Bayesian Simulation Research Articles

Bayesian modeling and simulation to inform rare disease drug development early decision-making: Application to Duchenne muscular dystrophy.

Rare disease clinical trials are constrained to small sample sizes and may lack placebo-control, leading to challenges in drug development. This paper proposes a Bayesian model-based framework for early go/no-go decision making in rare disease drug development, using Duchenne muscular dystrophy (DMD) as an example. Early go/no-go decisions were based on projections of long-term functional outcomes from a Bayesian model-based analysis of short-term trial data informed by prior knowledge based on 6MWT natural history literature data in DMD patients. Frequentist hypothesis tests were also applied as a reference analysis method. A number of combinations of hypothetical trial designs, drug effects and cohort comparison methods were assessed. The proposed Bayesian model-based framework was superior to the frequentist method for making go/no-go decisions across all trial designs and cohort comparison methods in DMD. The average decision accuracy rates across all trial designs for the Bayesian and frequentist analysis methods were 45.8 and 8.98%, respectively. A decision accuracy rate of at least 50% was achieved for 42 and 7% of the trial designs under the Bayesian and frequentist analysis methods, respectively. The frequentist method was limited to the short-term trial data only, while the Bayesian methods were informed with both the short-term data and prior information. The specific results of the DMD case study were limited due to incomplete specification of individual-specific covariates in the natural history literature data and should be reevaluated using a full natural history dataset. These limitations aside, the framework presented provides a proof of concept for the utility of Bayesian model-based methods for decision making in rare disease trials.

Computing quantities of interest and their uncertainty using Bayesian simulation

AbstractWhen analyzing data, researchers are often less interested in the parameters of statistical models than in functions of these parameters such as predicted values. Here we show that Bayesian simulation with Markov-Chain Monte Carlo tools makes it easy to compute these quantities of interest with their uncertainty. We illustrate how to produce customary and relatively new quantities of interest such as variable importance ranking, posterior predictive data, difficult marginal effects, and model comparison statistics to allow researchers to report more informative results.

Supply chain risk network value at risk assessment using Bayesian belief networks and Monte Carlo simulation

Supply chain risk network value at risk assessment using Bayesian belief networks and Monte Carlo simulation

Specific Macro Factors Affecting Economic Growth During the COVID-19 Pandemic : Evidence from EAGLEs

The study was conducted to assess the impact of macro factors on economic growth in emerging and growth-leading economies (EAGLEs) during the COVID-19 pandemic. The study applied a Bayesian simulation method, and the empirical results exhibited an ambiguous impact of trade openness and the number of internet users on economic growth in these countries during the COVID-19 outbreak. Besides, in response to the economic downturn caused by the COVID-19 pandemic, countries have loosened monetary and fiscal policies simultaneously. However, policy rate reduction was found to be less efficient in the countries previously applying low-interest rates. The evidence showed that reasonable pandemic control measures formed a basis for fastening economic recovery.

A Bayesian approach with urban-scale energy model to calibrate building energy consumption for space heating: A case study of application in Beijing

Urban-scale energy model can be a crucial tool for evaluating and in turn propelling the implementation of energy efficiency and low carbon programs for buildings and cites. A variety of disputes on integrity and correctness lie in basic statistical data of China's building energy use. Inadequate information and performance gap caused by input uncertainties are the common obstacles to produce reliable energy modelling results. This paper develops a bottom-up approach to depict energy use intensity (EUI) for space heating of building in the urban level accurately, even if the data resource is inadequate and imprecise or the data are influenced by uncertain issues. A hybrid probability model is developed and the model parameters are calibrated by Bayesian inference and Markov Chain Monte Carlo simulation using data set of meter reading from 2062 stochastic-sampled heating substations in Beijing. Preparation and simulation efforts of using this energy model are discussed, following this framework and adjusting according to local climate conditions, typological building characteristics and morphological urban-scale parameters. The results show that the approach is reliable and efficient to calibrate parameters in building energy models. The urban-scale benchmarks of EUI for space heating in Beijing is successfully performed to demonstrate the proposed methodology.

