Search

The multilevel hidden Markov model (MHMM) is a promising method to investigate intense longitudinal data obtained within the social and behavioral sciences. The MHMM quantifies information on the latent dynamics of behavior over time. In addition, heterogeneity between individuals is accommodated with the inclusion of individual-specific random effects, facilitating the study of individual differences in dynamics. However, the performance of the MHMM has not been sufficiently explored. We performed an extensive simulation to assess the effect of the number of dependent variables (1–8), number of individuals (5–90), and number of observations per individual (100–1600) on the estimation performance of a Bayesian MHMM with categorical data including various levels of state distinctiveness and separation. We found that using multivariate data generally alleviates the sample size needed and improves the stability of the results. Moreover, including variables only consisting of random noise was generally not detrimental to model performance. Regarding the estimation of group-level parameters, the number of individuals and observations largely compensate for each other. However, only the former drives the estimation of between-individual variability. We conclude with guidelines on the sample size necessary based on the level of state distinctiveness and separation and study objectives of the researcher.

As the demand for high-speed, reliable wireless communication among interconnected devices rises, the need for robust next-generation wireless MIMO systems becomes crucial.This dissertation is motivated by the need to address the challenges inherent in the development of such systems, specifically focusing on two key aspects: (i) Robust block-sparse mmWave channel modeling and (ii) Robust detection in the presence of few-bit MIMO systems. Central to this thesis is the integration of model-based methods with deep neural network (DNN)-aided approaches, leveraging the synergy between these two paradigms to enhance system performance and mitigate the impact of model inaccuracies and mismatches.The first part of this dissertation focuses on the spatial modeling of mmWave channels, to capture the heterogeneous scattering behavior, through block-sparse signal recovery.Despite the promise of block-sparse signal processing for channel modeling in the angular domain, a key challenge is block-patterned estimation without knowledge of block sizes and boundaries. This work propose a novel total variation sparse Bayesian learning (TV-SBL) method for block-sparse signal recovery under unknown block patterns. Unlike conventional approaches that employ block-promoting regularization on signal components, this method introduces two classes of hyperparameter regularizers for the SBL cost function inspired by total variation (TV) denoising. The first class relies on a conventional TV difference unit, allowing iterative SBL inference through convex optimization, thus facilitating the use of various numerical solvers. The second class integrates a region-aware TV penalty to penalize signal and zero blocks differently, thereby enhancing performance. An alternating optimization algorithm based on expectation-maximization is derived for computationally efficient parallel updates for both regularizer classes. Going beyond model-based methods, this work also presents a basis for extension to

Datasets such as Seshat have allowed researchers to quantitatively test hypotheses about premodern societies and states with great success. Nevertheless, one has to take into account potential sources of bias in the data such as a survivorship bias favouring the inclusion of long-lived over short-lived states. Bayesian methods can be used to complement standard modelling procedures to take this issue into account as is demonstrated by analysing the longevity distribution of premodern states.

Proactive policing methods are crucial to ensuring safety and security in line with the UN Sustainable Development Goals. This chapter considers aoristic crime data, where an event occurs within a known time interval, but at an unknown time. We introduce a Bayesian likelihood-based approach to estimate occurrence times of property crimes given a known time interval by modelling victim and offender behaviour as stochastic processes. The model can capture non-homogeneous behaviour by both the victim and the offender and underlying factors leading to patterns in crime occurrence times. We test our model on an open-source aoristic crime data set from the USA, comparing our approach to previous approaches. The model determines the most likely occurrence times through parameter estimation methods, finding potential hot spots, and allowing police to adapt proactive policing strategies. This ties in with SDG 16, which involves strengthening institutions and working towards safe and secure societies.

Near-infrared spectroscopy (NIRS) provides a high-throughput phenotyping technique to assist breeding for improved faba bean seed quality. We combined chemical analysis of protein, oil content (and composition) with NIRS through chemometrics, employing Partial Least Squares (PLS), Elastic Net (EN), Memory-based Learning (MBL), and Bayes B (BB) as prediction models. Protein was the most reliably predicted trait (R2 = 0.96–0.98) across field trials, followed by oil (R2 = 0.82–0.86) and oleic acid (R2 = 0.31–0.68). Samples for training the models were selected using K-means clustering. The optimal statistical approach for prediction was compound-specific: PLS for protein (Root Mean Squared Error - RMSE = 0.46), BB for oil (RMSE = 0.067), and EN for oleic acid content (RMSE = 2.83). Reduced training set simulations revealed different effects on prediction accuracy depending on the model and compound. Several NIR regions were pinpointed as highly informative for the compounds, using the shrinkage and variable selection capabilities of EN and BB.

Bayesian methods and sports analytics have become popular areas of research, but their intersection remains under-considered in Statistics. While the Nested Dirichlet distribution has been proposed as a conjugate prior to Multinomial data commonly produced in sports settings, many properties of this distribution and its generalizability have not been explored. In this thesis, we propose a different parameterization for the Nested Dirichlet distribution and explain how it can be used to derive the posterior and posterior predictive distributions for the Nested Dirichlet Multinomial model. We also demonstrate the generalizability of our parameterization, an important improvement over the approaches that can be found in the literature. Finally, we present how we used this model to analyze 2023 MLB batting outcome data to produce model-based batting metrics with appropriate uncertainty quantification and compare the results to those produced by the traditional Dirichlet Multinomial model. We found that each model works well under different circumstances, leading us to suggest methods for their improvement in future research. For example, creating mixture models to best capture different player abilities and styles, amongst other suggestions.

This thesis contributes to the field of statistical and mathematical finance by introducing novel Bayesian and game-theoretic methods in discrete-time portfolio theory. These methodologies enhance the precision and adaptability of investment strategies and risk management, particularly in complex market environments. The work is structured around five papers. Paper I introduces a Bayesian framework for optimizing portfolio allocation, utilizing value at risk (VaR) and conditional value at risk (CVaR) as risk measures. This approach leverages the posterior predictive distribution to derive portfolio weights directly from observed data, contrasting with traditional methods that rely on estimates of unobserved variables. The benefit of the Bayesian method is demonstrated through simulations and empirical comparisons, particularly in predicting out-of-sample VaR. Paper II presents a dynamic Bayesian approach to incorporate volatility clustering into VaR and CVaR estimation, utilizing hyperparameters based on different rolling windows to adapt quickly to changing market conditions. This method shows distinct advantages over existing models by adjusting the certainty and expected values of prior distributions in response to volatility changes, offering improved risk estimates during market turbulence. Paper III develops a Bayesian inference procedure for tangency portfolios by establishing a new conjugate prior directly for the optimal portfolio weights, integrating high-frequency returns and a market condition metric, such as the CBOE Volatility Index (VIX) or Economic Policy Uncertainty Index (EPU). This approach enables direct inference on portfolio weights, and backtesting suggests potential advantages over traditional strategies in real-world scenarios. Paper IV addresses the construction of tangency portfolios under short-selling constraints, using the same reparameterized asset return model within a Bayesian context as in Paper III. An innovative prior enforces pos

