Statistical Decision Research Articles

A Likelihood Perspective on Dose-Finding Study Designs in Oncology.

Dose-finding studies in oncology often include an up-and-down dose transition rule that assigns a dose to each cohort of patients based on accumulating data on dose-limiting toxicity (DLT) events. In making a dose transition decision, a key scientific question is whether the true DLT rate of the current dose exceeds the target DLT rate, and the statistical question is how to evaluate the statistical evidence in the available DLT data with respect to that scientific question. This article introduces generalized likelihood ratios (GLRs) that can be used to measure statistical evidence and support dose transition decisions. Applying this approach to a single-dose likelihood leads to a GLR-based interval design with three parameters: the target DLT rate and two GLR cut-points representing the levels of evidence required for dose escalation and de-escalation. This design gives a likelihood interpretation to each existing interval design and provides a unified framework for comparing different interval designs in terms of how much evidence is required for escalation and de-escalation. A GLR-based comparison of commonly used interval designs reveals important differences and motivates alternative designs that reduce over-treatment while maintaining MTD estimation accuracy. The GLR-based approach can also be applied to a joint likelihood based on a nonparametric (e.g., isotonic regression) model or a parametric model. Simulation results indicate that the isotonic GLR performs similarly to the single-dose GLR but the GLR based on a parsimonious model can improve MTD estimation when the underlying model is correct.

Административные решения алгоритмов

Examples of algorithms being involved in administrative practice are multiplying. However, the process of their use remains unsettled. For the legal evaluation of the results of algorithms’ decisions and subsequent legal regulation, it is important to distinguish between automated decision-making systems and machine learning systems. But if the prospects for the use of algorithms by both courts and the executive branch seem obvious, such use should certainly take into account possible risks and disadvantages. This is especially true for machine learning algorithms. First, human decision-making inevitably leads to the problem of scoring, which has not only an ethical but also a legal dimension. Second, there is the problem of algorithm errors. A statistical decision, even based on a working algorithm, can be wrong. Statistics using probability calculus, even when applied to a mass of cases, leads to probable rather than certain conclusions. This means that the personalized decision of a machine learning algorithm cannot be final, but must be “sanctioned” by a human. Hence the inevitability of human control.

A hybrid binary logical regression -gradient decent approach for dynamic cooperative spectrum sensing in CRN

ABSTRACT This paper proposes hybrid binary logical regression with a gradient decent optimisation (GDO) algorithm for spectrum sensing. From multiple secondary users (SU) systems, all signal vectors are collected with cognitive radios (CRs), and the features associated with the signal vector are considered for decision statistics. The decision statistics are modelled with a hybrid binary logical regression with gradient decent (BLR-GD) algorithm, which improves efficiency. The gradient decent (GD) is accomplished with binary logical regression (BLD), in which the regression coefficients are calculated efficiently. For evaluating the performance of the proposed algorithm, the spectrum sensing is evaluated in low signal-to-noise ratio (SNR) and high SNR scenarios. The detection probability, accuracy, F-measure and ROC curve performance of the proposed approach will outperform other existing approaches. The latency value of the proposed approach has reached 0.009 ms, which shows the efficiency of the proposed approach with 5 G communication features.

Bootstrapped Edge Count Tests for Nonparametric Two-Sample Inference Under Heterogeneity

Nonparametric two-sample testing is a classical problem in inferential statistics. While modern two-sample tests, such as the edge count test and its variants, can handle multivariate and non-Euclidean data, contemporary gargantuan datasets often exhibit heterogeneity due to the presence of latent subpopulations. Direct application of these tests, without regulating for such heterogeneity, may lead to incorrect statistical decisions. We develop a new nonparametric testing procedure that accurately detects differences between the two samples in the presence of unknown heterogeneity in the data generation process. Our framework handles this latent heterogeneity through a composite null that entertains the possibility that the two samples arise from a mixture distribution with identical component distributions but with possibly different mixing weights. In this regime, we study the asymptotic behavior of weighted edge count test statistic and show that it can be effectively recalibrated to detect arbitrary deviations from the composite null. For practical implementation we propose a Bootstrapped Weighted Edge Count test which involves a bootstrap-based calibration procedure that can be easily implemented across a wide range of heterogeneous regimes. A comprehensive simulation study and an application to detecting aberrant user behaviors in online games demonstrates the excellent non-asymptotic performance of the proposed test. Supplementary materials for this article are available online.

WELFARE ANALYSIS VIA MARGINAL TREATMENT EFFECTS

We consider a causal structure with endogeneity, i.e., unobserved confoundedness, where an instrumental variable is available. In this setting, we show that the mean social welfare function can be identified and represented via the marginal treatment effect as the operator kernel. This representation result can be applied to a variety of statistical decision rules for treatment choice, including plug-in rules, Bayes rules, and empirical welfare maximization rules. Focusing on the application of the empirical welfare maximization framework, we provide convergence rates of the worst-case average welfare loss (regret).