Bayesian Network Monte Carlo Simulation of Impact of Abnormalities on Event Time Estimation at Clinical Sites

Bayesian Network Monte Carlo Simulation of Impact of Abnormalities on Event Time Estimation at Clinical Sites

Design of a reference model for fast optimization of photo-electrochemical cells

Photo-electrochemical cells: Bayesian simulation enchmarking.

Bayesian control charts for tolerance limits in the case of normal populations

By using air-lead data analysed by Krishnamoorthy and Mathew (2009) a Bayesian procedure is applied to obtain control limits for the upper one-sided tolerance limit. Reference and probability matching priors are derived for the pth quantile of a normal distribution. By simulating the predictive density of a future upper one-sided tolerance limit, "run-lengths" and average "run-lengths" are derived. In the second part of this paper control limits are derived for one-sided tolerance limits for the distribution of the difference between two normal random variables. This article illustrates the flexibility and unique features of the Bayesian simulation method for obtaining the posterior predictive distribution of a future one-sided tolerance limit. Keywords: Control charts, Probability-matching prior, Reference prior, Tolerance limits

An Analysis of the Impact of a Pandemic on the Performance of Pharmaceutical Stocks

Abstract This research paper investigates the impact of the 2009 H1N1 and Covid-19 pandemics on the returns, volatility, systematic risk and total risk composition of 80 pharmaceutical stocks listed on 11 market indices. Using Bayesian inference and Monte Carlo simulation, the analysis creates an expectation of the potential impact that the Covid-19 pandemic will have on the performance of pharmaceutical stocks. The analysis show a likely increase in stock prices of up to 25% of their values at the start of the pandemic. The results also show that the negative impacts of the pandemic will be realised as increased volatility rather than a decrease in returns. The research makes a methodological contribution to the research on market reaction during pandemics. It also extends the literature on market behaviour during periods of economic uncertainty.

Parameter uncertainty modeling of safety instrumented systems

In this study, a novel safety integrity level (SIL) determination methodology of safety instrumented systems (SISs) with parameter uncertainty is proposed by combining multistage dynamic Bayesian networks (DBNs) and Monte Carlo simulation. A multistage DBN model for SIL determination with multiple redundant cells is established. The models of function inspection test interval and function inspection test stages are alternately connected to form the multistage DBNs. The redundant cells can have different M out of N voting system architectures. An automatic modeling of conditional probability between nodes is developed. The SIL determination of SISs with parameter uncertainty is constructed by using the multistage DBNs and Monte Carlo simulation. A high-pressure SIS in the export of oil wellplatform is adopted to demonstrate the application of the proposed approach. The SIL and availability of the SIS and its subsystems are obtained. The influence of single subsystem on the SIL and availability of the SIS is studied. The influence of single redundant element on the SIL and availability of the subsystem is analyzed. A user-friendly SIL determination software with parameter uncertainty is developed on MATLAB graphical user interface.

CPT-based probabilistic liquefaction assessment considering soil spatial variability, interpolation uncertainty and model uncertainty

In engineering practice, simplified procedure based on cone penetration test (CPT) results is widely used for evaluating soil liquefaction potential. Since the CPT-based simplified procedure was developed from observations during past earthquakes, it is semi-empirical and involves significant uncertainty (e.g., model uncertainty). In addition, due to time, budget and access constraints, CPTs are often sparsely conducted at a specific site, leading to a significant uncertainty associated with interpolation of the limited CPT soundings, particularly along horizontal direction. Furthermore, it is well-recognized that spatial variability of soil properties has a remarkable effect on soil liquefaction. All these variability and uncertainties greatly affect the seismic liquefaction assessment results, particularly spatial distribution of liquefiable soils in a site, and liquefaction-induced damage. This underscores a question of how to properly incorporate these variability and uncertainties in liquefaction assessment, e.g., how to characterize spatial distribution of soil liquefaction potential in a site with quantitative consideration of the abovementioned variability and uncertainty. To address this issue, this paper develops a novel probabilistic method for characterizing spatial distribution of soil liquefaction potential through factor of safety, FS against liquefaction in a vertical cross-section using Bayesian compressive sampling and Monte Carlo simulation. Using the proposed method, many random field samples of FS cross-section are obtained directly from limited CPT measurements. The proposed method is illustrated using both a simulated data example and a set of real CPT data from Christchurch, New Zealand. It is shown that the proposed method performs well and provides reasonable liquefaction assessment results.