This thesis contributes to the field of statistical and mathematical finance by introducing novel Bayesian and game-theoretic methods in discrete-time portfolio theory. These methodologies enhance the precision and adaptability of investment strategies and risk management, particularly in complex market environments. The work is structured around five papers. Paper I introduces a Bayesian framework for optimizing portfolio allocation, utilizing value at risk (VaR) and conditional value at risk (CVaR) as risk measures. This approach leverages the posterior predictive distribution to derive portfolio weights directly from observed data, contrasting with traditional methods that rely on estimates of unobserved variables. The benefit of the Bayesian method is demonstrated through simulations and empirical comparisons, particularly in predicting out-of-sample VaR. Paper II presents a dynamic Bayesian approach to incorporate volatility clustering into VaR and CVaR estimation, utilizing hyperparameters based on different rolling windows to adapt quickly to changing market conditions. This method shows distinct advantages over existing models by adjusting the certainty and expected values of prior distributions in response to volatility changes, offering improved risk estimates during market turbulence. Paper III develops a Bayesian inference procedure for tangency portfolios by establishing a new conjugate prior directly for the optimal portfolio weights, integrating high-frequency returns and a market condition metric, such as the CBOE Volatility Index (VIX) or Economic Policy Uncertainty Index (EPU). This approach enables direct inference on portfolio weights, and backtesting suggests potential advantages over traditional strategies in real-world scenarios. Paper IV addresses the construction of tangency portfolios under short-selling constraints, using the same reparameterized asset return model within a Bayesian context as in Paper III. An innovative prior enforces pos

Fine-tuning studies whether some physical parameters, or relevant ratios between them, are located within so-called life-permitting intervals of small probability outside of which carbon-based life would not be possible. Recent developments have found estimates of these probabilities that circumvent previous concerns of measurability and selection bias. However, the question remains whether fine-tuning can indeed be known. Using a mathematization of the concepts of learning and knowledge acquisition, we argue that most examples that have been touted as fine-tuned cannot be formally assessed as such. Nevertheless, fine-tuning can be known when the physical parameter is seen as a random variable and it is supported in the nonnegative real line, provided the size of the life-permitting interval is small in relation to the observed value of the parameter.

This thesis contributes to the field of statistical and mathematical finance by introducing novel Bayesian and game-theoretic methods in discrete-time portfolio theory. These methodologies enhance the precision and adaptability of investment strategies and risk management, particularly in complex market environments. The work is structured around five papers. Paper I introduces a Bayesian framework for optimizing portfolio allocation, utilizing value at risk (VaR) and conditional value at risk (CVaR) as risk measures. This approach leverages the posterior predictive distribution to derive portfolio weights directly from observed data, contrasting with traditional methods that rely on estimates of unobserved variables. The benefit of the Bayesian method is demonstrated through simulations and empirical comparisons, particularly in predicting out-of-sample VaR. Paper II presents a dynamic Bayesian approach to incorporate volatility clustering into VaR and CVaR estimation, utilizing hyperparameters based on different rolling windows to adapt quickly to changing market conditions. This method shows distinct advantages over existing models by adjusting the certainty and expected values of prior distributions in response to volatility changes, offering improved risk estimates during market turbulence. Paper III develops a Bayesian inference procedure for tangency portfolios by establishing a new conjugate prior directly for the optimal portfolio weights, integrating high-frequency returns and a market condition metric, such as the CBOE Volatility Index (VIX) or Economic Policy Uncertainty Index (EPU). This approach enables direct inference on portfolio weights, and backtesting suggests potential advantages over traditional strategies in real-world scenarios. Paper IV addresses the construction of tangency portfolios under short-selling constraints, using the same reparameterized asset return model within a Bayesian context as in Paper III. An innovative prior enforces pos

Many insurance companies offer coverage for damages caused by wasps to living environments. The frequency of insurance claims related to wasps varies yearly, and anticipating the exact frequency is a complex task. By forecasting insurance claims, companies can optimize their resource allocation and management. The objective of this thesis is to forecast the frequency of insurance claims related to wasps using weather data collected over time and space by developing probabilistic models within the Bayesian framework. Weather data is used as it is assumed to capture environmental conditions that affect wasp behavior, and conditions that increase the chances of damages caused by wasps being detected. The Bayesian framework is employed as it offers an efficient way to model uncertainty by treating parameters as random. Twelve models were fitted and their predictive performance for June, July, and August were evaluated during 2022 and 2023. For June, a Negative Binomial model incorporating a spatial adjustment component with a CAR prior, and weather covariates, demonstrated the highest predictive performance. For July, a model incorporating an autoregressive parameter and the weather effect three weeks preceding the insurance claim performed best. For August, a model incorporating only weather covariates outperformed the others. The differing results show that the models capture different underlying processes in the months.

In this tutorial, we introduce the reader to analyzing ecological momentary assessment (EMA) data as applied in psychological sciences with the use of Bayesian (generalized) linear mixed-effects models. We discuss practical advantages of the Bayesian approach over frequentist methods and conceptual differences. We demonstrate how Bayesian statistics can help EMA researchers to (a) incorporate prior knowledge and beliefs in analyses, (b) fit models with a large variety of outcome distributions that reflect likely data-generating processes, (c) quantify the uncertainty of effect-size estimates, and (d) quantify the evidence for or against an informative hypothesis. We present a workflow for Bayesian analyses and provide illustrative examples based on EMA data, which we analyze using (generalized) linear mixed-effects models to test whether daily self-control demands predict three different alcohol outcomes. All examples are reproducible, and data and code are available at https://osf.io/rh2sw/. Having worked through this tutorial, readers should be able to adopt a Bayesian workflow to their own analysis of EMA data.

This paper introduces CUQIpy, a versatile open-source Python package for computational uncertainty quantification (UQ) in inverse problems, presented as Part I of a two-part series. CUQIpy employs a Bayesian framework, integrating prior knowledge with observed data to produce posterior probability distributions that characterize the uncertainty in computed solutions to inverse problems. The package offers a high-level modeling framework with concise syntax, allowing users to easily specify their inverse problems, prior information, and statistical assumptions. CUQIpy supports a range of efficient sampling strategies and is designed to handle large-scale problems. Notably, the automatic sampler selection feature analyzes the problem structure and chooses a suitable sampler without user intervention, streamlining the process. With a selection of probability distributions, test problems, computational methods, and visualization tools, CUQIpy serves as a powerful, flexible, and adaptable tool for UQ in a wide selection of inverse problems. Part II of the series focuses on the use of CUQIpy for UQ in inverse problems with partial differential equations.

Inverse problems, particularly those governed by Partial Differential Equations (PDEs), are prevalent in various scientific and engineering applications, and uncertainty quantification (UQ) of solutions to these problems is essential for informed decision-making. This second part of a two-paper series builds upon the foundation set by the first part, which introduced CUQIpy, a Python software package for computational UQ in inverse problems using a Bayesian framework. In this paper, we extend CUQIpy’s capabilities to solve PDE-based Bayesian inverse problems through a general framework that allows the integration of PDEs in CUQIpy, whether expressed natively or using third-party libraries such as FEniCS. CUQIpy offers concise syntax that closely matches mathematical expressions, streamlining the modeling process and enhancing the user experience. The versatility and applicability of CUQIpy to PDE-based Bayesian inverse problems are demonstrated on examples covering parabolic, elliptic and hyperbolic PDEs. This includes problems involving the heat and Poisson equations and application case studies in electrical impedance tomography and photo-acoustic tomography, showcasing the software’s efficiency, consistency, and intuitive interface. This comprehensive approach to UQ in PDE-based inverse problems provides accessibility for non-experts and advanced features for experts.

The problem of estimating brake pad wear of cars has been considered, using friction work approximated from the product of longitudinal braking force and distance travelled during braking. The braking force is estimated from a longitudinal dynamics model with inputs from an inertial measurement sensing unit with Kalman filter based sensor fusion, and standard vehicle on-board diagnostics data. Wear coefficients are fitted with Bayesian linear regression on measurements from two series: (I) 16 measurements of previously worn pads over approx. 4,800 km with average wear of approx. -0.5 mm and (II) seven measurements of almost new pads over approx. 1,850 km and approx. -0.15 mm of wear. The approximated friction work appears to correlate well with the wear. The wear coefficients converge quickly after just 4-5 measurements. Coefficients ranging from -4. 95·10-5 mm3/J to -2. 08 ·10-5 mm3/J are obtained across the cases, when assuming a coefficient of friction µ = 0.6 obtained through pin-on-disc (POD) tests. The wear coefficients are validated using POD tests, showing good agreements with the indirectly estimated wear coefficients from vehicle longitudinal dynamics. Data from series (II) is used for prediction of remaining useful life (RUL), where one additional measurement is carried out after 16,552 km. The RUL prediction requires knowledge of the relationship between usage feature and distance travelled. Different approaches are investigated for the predictions: wear based on only distance travelled, linear relationship between usage feature and distance, and three levels of braking severity based on the usage data. Four of the approaches underestimate the distance significantly at around 4,000 to 8,000 km against the actual distance of 16,552 km, while the low severity estimate is closest at 20,460 km, agreeing with expectations due to the driving being primarily on highways.

