and Association Models for Repeated Categorical Responses

The focus of this study is on statistical analysis of categorical responses, where the response values are dependent of each other. The most typical example of this kind of dependence is when repeated responses have been obtained from the same study unit. For example, in Paper I, the response of interest is the pneumococcal nasopharengyal carriage (yes/no) on 329 children. For each child, the carriage is measured nine times during the first 18 months of life, and thus repeated respones on each child cannot be assumed independent of each other. In the case of the above example, the interest typically lies in the carriage prevalence, and whether different risk factors affect the prevalence. Regression analysis is the established method for studying the effects of risk factors. In order to make correct inferences from the regression model, the associations between repeated responses need to be taken into account. The analysis of repeated categorical responses typically focus on regression modelling. However, further insights can also be gained by investigating the structure of the association. The central theme in this study is on the development of joint regression and association models. The analysis of repeated, or otherwise clustered, categorical responses is computationally difficult. Likelihood-based inference is often feasible only when the number of repeated responses for each study unit is small. In Paper IV, an algorithm is presented, which substantially facilitates maximum likelihood fitting, especially when the number of repeated responses increase. In addition, a notable result arising from this work is the freely available software for likelihood-based estimation of clustered categorical responses.

Bayesian statistical analysis of bacterial diversity

Bacteria play an important role in many ecological systems. The molecular characterization of bacteria using either cultivation-dependent or cultivation-independent methods reveals the large scale of bacterial diversity in natural communities, and the vastness of subpopulations within a species or genus. Understanding how bacterial diversity varies across different environments and also within populations should provide insights into many important questions of bacterial evolution and population dynamics. This thesis presents novel statistical methods for analyzing bacterial diversity using widely employed molecular fingerprinting techniques. The first objective of this thesis was to develop Bayesian clustering models to identify bacterial population structures. Bacterial isolates were identified using multilous sequence typing (MLST), and Bayesian clustering models were used to explore the evolutionary relationships among isolates. Our method involves the inference of genetic population structures via an unsupervised clustering framework where the dependence between loci is represented using graphical models. The population dynamics that generate such a population stratification were investigated using a stochastic model, in which homologous recombination between subpopulations can be quantified within a gene flow network. The second part of the thesis focuses on cluster analysis of community compositional data produced by two different cultivation-independent analyses: terminal restriction fragment length polymorphism (T-RFLP) analysis, and fatty acid methyl ester (FAME) analysis. The cluster analysis aims to group bacterial communities that are similar in composition, which is an important step for understanding the overall influences of environmental and ecological perturbations on bacterial diversity. A common feature of T-RFLP and FAME data is zero-inflation, which indicates that the observation of a zero value is much more frequent than would be expected, for example, from a Poisson distribution in the discrete case, or a Gaussian distribution in the continuous case. We provided two strategies for modeling zero-inflation in the clustering framework, which were validated by both synthetic and empirical complex data sets. We show in the thesis that our model that takes into account dependencies between loci in MLST data can produce better clustering results than those methods which assume independent loci. Furthermore, computer algorithms that are efficient in analyzing large scale data were adopted for meeting the increasing computational need. Our method that detects homologous recombination in subpopulations may provide a theoretical criterion for defining bacterial species. The clustering of bacterial community data include T-RFLP and FAME provides an initial effort for discovering the evolutionary dynamics that structure and maintain bacterial diversity in the natural environment.

Synchronous decade up/down counter

Sequential up/down counting is required many a time. In this paper, the logical design of such a counter of the parallel carry type is furnished.