Spatio-temporal patterns of childhood pneumonia in Bhutan: a Bayesian analysis

Pneumonia is one of the top 10 diseases by morbidity in Bhutan. This study aimed to investigate the spatial and temporal trends and risk factors of childhood pneumonia in Bhutan. A multivariable Zero-inflated Poisson regression model using a Bayesian Markov chain Monte Carlo simulation was undertaken to quantify associations of age, sex, altitude, rainfall, maximum temperature and relative humidity with monthly pneumonia incidence and to identify the underlying spatial structure of the data. Overall childhood pneumonia incidence was 143.57 and 10.01 per 1000 persons over 108 months of observation in children aged < 5 years and 5–14 years, respectively. Children < 5 years or male sex were more likely to develop pneumonia than those 5–14 years and females. Each 1 °C increase in maximum temperature was associated with a 1.3% (95% (credible interval [CrI] 1.27%, 1.4%) increase in pneumonia cases. Each 10% increase in relative humidity was associated with a 1.2% (95% CrI 1.1%, 1.4%) reduction in the incidence of pneumonia. Pneumonia decreased by 0.3% (CrI 0.26%, 0.34%) every month. There was no statistical spatial clustering after accounting for the covariates. Seasonality and spatial heterogeneity can partly be explained by the association of pneumonia risk to climatic factors including maximum temperature and relative humidity.

Factored Models for Multiscale Decision-Making in Smart Grid Customers

Active participation of customers in the management of demand, and renewable energy supply, is a critical goal of the Smart Grid vision. However, this is a complex problem with numerous scenarios that are difficult to test in field projects. Rich and scalable simulations are required to develop effective strategies and policies that elicit desirable behavior from customers. We present a versatile agent-based "factored model" that enables rich simulation scenarios across distinct customer types and varying agent granularity. We formally characterize the decisions to be made by Smart Grid customers as a multiscale decision-making problem and show how our factored model representation handles several temporal and contextual decisions by introducing a novel "utility optimizing agent." We further contribute innovative algorithms for (i) statistical learning-based hierarchical Bayesian timeseries simulation, and (ii) adaptive capacity control using decision-theoretic approximation of multiattribute utility functions over multiple agents. Prominent among the approaches being studied to achieve active customer participation is one based on offering customers financial incentives through variable-price tariffs; we also contribute an effective solution to the problem of "customer herding" under such tariffs. We support our contributions with experimental results from simulations based on real-world data on an open Smart Grid simulation platform.

How many species does thePsammobates tentorius(tent tortoise) species complex (Reptilia, Testudinidae) comprise? A taxonomic solution potentially applicable to species complexes

We examined morphometric differentiation in the highly polymorphic and taxonomically confusing Psammobates tentorius (tent tortoise) species complex in southern Africa, using morphological data together with previously published DNA sequence and microsatellite DNA data. We used the approximate Bayesian computation-based simulation analysis to test alternative phylogenetic hypotheses supported by different markers, using a total evidence dataset for the tent tortoise species complex. The results supported a scenario, which is better and more inclusive in explaining its genealogical history. Our total evidence-based Bayesian BPP species delimitation analysis (mtDNA + nDNA + morphology) suggested a seven species scheme should be applied to the P. tentorius species complex. Nonetheless, based on comparative results obtained from sequence, microsatellite, ecological niche, and morphological data, a four-species scheme (among the seven mtDNA clades) appears to be the best taxonomic solution for the systematic puzzle of the P. tentorius species complex, namely, “C1 + C4 + C5 + C7,” “C3,” “C2,” and “C6.” We detected several possible hybridizations between C1 and C2 in their intergradation zone that confirmed the possible cross-over between them. Lastly, we provide a summarized flow chart of the analyses carried out for determining the optimal taxonomic solution for this phenotypically difficult group, as it may also be useful for resolving complex taxonomic issues in other species groups.