In sub-Saharan Africa (SSA), integrating HIV testing into antenatal care (ANC) has been crucial toward reducing mother-to-child transmission of HIV. With the introduction of new testing modalities, we explored temporal trends in HIV testing within and outside of ANC and identified sociodemographic determinants of testing during ANC., SCOPUS: ar.j, info:eu-repo/semantics/published

BACKGROUND: Following the first locally transmitted case in Sukhbaatar soum, Selenge Province, we aimed to investigate the ultimate scale of the epidemic in the scenario of uninterrupted transmission. METHODS: This was a prospective case study following the locally modified WHO FFX cases generic protocol. A rapid response team collected data from November 14 to 29, 2020. We created a stochastic process to draw many transmission chains from this greater distribution to better understand and make inferences regarding the outbreak under investigation. RESULTS: The majority of the cases involved household transmissions (35, 52.2%), work transmissions (20, 29.9%), index (5, 7.5%), same apartment transmissions (2, 3.0%), school transmissions (2, 3.0%), and random contacts between individuals transmissions (1, 1.5%). The posterior means of the basic reproduction number of both the asymptomatic cases R 0 Asy $$ {R}_0^{Asy} $$ and the presymptomatic cases R 0 Pre $$ {R}_0^{Pre} $$ (1.35 [95% CrI 0.88-1.86] and 1.29 [95% CrI 0.67-2.10], respectively) were lower than that of the symptomatic cases (2.00 [95% Crl 1.38-2.76]). CONCLUSION: Our study highlights the heterogeneity of COVID-19 transmission across different symptom statuses and underscores the importance of early identification and isolation of symptomatic cases in disease control. Our approach, which combines detailed contact tracing data with advanced statistical methods, can be applied to other infectious diseases, facilitating a more nuanced understanding of disease transmission dynamics.

Many insurance companies offer coverage for damages caused by wasps to living environments. The frequency of insurance claims related to wasps varies yearly, and anticipating the exact frequency is a complex task. By forecasting insurance claims, companies can optimize their resource allocation and management. The objective of this thesis is to forecast the frequency of insurance claims related to wasps using weather data collected over time and space by developing probabilistic models within the Bayesian framework. Weather data is used as it is assumed to capture environmental conditions that affect wasp behavior, and conditions that increase the chances of damages caused by wasps being detected. The Bayesian framework is employed as it offers an efficient way to model uncertainty by treating parameters as random. Twelve models were fitted and their predictive performance for June, July, and August were evaluated during 2022 and 2023. For June, a Negative Binomial model incorporating a spatial adjustment component with a CAR prior, and weather covariates, demonstrated the highest predictive performance. For July, a model incorporating an autoregressive parameter and the weather effect three weeks preceding the insurance claim performed best. For August, a model incorporating only weather covariates outperformed the others. The differing results show that the models capture different underlying processes in the months.

Recent research is revealing how cognitive processes are supported by a complex interplay between the brain and the rest of the body, which can be investigated by the analysis of physiological features such as breathing rhythms, heart rate, and skin conductance. Heart rate dynamics are of particular interest as they provide a way to track the sympathetic and parasympathetic outflow from the autonomic nervous system, which is known to play a key role in modulating attention, memory, decision-making, and emotional processing. However, extracting useful information from heartbeats about the autonomic outflow is still challenging due to the noisy estimates that result from standard signal-processing methods. To advance this state of affairs, we propose a novel approach in how to conceptualise and model heart rate: instead of being a mere summary of the observed inter-beat intervals, we introduce a modelling framework that views heart rate as a hidden stochastic process that drives the observed heartbeats. Moreover, by leveraging the rich literature of state-space modelling and Bayesian inference, our proposed framework delivers a description of heart rate dynamics that is not a point estimate but a posterior distribution of a generative model. We illustrate the capabilities of our method by showing that it recapitulates linear properties of conventional heart rate estimators, while exhibiting a better discriminative power for metrics of dynamical complexity compared across different physiological states. © 2024 The Authors

Urbanization has caused a historical transformation at a global scale, and humanity is moving towards a fully connected society where cities will concentrate population, infrastructure and economic activity. A key element in the cities’ infrastructure is the transportation system, as it facilitates the mobility of people and goods. Transportation systems are constantly generating data from, e.g., GPS, sensors and cameras, and the statistical modeling is challenging due to the complex structure and dynamics of the system, and the inherent uncertainty. In this thesis, we develop Bayesian models with applications to transportation. We specifically focus on models that can be trained on spatiotemporal data coming from transport networks to make predictions on, e.g., bus delays or the actual network topology. Special attention has been given to model scalability issues and uncertainty quantification. We have used real-world data from transportation systems in every study to keep a balance between statistical rigor, novelty, and applicability. The thesis consists of four papers. The first study presents a state-of-the-art probabilistic latent network model to forecast multilayer dynamic graphs. The model uses stochastic blockmodeling to reduce the computational burden, and is illustrated on a sample of 10-year data from four major airlines within the US air transportation system. In the second paper, we develop a robust model for real-time bus travel time prediction that departs from Gaussian assumptions by using Student-t errors, and show how Bayesian inference naturally allows for predictive uncertainty quantification in a highly stochastic environment. Experiments are performed using data from high-frequency buses in Stockholm, Sweden. The third paper shows the potential of multi-output Gaussian processes to tackle network-wide travel time prediction in an urban area. We develop a responsive online model based on a coregionalized covariance and test its accuracy on re, Urbaniseringen har orsakat en historisk förändring på en global skala, och mänskligheten går mot ett uppkopplat globalt nätverkssamhälle där städer kommer att koncentrera befolkning, infrastruktur och ekonomisk aktivitet. Ett nyckelelement i städernas infrastruktur är transportsystemet, eftersom det underlättar rörligheten av människor och varor. Transportsystem genererar ständigt data från tex. GPS, sensorer och kameror, och den statistiska modelleringen är utmanande på grund av systemets komplexa struktur och dynamik, samt dess naturliga osäkerheter. I denna avhandling utvecklar vi Bayesianska modeller med tillämpningar för transporter. Vi fokuserar specifikt på modeller som kan tränas på spatiotemporala data från transportnätverk för att göra prediktioner av t ex. bussförseningar eller verklig nätverkstopologi. Särskild uppmärksamhet har ägnats åt modellskalbarhetsfrågor och kvantifiering av osäkerhet. Vi har använt data från riktiga transportsystem i varje studie för att skapa en balans mellan statistisk korrekthet, praktiskt tillämpbarhet och vetenskaplig höjd. Avhandlingen består av fyra artiklar. Den första artikeln presenterar en probabilistisk latent nätverksmodell för att prognostisera dynamiska grafer med multipla lager. Modellen använder stokastisk blockmodellering för att minska beräkningsbördan, och illustreras på ett datamaterial bestånde av tio års data från fyra stora flygbolag inom det amerikanska lufttransportsystemet. I den andra artikeln utvecklar vi en robust modell för realtidsprognoser av bussförseningar genom att använda Student-t fördelning och vi visar hur Bayesiansk inferens ger en naturlig kvantifiering av osäkerhet i en mycket stokastisk miljö. Experiment utförs med hjälp av högfrekventa data från bussar i Stockholm. Den tredje artikeln visar potentialen hos fler-dimensionella Gaussiska processer för att generera nätverksövergripande prediktioner av trafikflöden i en tätortsmiljö. Vi utvecklar en responsiv onlinemodell baserad på en co, Funding agencies: This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation, Sweden. The computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973.