Luokan P loogisesta karakterisoinnista

Deskriptiivisessä vaativuusteoriassa tutkitaan laskennan vaativuuteen liittyviä kysymyksiä logiikan työkalujen avulla. Tällöin käsitellään tilannetta, jossa laskennan syötteenä toimivat äärelliset mallit. Tässä kehyksessä erinäisiä vaativuusluokkia voidaan karakterisoida etsimällä logiikoita, joilla on kyseistä vaativuusluokkaa vastaava ilmaisuvoima. Klassiset esimerkit tällaisista tuloksista ovat Faginin esittämä epädeterministisen polynomiaalisen ajan karakterisaatio logiikan Σ_1^1 avulla ja Immermanin, Livchakin ja Vardin esittämä deterministisen polynomiaalisen ajan karakterisaatio ensimmäisen kertaluvun inflatorisen kiintopistelogiikan avulla. Tässä opinnäytetyössä tarkastellaan Gurevichin esittämää kysymystä polynomiaalisessa ajassa ratkeavien kielten luokan P vahvasta loogisesta karakterisaatiosta. Kyseinen kysymys on yksi äärellisen malliteorian haastavimpia ongelmia. Kysymyksen esittelyyn tarvittavan peruskoneiston läpikäynnin lisäksi tässä käsi- tellään myös sen yhteyksiä laskennan vaativuusteoriassa keskeiseen P-NP-ongelmaan. Gurevichin kysymyksestä voidaan esittää myös rajoitetumpia versioita, mikäli käsitellään tilannetta, jossa laskennan syötteenä voi olla vain kiinnitetyn malliluokan K malleja. Tällöin luokan P karakterisointi helpottuu, ainakin jos luokka K on riittävän suppea. Tässä opinnäytetyössä käydään läpi Grohen esittämä tulos siitä, että mikäli luokaksi K valitaan 3-yhtenäisten tasoverkkojen luokka, niin ensimmäisen kertaluvun inflatorinen kiintopistelogiikka karakterisoi polynomiaalisessa ajassa laskettavat kielet.

Computing the Stochastic Complexity of Simple Probabilistic Graphical Models

Minimum Description Length (MDL) is an information-theoretic principle that can be used for model selection and other statistical inference tasks. There are various ways to use the principle in practice. One theoretically valid way is to use the normalized maximum likelihood (NML) criterion. Due to computational difficulties, this approach has not been used very often. This thesis presents efficient floating-point algorithms that make it possible to compute the NML for multinomial, Naive Bayes and Bayesian forest models. None of the presented algorithms rely on asymptotic analysis and with the first two model classes we also discuss how to compute exact rational number solutions.

Thermal decomposition of rare-earth trioxalatocobaltates

The thermal decomposition of rare-earth trioxalatocobaltates LnCo(C2O4)3 · x H2O, where Ln = La, Pr, Nd, has been studied in flowing atmospheres of air/oxygen, argon/ nitrogen, carbon dioxide and a vacuum. The compounds decompose through three major steps, viz. dehydration, decomposition of the oxalate to an intermediate carbonate, which further decomposes to yield rare-earth cobaltite as the final product. The formation of the final product is influenced by the surrounding gas atmosphere. Studies on the thermal decomposition of photodecomposed lanthanum trioxalatocobaltate and a mechanical mixture of lanthanum oxalate and cobalt oxalate in 1 : 2 molar ratio reveal that the decomposition behaviour of the two samples is different. The drawbacks of the decomposition scheme proposed earlier have been pointed out, and logical schemes based on results obtained by TG, DTA, DTG, supplemented by various physico-chemical techniques such as gas and chemical analyses, IR and mass spectroscopy, surface area and magnetic susceptibility measurements and X-ray powder diffraction methods, have been proposed for the decomposition in air of rare-earth trioxalatocobaltates as well as for the photoreduced lanthanum salt and a mechanical mixture of lanthanum and cobalt oxalates.