Adaptive network reliability analysis: Methodology and applications to power grid

Flow network models can capture the underlying physics and operational constraints of many networked systems including the power grid and transportation and water networks. However, analyzing systems’ reliability using computationally expensive flow-based models faces substantial challenges, especially for rare events. Existing actively trained meta-models, which present a new promising direction in reliability analysis, are not applicable to networks due to the inability of these methods to handle high-dimensional problems as well as discrete or mixed variable inputs. This study presents the first Adaptive surrogate-based Network Reliability (ANR) analysis through integration of Bayesian Additive Regression Trees (BART) and Monte Carlo simulation (MCS). An active learning method is developed that identifies the most valuable training samples based on the credible intervals derived by BART over the space of predictor variables as well as the proximity of the points to the estimated limit state. Benchmark power grids including IEEE 30, 57, 118, and 300-bus systems and their power flow models for cascading failure analysis are considered to investigate ANR-BART, MCS, subset simulation, and passively-trained optimal BART and deep neural networks. Results indicate that ANR-BART is robust and yields accurate estimates of network failure probability, while significantly reducing the computational cost of reliability analysis.

Inferring species absence from zero‐sighting records using analytical Bayesian models with population growth

Abstract The eradication of invasive species and surveillance to detect new incursions are important for protecting native biodiversity and agricultural productivity, and are being applied across increasingly large areas due to improvements in eradication tools and funding commitments. For an effective and cost‐efficient assessment of eradication success or population absence, quantitative frameworks play a critical role, with many current methods relying on Bayesian stochastic models to simulate the monitoring and detection processes. While flexible, Bayesian simulation models of monitoring systems can be computationally expensive, particularly when applied over large areas or when trying to capture rare events. In addition, it can be difficult to gain insight into system behaviour from large simulation models. Here, we develop analytical solutions for the posterior distributions of these simulation models and derive expressions for statistics of interest, such as the probability of pest absence and population size, given no detections. Solutions are fast and simple to apply and explicitly expose the nonlinear interactions between system drivers—prior assumptions, population growth and detection processes. Using an example application, we demonstrate that solutions are equivalent to published simulation results, with the potential to simplify and extend current analysis. We also show that model results without population growth, results with deterministic growth and results with stochastic growth can be quite different, with the potential to affect management decisions. Analytical solutions for the posterior distributions of these Bayesian models offer a powerful and efficient means of assessing population absence following eradication or surveillance programmes, which complements current simulation‐based methods.

Dynamic probabilistic risk assessment of decision-making in emergencies for complex systems, case study: Dynamic positioning drilling unit

Decision-making in emergency situations is a risky and uncertain process due to the limited information and lack of time. Some key problem parameters, such as the time required to complete important response tasks, must be estimated and are therefore prone to errors. Other parameters, such as the probability of occurrence of a consequential event, will typically change as the response operation progresses. As a result, there should be a dynamic probabilistic risk assessment framework to assess the risk level of decision scenarios and facilitate the decision-making process.In this paper, a methodology for dynamic probabilistic risk assessment of decision making in emergencies for complex marine systems is proposed. In this method, a dynamic event sequence diagram is introduced that helps to quantify events probabilities as a function of time, as well as environmental and operational variables, considering events interdependencies and uncertainties. In addition, the effects of time required11Time required refers to the time needed to perform each level of decision-making process (detection, diagnosis, decision-making, execution). and time available22Time available is the time remaining before an accident happens in a system. It is derived from the dynamic simulator of the system. The dynamic simulator calculates the time remaining before a collision based on the system components status, operation and environmental conditions at the time of incident. for performing a decision in emergency are considered in the risk model. In this methodology, probabilistic models including Bayesian network and Monte Carlo simulation are utilized to quantify the uncertain behavior of the decision-making process in complex marine systems.A computational study is also conducted to evaluate the methodology performance, in terms of effectiveness and efficiency. Computational results show that the proposed approach can obtain optimal solutions for large and practical problem sizes.

Species cohesion of an extremophyte (Carex angustisquama, Cyperaceae) in solfatara fields maintained under interspecific natural hybridization.