Recently Díaz, Hössjer and Marks (DHM) presented a Bayesian framework to measure cosmological tuning (either fine or coarse) that uses maximum entropy (maxent) distributions on unbounded sample spaces as priors for the parameters of the physical models (https://doi.org/10.1088/1475-7516/2021/07/020). The DHM framework stands in contrast to previous attempts to measure tuning that rely on a uniform prior assumption. However, since the parameters of the models often take values in spaces of infinite size, the uniformity assumption is unwarranted. This is known as the normalization problem. In this paper we explain why and how the DHM framework not only evades the normalization problem but also circumvents other objections to the tuning measurement like the so called weak anthropic principle, the selection of a single maxent distribution and, importantly, the lack of invariance of maxent distributions with respect to data transformations. We also propose to treat fine-tuning as an emergence problem to avoid infinite loops in the prior distribution of hyperparameters (common to all Bayesian analysis), and explain that previous attempts to measure tuning using uniform priors are particular cases of the DHM framework. Finally, we prove a theorem, explaining when tuning is fine or coarse for different families of distributions. The theorem is summarized in a table for ease of reference, and the tuning of three physical parameters is analyzed using the conclusions of the theorem.

Through a systematic review and a series of meta-analyses, we evaluated the general responsiveness of putative transcriptional biomarkers of general toxicity and chemical stress. We targeted metal exposures performed on bivalves under controlled laboratory conditions, and selected six transcripts associated with general toxicity for evaluation: catalase (cat), glutathione-S-transferase (gst), heat shock proteins 70 and 90 (hsp70, hsp90), metallothionein (mt) and superoxide dismutase (sod). Transcriptional responses (n = 396) were extracted from published scientific articles (k = 22) and converted to log response ratios (lnRRs). By estimating toxic units (TUs), we normalized different metal exposures to a common scale, as a proxy of concentration. Using Bayesian hierarchical random effect models, we then tested the effects of metal exposure on lnRR, both for metal exposure in general and in meta-regressions using TU and exposure time as independent variables. Corresponding analyses were also repeated with transcript and tissue as additional moderators. Observed patterns were similar for general as for transcript- and tissue-specific responses. The expected overall response to arbitrary metal exposure was a lnRR of 0.50, corresponding to a 65 % increase relative a non-exposed control. However, when accounting for publication bias, the estimated ‘true’ response showed no such effect. Furthermore, expected response magnitude increased slightly with exposure time, but there was little support for general monotonic concentration-dependence with regards to TU. Altogether, this work reveals potential limitations that need consideration prior to applying the selected transcripts as biomarkers in environmental risk assessment. This article is protected by copyright. All rights reserved. Environ Toxicol Chem 2022;00:0–0., CC BY 4.0© 2022 SETAC. This article is protected by copyright. All rights reserved.First published: 06 October 2022Correspondence gustaf.ekelund_ugge@biol.lu.se

Urbanization has caused a historical transformation at a global scale, and humanity is moving towards a fully connected society where cities will concentrate population, infrastructure and economic activity. A key element in the cities’ infrastructure is the transportation system, as it facilitates the mobility of people and goods. Transportation systems are constantly generating data from, e.g., GPS, sensors and cameras, and the statistical modeling is challenging due to the complex structure and dynamics of the system, and the inherent uncertainty. In this thesis, we develop Bayesian models with applications to transportation. We specifically focus on models that can be trained on spatiotemporal data coming from transport networks to make predictions on, e.g., bus delays or the actual network topology. Special attention has been given to model scalability issues and uncertainty quantification. We have used real-world data from transportation systems in every study to keep a balance between statistical rigor, novelty, and applicability. The thesis consists of four papers. The first study presents a state-of-the-art probabilistic latent network model to forecast multilayer dynamic graphs. The model uses stochastic blockmodeling to reduce the computational burden, and is illustrated on a sample of 10-year data from four major airlines within the US air transportation system. In the second paper, we develop a robust model for real-time bus travel time prediction that departs from Gaussian assumptions by using Student-t errors, and show how Bayesian inference naturally allows for predictive uncertainty quantification in a highly stochastic environment. Experiments are performed using data from high-frequency buses in Stockholm, Sweden. The third paper shows the potential of multi-output Gaussian processes to tackle network-wide travel time prediction in an urban area. We develop a responsive online model based on a coregionalized covariance and test its accuracy on re, Urbaniseringen har orsakat en historisk förändring på en global skala, och mänskligheten går mot ett uppkopplat globalt nätverkssamhälle där städer kommer att koncentrera befolkning, infrastruktur och ekonomisk aktivitet. Ett nyckelelement i städernas infrastruktur är transportsystemet, eftersom det underlättar rörligheten av människor och varor. Transportsystem genererar ständigt data från tex. GPS, sensorer och kameror, och den statistiska modelleringen är utmanande på grund av systemets komplexa struktur och dynamik, samt dess naturliga osäkerheter. I denna avhandling utvecklar vi Bayesianska modeller med tillämpningar för transporter. Vi fokuserar specifikt på modeller som kan tränas på spatiotemporala data från transportnätverk för att göra prediktioner av t ex. bussförseningar eller verklig nätverkstopologi. Särskild uppmärksamhet har ägnats åt modellskalbarhetsfrågor och kvantifiering av osäkerhet. Vi har använt data från riktiga transportsystem i varje studie för att skapa en balans mellan statistisk korrekthet, praktiskt tillämpbarhet och vetenskaplig höjd. Avhandlingen består av fyra artiklar. Den första artikeln presenterar en probabilistisk latent nätverksmodell för att prognostisera dynamiska grafer med multipla lager. Modellen använder stokastisk blockmodellering för att minska beräkningsbördan, och illustreras på ett datamaterial bestånde av tio års data från fyra stora flygbolag inom det amerikanska lufttransportsystemet. I den andra artikeln utvecklar vi en robust modell för realtidsprognoser av bussförseningar genom att använda Student-t fördelning och vi visar hur Bayesiansk inferens ger en naturlig kvantifiering av osäkerhet i en mycket stokastisk miljö. Experiment utförs med hjälp av högfrekventa data från bussar i Stockholm. Den tredje artikeln visar potentialen hos fler-dimensionella Gaussiska processer för att generera nätverksövergripande prediktioner av trafikflöden i en tätortsmiljö. Vi utvecklar en responsiv onlinemodell baserad på en co, Funding agencies: This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation, Sweden. The computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973.

The ABC algorithm is a Bayesian method which simulates samples from the posterior distribution. In this thesis, the method is applied on both synthetic and observed data of a regression model. Under normal error distribution a conjugate prior and the likelihood function are used in the algorithm. Additionally, a bootstrap method is implemented in a modified algorithm to provide an alternative method, without requiring normal error distribution. The results of both methods are thereafter presented and compared with the analytic posterior under a conjugate prior, to evaluate their performances. Lastly, advantages and possible issues are discussed.

In this dissertation, we develop a new type of prior distribution, specifically for populations themselves, which we denote the Dirichlet Spacing prior. This prior solves a specific problem that arises when attempting to create synthetic populations from a known subset: the unfortunate reality that assuming independence between population members means that every synthetic population will be essentially the same. This is a problem because any model which only yields one result (several very similar results), when we have very incomplete information, is fundamentally flawed. We motivate our need for this new class of priors using Agent-based Models, though this prior could be used in any situation requiring synthetic populations.