Affektiivisuuden laskennallinen määritteleminen

One of the most tangled fields of research is the field of defining and modeling affective concepts, i. e. concepts regarding emotions and feelings. The subject can be approached from many disciplines. The main problem is lack of generally approved definitions. However, e.g. linguists have recently started to check the consistency of their theories with the help of computer simulations. Definitions of affective concepts are needed for performing similar simulations in behavioral sciences. In this thesis, preliminary computational definitions of affects for a simple utility-maximizing agent are given. The definitions have been produced by synthetizing ideas from theories from several fields of research. The class of affects is defined as a superclass of emotions and feelings. Affect is defined as a process, in which a change in an agent's expected utility causes a bodily change. If the process is currently under the attention of the agent (i.e. the agent is conscious of it), the process is a feeling. If it is not, but can in principle be taken into attention (i.e. it is preconscious), the process is an emotion. Thus, affects do not presuppose consciousness, but emotions and affects do. Affects directed at unexpected materialized (i.e. past) events are delight and fright. Delight is the consequence of an unexpected positive event and fright is the consequence of an unexpected negative event. Affects directed at expected materialized (i.e. past) events are happiness (expected positive event materialized), disappointment (expected positive event did not materialize), sadness (expected negative event materialized) and relief (expected negative event did not materialize). Affects directed at expected unrealized (i.e. future) events are fear and hope. Some other affects can be defined as directed towards originators of the events. The affect classification has also been implemented as a computer program, the purpose of which is to ensure the coherence of the definitions and also to illustrate the capabilities of the model. The exact content of bodily changes associated with specific affects is not considered relevant from the point of view of the logical structure of affective phenomena. The utility function need also not be defined, since the target of examination is only its dynamics.

Variation in the Understanding of Lutheranism and Its Implications for Religious Education : Meaning Discernment of Students and Teachers in Finnish Upper Secondary Schools

The study investigated variation in the ways in which a group of students and teachers of Evangelical Lutheran religious education in Finnish upper secondary schools understand Lutheranism and searched for educational implications for learning in religious education. The aim of understanding the qualitative variation in understanding Lutheranism was explored through the relationship between the following questions, which correspond to the results reported in the following original refereed publications: 1) How do Finnish students understand Lutheranism? 2) How do Finnish teachers of religious education constitute the meaning of Lutheranism? 3) How could phenomenography and the Variation Theory of Learning contribute to learning about and from religion in the context of Finnish Lutheran Religious Education as compared to religious education in the UK? Two empirical studies (Hella, 2007; Hella, 2008) were undertaken from a phenomenographic research perspective (e.g., Marton, 1981) and the Variation Theory of Learning (e.g., Marton & Tsui et al. 2004) that developed from it. Data was collected from 63 upper secondary students and 40 teachers of religious education through written tasks with open questions and complementary interviews with 11 students and 20 teachers for clarification of meanings. The two studies focused on the content and structure of meaning discernment in students and teachers expressed understandings of Lutheranism. Differences in understandings are due to differences in the meanings that are discerned and focused on. The key differences between the ways students understand varied from understanding Lutheranism as a religion to personal faith with its core in mercy. The logical relationships between the categories that describe variation in understanding express a hierarchy of ascending complexity, according to which more developed understandings are inclusive of less developed ones. The ways the teachers understand relate to student s understandings in a sequential manner. Phenomenography and Variation Theory were discussed in the context of religious education in Finland and the UK in relation to the theoretical notion of learning about and from religion (Hella & Wright, 2008). The thesis suggests that variation theory enables religious educators to recognise the unity of learning about and from religion, as learning is always learning about something and involves simultaneous engagement with the object of learning and development as a person. The study also suggests that phenomenography and variation theory offer a means by which it is possible for academics, policy makers, curriculum designers, teachers and students to learn to discern different ways of understanding the contested nature of religions. Keywords: Lutheranism, understanding, variation, teaching, learning, phenomenography, religious education