Hybridization is the main driver of plant diversification, and gene flow via hybridization has multifaceted effects on plant evolution. Carex angustisquama is an extremophyte that grows on soils heavily acidified by volcanism. Despite its habitat distinct from that of other species, this species is known to form interspecific hybrids, implying interspecific gene flow. It is crucial to verify the extent and direction of interspecific gene flow between C. angustisquama and closely related species to understand the evolutionary process of an extremophyte in solfatara fields. In this study, expressed sequence tag-simple sequence repeat markers were utilized to infer the extent and direction of interspecific gene flow between C. angustisquama and closely related species. Bayesian clustering and simulation analyses revealed that all individuals of the three hybrid species were classified into the first hybrid generation or first backcross to C. angustisquama; therefore, current interspecific gene flow is limited. Moreover, in the Bayesian inference of historical gene flow based on multispecies samples, the model that assumed no interspecific gene flow was the most strongly supported across all species pairs, including phylogenetically close but ecologically distinctive species pairs. Our results revealed that interspecific gene flow between C. angustisquama and its related species has been limited both currently and historically. Moreover, our results of Bayesian inference of historical gene flow indicated that extrinsic, rather than intrinsic, factors probably act as isolating barriers between Carex species, with hybrid breakdown via microhabitat segregation being the probable potential barrier. Overall, our findings provide insights into the evolutionary process of an extremophyte in solfatara fields and offer an important example of the mechanisms of diversification of the speciose genus Carex.

A Bayesian Spatio-Temporal Analysis of Malaria in the Greater Accra Region of Ghana from 2015 to 2019.

The Greater Accra Region is the smallest of the 16 administrative regions in Ghana. It is highly populated and characterized by tropical climatic conditions. Although efforts towards malaria control in Ghana have had positive impacts, malaria remains in the top five diseases reported at healthcare facilities within the Greater Accra Region. To further accelerate progress, analysis of regionally generated data is needed to inform control and management measures at this level. This study aimed to examine the climatic drivers of malaria transmission in the Greater Accra Region and identify inter-district variation in malaria burden. Monthly malaria cases for the Greater Accra Region were obtained from the Ghanaian District Health Information and Management System. Malaria cases were decomposed using seasonal-trend decomposition, based on locally weighted regression to analyze seasonality. A negative binomial regression model with a conditional autoregressive prior structure was used to quantify associations between climatic variables and malaria risk and spatial dependence. Posterior parameters were estimated using Bayesian Markov chain Monte Carlo simulation with Gibbs sampling. A total of 1,105,370 malaria cases were recorded in the region from 2015 to 2019. The overall malaria incidence for the region was approximately 47 per 1000 population. Malaria transmission was highly seasonal with an irregular inter-annual pattern. Monthly malaria case incidence was found to decrease by 2.3% (95% credible interval: 0.7–4.2%) for each 1 °C increase in monthly minimum temperature. Only five districts located in the south-central part of the region had a malaria incidence rate lower than the regional average at >95% probability level. The distribution of malaria cases was heterogeneous, seasonal, and significantly associated with climatic variables. Targeted malaria control and prevention in high-risk districts at the appropriate time points could result in a significant reduction in malaria transmission in the Greater Accra Region.

Relationship between lean tools and operational and environmental performance by integrated ISM–Bayesian network approach

PurposeExisting studies suggested that there is a nonlinear relationship between lean production adoption and organizational performance. Lean production adoption is a gradual process, and the application status of lean tools will affect enterprise performance. The existing literature has insufficiently explored the nonlinear relationship of the lean tools application status on operational performance and environmental performance using the same theoretical framework. A combination approach of interpretative structural modeling (ISM) and Bayesian networks was proposed in this paper, which was used to analyze the complex relationship between lean tools application status with operational and environmental performance.Design/methodology/approachISM was used to analyze the inter-relationship of 17 lean tools identified from the lean literature and construct the lean tools structure model providing reference for building Bayesian network. By calculating the prior and conditional probabilities within the lean tools and between the lean tools with the operational and environmental performance, a Bayesian simulation model was constructed and used to analyze the performance outcomes under different lean tools application status.FindingsThe performance simulation result – representing by the probability of three performance levels as good, average and poor – shows inconsistent changes with the changing of lean tools application status. By comparing the changes of operational performance and environmental performance, it can be found that environmental performance is less sensitive to the change of lean tools application status than operational performance.Originality/valueUsing the integrated ISM–Bayesian network approach, the results indicated a nonlinear relationship between lean tools with operational and environmental performance and provided a reference for the exploration of the nonlinear relationship between lean tools and performance. This research further calls for exploring the S-curve relationship between lean tools and environmental performance.