The hippocampus plays a crucial role in organizing the memory of daily events, yet unraveling its mechanisms poses challenges. Decoding the information encoded in the hippocampus is particularly challenging due to sparse neuron activity in non-spatial tasks. However, accurate decoding is crucial for understanding how the hippocampus represents and processes information. This work focuses on decoding neural activity using multivariate point processes, specifically Poisson and Hawkes processes. The first two chapters concentrate on Hawkes processes, which are well-suited for modeling history-dependent phenomena characterized by clustered events, such as the spiking activity in the brain. The study introduces several self-exciting/inhibiting Hawkes process models that effectively capture the interactions among an ensemble of neurons in the hippocampus of rats. The study demonstrates that this approach enables more accurate decoding with significantly lower computational complexity. In the final chapter, we present two novel models for encoding and de- coding neural activity using non-homogeneous Poisson processes. The encoding model captures neuronal dynamics in response to stimuli, revealing temporal variations in neuronal activity over time. On the other hand, the decoding model focuses on decoding the underlying stimulus patterns from the spike train data, leveraging the estimated firing rates from the encoding model. These models demonstrate improved decoding accuracy, emphasizing the importance of incorporating temporal dynamics in decoding stimulus patterns from neural activity.

High-precision measurements of large-scale cosmic structure are expected to revolutionize our understanding of fundamental physics, for example by the quantifying neutrino mass and elucidating the nature of dark energy. This dissertation tackles various of the challenges that must be faced in order to optimally extract information from cosmological surveys, taking a particular interest in neutrino mass.Massive neutrinos suppress the growth of cosmic structure on small scales, where gravity is nonlinear. It is currently an urgent task to determine how to maximally retrieve information in the nonlinear regime, as a traditional power spectrum analysis is no longer optimal. We start by using simulations to investigate the amount of information regarding neutrino mass present in cosmic structure. We find that while there is in principle a lot of information, only a small fraction will be measurable by upcoming surveys such as DESI and LSST. This motivates the need to perform a combined analysis with other cosmological tracers, such as the cosmic microwave background, and galaxy peculiar velocities. We thus develop a Bayesian forward modeling framework to combine field-level inference with galaxy peculiar velocities as a means to optimally extract information.Additionally, various numerical challenges arise due to the nonlinear effects of gravity. For example, computing the covariance matrices required for likelihood-based analyses becomes challenging, in particular due to the super-sample covariance effect. Moreover, the inference often involves non-trivial posterior surfaces which are plagued by volume effects such as the Look-Elsewhere Effect. This is particularly prevalent when searching for evidence of exotic new models. In the latter chapters of the dissertation we provide methods to solve both of these problems.All put together, this dissertation provides the ingredients for the cosmology community to move closer to an optimal measurement of neutrino mass and other

One in three women worldwide experience physical or sexual violence, mostly by an intimate partner. Despite the large number of complaints, it is suspected that they represent only a small portion of the cases occurring, as for very different reasons, the victims often decide not to report the assaults they suffer. In this work, the number of weekly diagnoses related to gender-based violence registered in the Primary Care system in one of the largest areas in Catalonia (Spain) is analysed, estimating its under-reporting and considering the different behavior of the phenomenon due to the COVID-19 mitigation measures undertaken by the Spanish government and the impact of a training activity to sensitize practitioners conducted in late 2019 in the considered area. The proposed methodology is also capable of reconstructing the most likely evolution of the process.

We explore the positive geometry of statistical models in the setting of toric varieties. Our focus lies on models for discrete data that are parameterized in terms of Cox coordinates. We develop a geometric theory for computations in Bayesian statistics, such as evaluating marginal likelihood integrals and sampling from posterior distributions. These are based on a tropical sampling method for evaluating Feynman integrals in physics. We here extend that method from projective spaces to arbitrary toric varieties., QC 20231122

Protein quantification for shotgun proteomics is a complicated process where errors can be introduced in each of the steps. Triqler is a Python package that estimates and integrates errors of the different parts of the label-free protein quantification pipeline into a single Bayesian model. Specifically, it weighs the quantitative values by the confidence we have in the correctness of the corresponding PSM. Furthermore, it treats missing values in a way that reflects their uncertainty relative to observed values. Finally, it combines these error estimates in a single differential abundance FDR that not only reflects the errors and uncertainties in quantification but also in identification. In this tutorial, we show how to (1) generate input data for Triqler from quantification packages such as MaxQuant and Quandenser, (2) run Triqler and what the different options are, (3) interpret the results, (4) investigate the posterior distributions of a protein of interest in detail, and (5) verify that the hyperparameter estimations are sensible. ., QC 20230613

In the face of spatially correlated data, Gaussian process regression is a very common modeling approach. Given observational data, kriging equations will provide the best linear unbiased predictor for the mean at unobserved locations. However, when a computer model provides a complete grid of forecasted values, kriging will not apply. To develop an approach to quantify uncertainty of computer model output in this setting, we leverage information from a collection of computer model runs (e.g., historical forecast and observation pairs for tropical cyclone precipitation totals) through a Bayesian hierarchical framework. This framework allows us to combine information and account for the spatial correlation within and across computer model output. Using maximum likelihood estimates and the corresponding Hessian matrices for Gaussian process parameters, these are input to a Gibbs sampler which provides posterior distributions for parameters of interest. These samples are used to generate predictions which provide uncertainty quantification for a given computer model run (e.g., tropical cyclone precipitation forecast). We then extend this framework using deep Gaussian processes to allow for nonstationary covariance structure, applied to multiple computer model runs from a cosmology application. We also perform sensitivity analyses to understand which parameter inputs most greatly impact cosmological computer model output.

In ecology, it is common for processes to be bounded based on physical constraints of the system. One common example is the positivity constraint, which applies to phenomena such as duration times, population sizes, and total stock of a system’s commodity. In this paper, we propose a novel method for parameterizing Lognormal state space models using an approach based on moment matching. Our method enforces the positivity constraint, allows for arbitrary mean evolution and variance structure, and has a closed-form Markov transition density which allows for more flexibility in fitting techniques. We discuss two existing Lognormal state space models and examine how they differ from the method presented here. We use 180 synthetic datasets to compare the forecasting performance under model misspecification and assess the estimation of precision parameters between our method and existing methods. We find that our models perform well under misspecification, and that fixing the observation variance both helps to improve estimation of the process variance and improves forecast performance. To test our method on a difficult problem, we compare the predictive performance of two Lognormal state space models in predicting the Leaf Area Index over a 151 day horizon by using a process-based ecosystem model to describe the temporal dynamics. We find that our moment matching model performs better than its competitor, and is better suited for intermediate predictive horizons. Overall, our study helps to inform practitioners about the importance of incorporating sensible dynamics when using models of complex systems to predict out-of-sample.