The Catholic Internet discussion on cloning : A study in cognitive rhetoric

This work combines the cognitive theory of folk-theoretical thought with the classical Aristotelian theory of artistic proof in rhetoric. The first half of the work discusses the common ground shared by the elements of artistic proof (logos, pathos, ethos) and the elements of folk-theoretical thought (naïve physics, folk biology, folk psychology, naïve sociology). Combining rhetoric with the cognitive theory of folk-theoretical thought creates a new point of view for argumentation analysis. The logos of an argument can be understood as the inferential relations established between the different parts of an argument. Consequently, within this study the analysis of logos is to be viewed as the analysis of the inferential folk-theoretical elements that make the suggested factual states-of-things appear plausible within given argumentative structures. The pathos of an argumentative structure can be understood as determining the quality of the argumentation in question in the sense that emotive elements play a great part in what can be called a distinction between good and deceptive rhetoric. In the context of this study the analysis of pathos is to be viewed as the analysis of the emotive content of argumentative structures and of whether they aim at facilitating surface- or deep cognitive elaboration of the suggested matters. The ethos of an argumentative structure means both the speaker-presentation and audience-construct that can be discerned within a body of argumentation. In the context of this study, the analysis of ethos is to be understood as the analysis of mutually manifest cognitive environments in the context of argumentation. The theory is used to analyse Catholic Internet discussion concerning cloning. The discussion is divided into six themes: Human Dignity, Sacred Family, Exploitation / Dehumanisation, Playing God, Monsters and Horror Scenarios and Ensoulment. Each theme is analysed for both the rhetorical and the cognitive elements that can be seen creating persuasive force within the argumentative structures presented. It is apparent that the Catholic voices on the Internet extensively oppose cloning. The voices utilise rhetoric that is aggressive and pejorative more often than not. Furthermore, deceptive rhetoric (in the sense presented above) plays a great part in argumentative structures of the Catholic voices. The theory of folk-theoretical thought can be seen as a useful tool for analysing the possible reasons why the Catholic speakers think about cloning and choose to present cloning in their argumentation as they do. The logos utilized in the argumentative structures presented can usually be viewed as based on folk-theoretical inference concerning biology and psychology. The structures of pathos utilized generally appear to aim at generating fear appeal in the assumed audiences, often incorporating counter-intuitive elements. The ethos utilised in the arguments generally revolves around Christian mythology and issues of social responsibility. These structures can also be viewed from the point of view of folk psychology and naïve sociological assumptions.

A Soul for Europe? : Contributions of European Churches to the Forum of the Convention on the Future of Europe

The aim of this research was to study how European churches contributed to the shaping of the Constitutional Treaty during the work of the Convention on the future of Europe through the public discussion forum, established by the Convention for this specific purpose in the years 2002 2003. In particular, this study sought to uncover the areas of interest brought up by the churches in their contributions, the objectives they pursued, and the approaches and arguments they employed to reach those objectives. The data for this study comprised all official submissions by European churches and church alliances to the Forum, totalling 21 contributions. A central criterion for inclusion of the data was that the organization can reasonably be assumed to represent the official position of one or more Christian churches within the European Union before the 2004 expansion. The contributing churches and organizations represent the vast majority of Christians in Europe. The data was analyzed using primarily qualitative content analysis. The research approach was a combination of abductive and inductive inference. Based on the analysis a two-fold theoretical framework was adopted, focusing on theories of public religion, secularization and deprivatization of religion, and of legitimation and collective identity. The main areas of interest found in the contributions of the churches were the value foundation of the European Union, which is demanded to coherently permeate all policies and actions of the EU, and the social dimension of Europe, which must be given equal status to the political and economic dimensions. In both areas the churches claim significant experience and expertise, which they want to see recognized in the Constituional Treaty through a formally guaranteed status for churches and religious communities in the EU. In their contributions the churches show a strong determination to secure a significant role for both religion and religious communities in the public life of Europe. As for the role of religion, they point out to its potential as a motivating and cohesive force in society and as a building block for a collective European identity, which is still missing. Churches also pursue a substantial public role for themselves beyond the spiritual dimension, permeating the secular areas of the social, political and economic dimensions. The arguments in suppport of such role are embedded in their interest and expertise in spiritual and other fundamental values and their broad involvement in providing social services. In this context churches use expressions inclusive of all religions and convictions, albeit clearly advocating the primacy of Europe's Christian heritage. Based on their historical role, their social involvement and their spiritual mission they use the public debate on the Constitutional Treaty to gain formal legitimacy for the public status of religion and religious communities, both nationally and on a European level, through appropriate provisions in the constitutional text. In return they offer the European Union ways of improving its own legitimacy by reducing the democratic and ideological deficit of the EU and advancing the development a collective European identity.