Reforming military organisational culture: an empirical study of the Army in Taiwan

ABSTRACT This study investigates the behaviour patterns of four key roles within Army units – policy initiators, policymakers, implementers (or supervisors), and policy beneficiaries – during the development of new policies, defined by the Army as those significantly diverging from previous practices. The research finds that when policymakers and implementers align with initiators and adopt a policy beneficiary-centred approach throughout planning, execution, and evaluation, there is a positive correlation with the policy’s long-term sustainability. Conversely, when policymakers operate within an authoritarian or hierarchical culture, focusing on the demands of initiators rather than addressing the needs of the policy beneficiaries, the policy outcomes often fall short. Through in-depth interviews with senior officers and surveys of Army personnel regarding policies that promote voluntary activities for soldiers, the study identifies these roles and analyzes their dynamics. Statistical methods, including T-tests, R programming (Central Limit Theorem, Monte Carlo Method), and decision tree analysis, validate the hypotheses. The study’s findings contribute to existing literature by offering a “gear model” centered on policy beneficiaries, providing a practical framework for future policy development. This model underscores the importance of considering all roles in policy formulation to ensure effective and sustainable outcomes.

Theories and hypotheses: The forgotten plane of the multiverse

Multiverse analyses—the systematic examination of the effects of decisions that researchers can take over the course of a research project—became more common in recent psychophysiological research. However, multiverse analyses in psychophysiology almost exclusively focus on methodological and statistical decisions that can have a considerable impact on the findings. The role of the conceptual multiverse regarding theory-related research decisions is largely ignored. We argue that the choice of a theory that guides hypotheses, study design, measurement methods, and statistical analyses is the first plane of the psychophysiological multiverse. Depending on the chosen theoretical framework, researchers will choose different methods, and statistical analyses will emphasize specific aspects. We illustrate this process with a research example studying the effects of task difficulty manipulations on cardiovascular effects reflecting effort. We argue in favor of an approach that explicitly acknowledges the various theoretical accounts that can constitute the background of a study and demonstrate how a comparative analytical approach can provide a comprehensive multiverse without increasing type I error due to mere exploration.

Self-Supervised Marine Noise Learning with Sparse Autoencoder Network for Generative Target Magnetic Anomaly Detection

As an effective physical field feature to perceive ferromagnetic targets, magnetic anomaly is widely used in covert marine surveillance tasks. However, its practical usability is affected by the complex marine magnetic noise interference, making robust magnetic anomaly detection (MAD) quite a challenging task. Recently, learning-based detectors have been widely studied for the discrimination of magnetic anomaly signal and achieve superior performance than traditional rule-based detectors. Nevertheless, learning-based detectors require abundant data for model parameter training, which are difficult to access in practical marine applications. In practice, target magnetic anomaly data are usually expensive to acquire, while rich marine magnetic noise data are readily available. Thus, there is an urgent need to develop effective models to learn discriminative features from the abundant marine magnetic noise data for newly appearing target anomaly detection. Motivated by this, in this paper we formulate MAD as a single-edge detection problem and develop a self-supervised marine noise learning approach for target anomaly classification. Specifically, a sparse autoencoder network is designed to model the marine noise and restore basis geomagnetic field from the collected noisy magnetic data. Subsequently, reconstruction error of the network is used as a statistical decision criterion to discriminate target magnetic anomaly from cluttered noise. Finally, we verify the effectiveness of the proposed approach on real sea trial data and compare it with seven state-of-the-art MAD methods on four numerical indexes. Experimental results indicate that it achieves a detection accuracy of 93.61% and has a running time of 21.06 s on the test dataset, showing superior MAD performance over its counterparts.

Anecdotes impact medical decisions even when presented with statistical information or decision aids

People are inundated with popular press reports about medical research concerning what is healthy, get advice from doctors, and hear personal anecdotes. How do people integrate conflicting anecdotal and statistical information when making medical decisions? In four experiments (N = 4126), we tested how people use conflicting information to judge the efficacy of artificial and real medical treatments. Participants read an anecdote from someone in a clinical trial, or who had undergone a medical treatment previously, for whom the medical treatment was ineffective. We found that reading anecdotes for either artificial or real medical treatments shifted participants’ beliefs about the efficacy of a medical treatment. We observed this result even when the anecdote was uninformative, was paired with an icon array, or when participants were provided with thorough medical decision aids about reproductive health procedures. Our findings highlight the pervasive effect of anecdotes on medical decision making.

DeepQCD: An end-to-end deep learning approach to quickest change detection

This paper aims to generalize the quickest change detection (QCD) framework via a data-driven approach. To this end, a generic neural network architecture is proposed for the QCD task, composed of feature transformation, recurrent, and dense layers. The neural network is trained end-to-end to learn the change detection rule directly from data without needing the knowledge of probabilistic data models. Specifically, the feature transformation layers can perform a broad range of operations including feature extraction, scaling, and normalization. The recurrent layers keep an internal state summarizing the time-series data seen so far and update the state as new information comes in. Finally, the dense layers map the internal state into a decision statistic, defined as the posterior probability that a change has taken place. Comparisons with the existing model-based QCD algorithms demonstrate the power of the proposed data-driven approach, called DeepQCD, under several scenarios including transient changes and temporally correlated data streams. Experiments with real-world data illustrate superior performance of DeepQCD compared to state-of-the-art algorithms in real-time anomaly detection over surveillance videos and real-time attack detection over Internet of Things (IoT) networks.