This thesis discusses the characterization of the undrained shear strength, S_u from the net cone resistance, q_net of clay in Dutch sites using Hierarchical Bayesian Modelling (HBM). The performance of the HBM is compared with the current practice methods of the site characterization which propose either the use of only site–specific observations (unpooled models) or the whole data simultaneously (pooled models). HBM can incorporate information from multiple sources such as prior knowledge of the engineers and behaviour met in the examined and the neighbouring sites. The use of different sources of information has been proposed by Eurocode-7 without providing a formal / mathematical procedure. Literature studies have highlighted the potential benefits of incorporating the HBM into the characterization of the geotechnical parameter values. Therefore, this thesis aims to assess whether HBM can enhance the geotechnical decision-making by precisely quantifying the uncertainty in the geotechnical parameter values and making more accurate predictions of them. The impact of using input from the HBM results in a reliability analysis of a dike slope is examined as well. First, a considerable number of paired q_net–S_u measurements is collected, and subsequently is divided into groups. Different statistical models are employed to describe this collected data. Two components characterize a statistical model; the functional form which is the relationship between S_u and q_net and the pooling family (pooled, unpooled and HBM), the method followed to train the statistical model parameters. The statistical models are applied in a comparative study to select the fittest one and to compare the behaviour of the HBM to the other pooling families. The comparative study is performed by applying the Bayesian Data Analysis (BDA) whose applicability is ensured by applying it in an artificial example using artificial data. The first result of the BDA with real data is the compa, Geo-Engineering

The Bayesian approach is a very important approach for tackling problems in statistics. It involves choosing a distribution that reflects the prior knowledge and thus takes all knowledge into account in contrast to the frequentist approach. It also assumes that the parameters (the regression coefficients) follow a distribution called the posterior distribution instead of fixed constants. When a specific choice of this prior is made, this needs to be justified as the prior directly influences the posterior distribution of the regression coefficients. It is also possible to consider priors that do not carry a lot of information and such priors will be compared in this project. In this thesis, the Bayesian approach will be used to apply a multinomial logistic regression model to data concerning students’ study habits and beliefs. The data is provided by a research group called PRIME and they focus on mathematics education at the TU Delft. Multinomial logistic regression is used to find predictions of the choices expressed in probabilities. Bayesian statistics is not only useful in a sense that it offers the possibility to specify the prior knowledge, but also because the Bayesian way of thinking can be incorporated in evaluating results. This can be done by constructing credible intervals for the predicted probabilities. Overlap between intervals can then give insight on prediction quality. In this project, the models are coded in R and here two packages are used: the UPG and the BRMS package. The priors that are compared are the Gaussian and Cauchy distributions. Other than that there are also default priors used in the packages, which can be compared to the Gaussian and Cauchy priors. In the end, a conclusion can be drawn about the performance of each model based on the prediction accuracy. It can be concluded that the BRMS package outperforms the UPG package in terms of accuracy both using default priors and overall using default priors gives mo, PRIME: PRogramme of Innovation in Mathematics Education, Applied Mathematics

In ecology, it is common for processes to be bounded based on physical constraints of the system. One common example is the positivity constraint, which applies to phenomena such as duration times, population sizes, and total stock of a system’s commodity. In this paper, we propose a novel method for parameterizing Lognormal state space models using an approach based on moment matching. Our method enforces the positivity constraint, allows for arbitrary mean evolution and variance structure, and has a closed-form Markov transition density which allows for more flexibility in fitting techniques. We discuss two existing Lognormal state space models and examine how they differ from the method presented here. We use 180 synthetic datasets to compare the forecasting performance under model misspecification and assess the estimation of precision parameters between our method and existing methods. We find that our models perform well under misspecification, and that fixing the observation variance both helps to improve estimation of the process variance and improves forecast performance. To test our method on a difficult problem, we compare the predictive performance of two Lognormal state space models in predicting the Leaf Area Index over a 151 day horizon by using a process-based ecosystem model to describe the temporal dynamics. We find that our moment matching model performs better than its competitor, and is better suited for intermediate predictive horizons. Overall, our study helps to inform practitioners about the importance of incorporating sensible dynamics when using models of complex systems to predict out-of-sample.

Urbanization has caused a historical transformation at a global scale, and humanity is moving towards a fully connected society where cities will concentrate population, infrastructure and economic activity. A key element in the cities’ infrastructure is the transportation system, as it facilitates the mobility of people and goods. Transportation systems are constantly generating data from, e.g., GPS, sensors and cameras, and the statistical modeling is challenging due to the complex structure and dynamics of the system, and the inherent uncertainty. In this thesis, we develop Bayesian models with applications to transportation. We specifically focus on models that can be trained on spatiotemporal data coming from transport networks to make predictions on, e.g., bus delays or the actual network topology. Special attention has been given to model scalability issues and uncertainty quantification. We have used real-world data from transportation systems in every study to keep a balance between statistical rigor, novelty, and applicability. The thesis consists of four papers. The first study presents a state-of-the-art probabilistic latent network model to forecast multilayer dynamic graphs. The model uses stochastic blockmodeling to reduce the computational burden, and is illustrated on a sample of 10-year data from four major airlines within the US air transportation system. In the second paper, we develop a robust model for real-time bus travel time prediction that departs from Gaussian assumptions by using Student-t errors, and show how Bayesian inference naturally allows for predictive uncertainty quantification in a highly stochastic environment. Experiments are performed using data from high-frequency buses in Stockholm, Sweden. The third paper shows the potential of multi-output Gaussian processes to tackle network-wide travel time prediction in an urban area. We develop a responsive online model based on a coregionalized covariance and test its accuracy on re, Urbaniseringen har orsakat en historisk förändring på en global skala, och mänskligheten går mot ett uppkopplat globalt nätverkssamhälle där städer kommer att koncentrera befolkning, infrastruktur och ekonomisk aktivitet. Ett nyckelelement i städernas infrastruktur är transportsystemet, eftersom det underlättar rörligheten av människor och varor. Transportsystem genererar ständigt data från tex. GPS, sensorer och kameror, och den statistiska modelleringen är utmanande på grund av systemets komplexa struktur och dynamik, samt dess naturliga osäkerheter. I denna avhandling utvecklar vi Bayesianska modeller med tillämpningar för transporter. Vi fokuserar specifikt på modeller som kan tränas på spatiotemporala data från transportnätverk för att göra prediktioner av t ex. bussförseningar eller verklig nätverkstopologi. Särskild uppmärksamhet har ägnats åt modellskalbarhetsfrågor och kvantifiering av osäkerhet. Vi har använt data från riktiga transportsystem i varje studie för att skapa en balans mellan statistisk korrekthet, praktiskt tillämpbarhet och vetenskaplig höjd. Avhandlingen består av fyra artiklar. Den första artikeln presenterar en probabilistisk latent nätverksmodell för att prognostisera dynamiska grafer med multipla lager. Modellen använder stokastisk blockmodellering för att minska beräkningsbördan, och illustreras på ett datamaterial bestånde av tio års data från fyra stora flygbolag inom det amerikanska lufttransportsystemet. I den andra artikeln utvecklar vi en robust modell för realtidsprognoser av bussförseningar genom att använda Student-t fördelning och vi visar hur Bayesiansk inferens ger en naturlig kvantifiering av osäkerhet i en mycket stokastisk miljö. Experiment utförs med hjälp av högfrekventa data från bussar i Stockholm. Den tredje artikeln visar potentialen hos fler-dimensionella Gaussiska processer för att generera nätverksövergripande prediktioner av trafikflöden i en tätortsmiljö. Vi utvecklar en responsiv onlinemodell baserad på en co, Funding agencies: This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation, Sweden. The computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973.

The ABC algorithm is a Bayesian method which simulates samples from the posterior distribution. In this thesis, the method is applied on both synthetic and observed data of a regression model. Under normal error distribution a conjugate prior and the likelihood function are used in the algorithm. Additionally, a bootstrap method is implemented in a modified algorithm to provide an alternative method, without requiring normal error distribution. The results of both methods are thereafter presented and compared with the analytic posterior under a conjugate prior, to evaluate their performances. Lastly, advantages and possible issues are discussed.

Sandia National Laboratories conducts Magnetized Liner Inertial Fusion (MagLIF) experiments at the Z Pulsed Power Facility. Their objective is to study the burning plasma formed under magnetic direct drive Inertial Confinement Fusion (ICF) conditions and use the inferred information to reduce uncertainty in computational models and improve experimental designs. The Z machine has five neutron time-of-flight (nToF) detectors that measure the fusion neutron time spectrum from three lines-of-sight. Together, these signals are used to infer the ion temperature, target liner mass density, and the burn history of the MagLIF experiment from measured data. These parameters are a few used by ICF scientists to determine if a plasma has achieved ignition or satisfies the Lawson net energy gain criterion. In this work, the computational resources of MCNP were utilized to simulate nToF signals for a user specified Impulse Response Function (IRF) and calculate the sensitivity of the nToF detector response to perturbations in the ion temperature, liner density, bang time, burn width, and IRF shape parameters. These sensitivity profiles are calculated using the CLUTCH methodology, which was implemented in MCNP as a standalone library that is called directly from the source code. The seven novel sensitivity coefficients presented in this work are used in conjunction with the generalized linear least squares Bayesian inference formalism to perform full uncertainty quantification of three simplified models of the Z machine and extract unknown fusion source conditions from synthetic data. It should be noted that while the techniques developed in this work are used to improve our understanding of MagLIF ICF experiments, these same techniques are more general and can be used to address any other fixed source neutron transport problem.

This thesis studies methods to improve the applicability and the performance of Markov Chain Monte Carlo (MCMC) algorithms based on Piecewise Deterministic Markov processes (PDMPs). First, we discuss the key ideas that lay the foundations of the field of MCMC, spanning from the Metropolis-Hastings algorithm to PDMC methods, emphasising a common structure underlying most non-reversible MCMC algorithms studied in the literature. The rest of the thesis is divided in two parts, respectively treating approximations and transformations of PDMC algorithms. In the first part we introduce several discretisation schemes that approximate a given PDMP and study the properties of the proposed algorithms in detail. This area is of fundamental importance to make PDMPs widely applicable, as indeed the PDMPs considered in the MCMC literature typically cannot be simulated exactly because of either complicated deterministic dynamics or because the random event times are distributed according to an exponential distribution with non-homogeneous rate. In the latter case, existing approaches to simulate the random event times are applicable exclusively when the rate is of simple form, a requirement that covers only toy models from the MCMC literature. In this thesis we introduce and study a wide variety of time discretisations of PDMPs of any order of accuracy, which can now be used as a basis for MCMC algorithms. We study two types of discretisations: the first kind is obtained generalising the principle behind classical Euler schemes, while the second is based on splitting schemes. In both settings, we establish the dependence of the error on the step size of the discretisation. For suitable Euler schemes we prove uniform in time estimates on the weak error, a particularly challenging result which gives that the error is fully controlled by the step size and does not depend on the time horizon. Moreover, for approximations of PDMPs obtained with Euler-based schemes we obta, Statistics

Establishing behavior change toward appetitive foods can be crucial to improve people's health. Food go/no-go training (GNG), in which people respond to some food items and not to other food items depending on the presentation of a go or no-go cue, is a means to establish behavior change. GNG changes the perceived value of food items and food consumption. After GNG, no-go items are rated as less attractive than go and/or untrained items, an empirical phenomenon called the NoGo-devaluation-effect. This effect is not always found, however. One theory-based explanation for these inconsistent results may be found in the timing of the go and no-go cues, which is also inconsistent across studies. Hence, in the present work we conducted two experiments to examine the possible role of go and no-go cue presentation timing in eliciting the NoGo-devaluation-effect. In Experiment 1, we presented the food items before the presentation of go/no-go cues, whereas we reversed this order in Experiment 2. As predicted, the NoGo-devaluation-effect was obtained in Experiment 1. This effect was absent in Experiment 2. Moreover, recognition memory for stimulus-action contingencies moderated the devaluation effect in Experiment 1, but not in Experiment 2. These results show that NoGo devaluation is dependent on the timing of the NoGo cue, which has theoretical and applied implications for understanding how and when go/no-go training influences food consumption. We propose that the value of food items is updated during go/no-go training to minimize prediction errors, and that this updating process is boosted by attention.

Most recent programming languages, such as Java, Python and Ruby, include a collection framework as part of their standard library (or runtime). The Java Collection Framework provides a number of collection classes, some of which implement the same abstract data type, making them interchangeable. Developers can therefore choose between several functionally equivalent options. Since collections have different performance characteristics, and can be allocated in thousands of programs locations, the choice of collection has an important impact on performance. Unfortunately, programmers often make sub-optimal choices when selecting their collections.In this thesis, we consider the problem of building automated tools that would help the programmer choose between different collection implementations. We divide this problem into two sub-problems. First, we need to measure the performance of a collection, and use relevant statistical methods to make meaningful comparisons. Second, we need to predict the performance of a collection with as little benchmarking as possible.To measure and analyze the performance of Java collections, we identify problems with the established methods, and suggest the need for more appropriate statistical methods, borrowed from Bayesian statistics. We use these statistical methods in a reproduction of two state-of-the-art dynamic collection selection approaches: CoCo and CollectionSwitch. Our Bayesian approach allows us to make sound comparisons between the previously reported results and our own experimental evidence.We find that we cannot reproduce the original results, and report on possible causes for the discrepancies between our results and theirs.To predict the performance of a collection, we consider an existing tool called Brainy. Brainy suggests collections to developers for C++ programs, using machine learning. One particularity of Brainy is that it generates its own training data, by synthesizing programs and benchmarking them. As a re

In this thesis, we study prediction of the ultimate maximum of a Brownian motion on a finite time horizon with sequential observation of the process. The problem is twofold in the sense that we study prediction of the time at which the ultimate maximum is achieved and prediction of the value of the maximum. We employ a Bayesian decision-theoretic view to find optimal estimators for both the time and space formulation of the problem. In particular, we focus on asymmetric loss functions such as weighted linear, entropy, and LINEX loss. We find Bayes estimators by using methods from the field of optimal stopping. In many cases, the Bayes estimator can be described by an explicit stopping time, while in some cases we resort to investigating free-boundary equations in the form of nonlinear Volterra equations of the second kind. Finally, we compare the estimators from a mean squared error perspective and by investigating the admissibility of estimators. We find that even though the space and time problems are closely related one has to be careful of using rules from one formulation in another since inadmissibility is possible. To our knowledge, the explicit Bayes estimator of the time problem under entropy loss and the proof of an optimal estimator of the maximal value based on the running maximum is completely new. Furthermore, the use of LINEX loss and comparison of estimators are important new contributions to the literature.

In this thesis, we study prediction of the ultimate maximum of a Brownian motion on a finite time horizon with sequential observation of the process. The problem is twofold in the sense that we study prediction of the time at which the ultimate maximum is achieved and prediction of the value of the maximum. We employ a Bayesian decision-theoretic view to find optimal estimators for both the time and space formulation of the problem. In particular, we focus on asymmetric loss functions such as weighted linear, entropy, and LINEX loss. We find Bayes estimators by using methods from the field of optimal stopping. In many cases, the Bayes estimator can be described by an explicit stopping time, while in some cases we resort to investigating free-boundary equations in the form of nonlinear Volterra equations of the second kind. Finally, we compare the estimators from a mean squared error perspective and by investigating the admissibility of estimators. We find that even though the space and time problems are closely related one has to be careful of using rules from one formulation in another since inadmissibility is possible. To our knowledge, the explicit Bayes estimator of the time problem under entropy loss and the proof of an optimal estimator of the maximal value based on the running maximum is completely new. Furthermore, the use of LINEX loss and comparison of estimators are important new contributions to the literature.

Introduction: We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome. Methods: We performed a systematic literature search on clinically available predictors. We combined these predictors with variables from a dataset of clinical ECT trajectories (performed in the University Medical Center Utrecht) to create priors and train the BN. Temporal validation was performed in an independent sample. Results: The systematic literature search yielded three meta-analyses, which provided prior knowledge on outcome predictors. The clinical dataset consisted of 248 treatment trajectories in the training set and 44 trajectories in the test set at the same medical center. The AUC for the primary outcome remission estimated on an independent validation set was 0.686 (95%CI 0.513–0.859) (AUC values of 0.505 – 0.763 observed in 5-fold cross validation of the model within the train set). Accuracy 0.73 (balanced accuracy 0.67), sensitivity 0.55, specificity 0.79, after temporal validation in the independent sample. Prior literature information marginally reduced CI width. Discussion: A BN model comprised of prior knowledge and clinical data can predict remission of depression after ECT with reasonable performance. This approach can be used to make outcome predictions in psychiatry, and offers a methodological framework to weigh additional information, such as patient characteristics, symptoms and biomarkers. In time, it may be used to improve shared decision-making in clinical practice.

Through a systematic review and a series of meta-analyses, we evaluated the general responsiveness of putative transcriptional biomarkers of general toxicity and chemical stress. We targeted metal exposures performed on bivalves under controlled laboratory conditions, and selected six transcripts associated with general toxicity for evaluation: catalase (cat), glutathione-S-transferase (gst), heat shock proteins 70 and 90 (hsp70, hsp90), metallothionein (mt) and superoxide dismutase (sod). Transcriptional responses (n = 396) were extracted from published scientific articles (k = 22) and converted to log response ratios (lnRRs). By estimating toxic units (TUs), we normalized different metal exposures to a common scale, as a proxy of concentration. Using Bayesian hierarchical random effect models, we then tested the effects of metal exposure on lnRR, both for metal exposure in general and in meta-regressions using TU and exposure time as independent variables. Corresponding analyses were also repeated with transcript and tissue as additional moderators. Observed patterns were similar for general as for transcript- and tissue-specific responses. The expected overall response to arbitrary metal exposure was a lnRR of 0.50, corresponding to a 65 % increase relative a non-exposed control. However, when accounting for publication bias, the estimated ‘true’ response showed no such effect. Furthermore, expected response magnitude increased slightly with exposure time, but there was little support for general monotonic concentration-dependence with regards to TU. Altogether, this work reveals potential limitations that need consideration prior to applying the selected transcripts as biomarkers in environmental risk assessment. This article is protected by copyright. All rights reserved. Environ Toxicol Chem 2022;00:0–0., CC BY 4.0© 2022 SETAC. This article is protected by copyright. All rights reserved.First published: 06 October 2022Correspondence gustaf.ekelund_ugge@biol.lu.se

A prior distribution for the underlying graph is introduced in the framework of Gaussian graphical models. Such a prior distribution induces a block structure in the graph's adjacency matrix, allowing learning relationships between fixed groups of variables. A novel sampling strategy named Double Reversible Jumps Markov chain Monte Carlo is developed for learning block structured graphs under the conjugate G-Wishart prior. The algorithm proposes moves that add or remove not just a single edge of the graph but an entire group of edges. The method is then applied to smooth functional data. The classical smoothing procedure is improved by placing a graphical model on the basis expansion coefficients, providing an estimate of their conditional dependence structure. Since the elements of a B-Spline basis have compact support, the conditional dependence structure is reflected on well-defined portions of the domain. A known partition of the functional domain is exploited to investigate relationships among portions of the domain and improve the interpretability of the results. for this article are available online.

Through a systematic review and a series of meta-analyses, we evaluated the general responsiveness of putative transcriptional biomarkers of general toxicity and chemical stress. We targeted metal exposures performed on bivalves under controlled laboratory conditions, and selected six transcripts associated with general toxicity for evaluation: catalase (cat), glutathione-S-transferase (gst), heat shock proteins 70 and 90 (hsp70, hsp90), metallothionein (mt) and superoxide dismutase (sod). Transcriptional responses (n = 396) were extracted from published scientific articles (k = 22) and converted to log response ratios (lnRRs). By estimating toxic units (TUs), we normalized different metal exposures to a common scale, as a proxy of concentration. Using Bayesian hierarchical random effect models, we then tested the effects of metal exposure on lnRR, both for metal exposure in general and in meta-regressions using TU and exposure time as independent variables. Corresponding analyses were also repeated with transcript and tissue as additional moderators. Observed patterns were similar for general as for transcript- and tissue-specific responses. The expected overall response to arbitrary metal exposure was a lnRR of 0.50, corresponding to a 65 % increase relative a non-exposed control. However, when accounting for publication bias, the estimated ‘true’ response showed no such effect. Furthermore, expected response magnitude increased slightly with exposure time, but there was little support for general monotonic concentration-dependence with regards to TU. Altogether, this work reveals potential limitations that need consideration prior to applying the selected transcripts as biomarkers in environmental risk assessment. This article is protected by copyright. All rights reserved. Environ Toxicol Chem 2022;00:0–0., CC BY 4.0© 2022 SETAC. This article is protected by copyright. All rights reserved.First published: 06 October 2022Correspondence gustaf.ekelund_ugge@biol.lu.se

Frequentist statistics and Bayesian statistics are the two main approaches to statistical inference. The frequentist approach is commonly integrated into academic curricula, while the Bayesian approach is less frequently employed. However a comparison of the approaches, further investigating their shortcomings and advantages, might give a better comprehension of statistics and more insight in statistical inference. Therefore the current study applied both the frequentist and Bayesian approach to multinomial logistic regression. The multinomial logistic regression model can be described as a generalized linear model and as a random utility model, and the current study has shown that these models generate an equivalent probability function. Moreover, the method of estimating coefficients in the frequentist and in the Bayesian approach were described. The multinomial logistic regression model was subsequently applied to data from educational research, conducted by PRIME. Three different R packages were used to perform the multinomial logistic regression: the VGAM package (frequentist, generalized linear model), the mlogit package (frequentist, random utility model) and the UPG package (Bayesian, random utility model). The results of the analysis of one dependent variable were subsequently compared. The results indicated that the frequentist and Bayesian approach differ in their estimation time and model fit: the Bayesian approach required more computational time, but resulted in a better model fit. The frequentist 95% confidence intervals and Bayesian 95% credible intervals are comparable, but the interpretation of these is considerably different due to the philosophical underpinnings of both approaches. Moreover in the Bayesian approach, existing knowledge and information can be incorporated by choosing the prior distribution. Furthermore the Bayesian approach gives a posterior distribution, which is more informative than only a point estimate. In, PRIME, Applied Mathematics

Quantile regression is a useful method to analyse data such that the estimates are more robust to outliers and the conditional distributions are more reliable for asymmetric distributions with respect to the commonly used ordinary least squares regression. Besides this, the quantile regression analysis might also include extra information on the conditional relations between the response variable and the explanatory variables. Therefore, it is previously used in educational sciences, among many other research areas. Bayesian statistics is an upcoming approach for computing estimates, as it allows prior knowledge modelling. The Bayesian quantile regression approach produces accurate parameter estimates by specifying prior distributions, likelihood estimators and MCMC methods to model an informative posterior distribution. In this research, the theory behind the quantile regression and the Bayesian quantile regression approach are considered. Especially Bayesian quantile regression for ordinal longitudinal data. This theory is then used on data of academic emotions to analyse its effect on attained grades of engineering students. Multiple aspects of quantile regression are included to analyse this effect, regarding gender, time and correlations between academic emotions. It was found that the quantile regression produced insights that were ignored by ordinary least squares regression, as the effects of anxiety altered over different quantiles. Especially when seperating genders, the effect of anxiety seemed to differ a lot between genders and different fractions of the response variable. Furthermore, an assumption for Bayesian quantile regression is made by specifying an exponentially distributed prior and by seperating the gender distributions, as was found by the estimates of the quantile regression approach., PRIME: PRogramme of Innovation in Mathematics Education, Applied Mathematics