New methods for statistical decision making in conditions of a limited volume of observations and with a prioriy parametric uncertainty

A new generalized adaptive algorithm for learning to make statistical decisions for exponential families of distributions with a priori parametric uncertainty in conditions of small samples has been developed. A generalized decision rule is presented, obtained by estimating unknown parameters of distributions, as well as a decision rule that satisfies the necessary optimality conditions: constancy of the average probability of a type I error and unbiasedness. Specific decision procedures for partial distributions obtained from a generalized algorithm are considered. Numerical examples are given. The effectiveness of the developed optimal procedure for small samples is shown.

Application of Bayesian Decision Analysis to Estimate Occupational Noise Levels from Limited Exposure Data

In recent years, Bayesian statistical modeling approaches have emerged as valuable tools in Industrial Hygiene (IH), particularly in situations with limited exposure data. This paper delves into the application of Bayesian Statistical Models, specifically Bayesian Decision Analysis (BDA), to analyze occupational noise exposure data within two Similar Exposure Groups (SEGs) of groundskeeping workers, addressing the pervasive issue of high noise levels exceeding 85 dBA. The primary aim is to estimate exposure levels based on the location of the exposure profiles for the SEGs within the AIHA® Exposure Control Categories (ECCs) 0-4, later modified and expanded to AIHA-ECC 0-5. This study employs BDA to estimate noise exposures among groundskeepers, emphasizing the scarcity of literature on BDA in noise exposure rating. Groundskeepers, facing potential risk of hearing impairment due to prolonged exposure, constitute a crucial and critical demographic, with nearly one million individuals in the United States alone. Noise data from the two SEGs was analyzed by using the Exposure Assessment Strategies Committee—EASC- AIHA® IHData Analyst for BDA modeling, complemented with the AIHA IHSTAT™ for certainty rating. The resulting posterior graphs were utilized to categorize exposure profiles into respective AIHA ECCs relative to noise OEL. These findings provide valuable insights, indicating a posterior probability of approximately 43.5% and 56.5% with 95% confidence that noise exposure levels fall within AIHA ECC 3 and AIHA ECC 4, respectively. However, while the 95% percentile decision statistics suggest exposure values lower than the OEL, the Upper Tolerance Limit (UTL) significantly surpass the OEL indicating low certainty regarding these exposure values for employees. Notably, the UTLs suggest that the SEGs are experiencing noise levels above the legally required 90 dBA for more than 5% of the time, which is an unacceptable scenario. Recommendations include implementing protective strategies such as regular training, surveillance, and monitoring, alongside engineering control strategies and mandatory use of personal protective equipment. These results underscore the critical need for refining judgments about noise exposures based on variability within and between employees, suggesting the use of additional statistical tools such as ANOVA (single-multivariate), MATLAB, and Python.

Model selection of GLMMs in the analysis of count data in single-case studies: A Monte Carlo simulation.

Generalized linear mixed models (GLMMs) have great potential to deal with count data in single-case experimental designs (SCEDs). However, applied researchers have faced challenges in making various statistical decisions when using such advanced statistical techniques in their own research. This study focused on a critical issue by investigating the selection of an appropriate distribution to handle different types of count data in SCEDs due to overdispersion and/or zero-inflation. To achieve this, I proposed two model selection frameworks, one based on calculating information criteria (AIC and BIC) and another based on utilizing a multistage-model selection procedure. Four data scenarios were simulated including Poisson, negative binominal (NB), zero-inflated Poisson (ZIP), and zero-inflated negative binomial (ZINB). The same set of models (i.e., Poisson, NB, ZIP, and ZINB) were fitted for each scenario. In the simulation, I evaluated 10 model selection strategies within the two frameworks by assessing the model selection bias and its consequences on the accuracy of the treatment effect estimates and inferential statistics. Based on the simulation results and previous work, I provide recommendations regarding which model selection methods should be adopted in different scenarios. The implications, limitations, and future research directions are also discussed.

CFAR Target Detector in Synthetic Aperture Radar

Introduction. Constant false alarm rate (CFAR) detectors have found application in synthetic aperture radar (SAR) systems. The operating principle of a classic cell averaging detector (CA-CFAR detector) is based on comparing the decision statistics in the test resolution element with an adaptive threshold, which is calculated from signals in the reference cells. The decision statistic is an estimate of the signal power. Therefore, target signal detection is based on the brightness contrast of the test and reference resolution cells. Such a detector is optimal provided that the noise background is homogeneous. In cases where the background homogeneity is violated, the quality of detection deteriorates. There are several known methods for improving the quality of detection (GO-CFAR, SO-CFAR, OS-CFAR, etc.). However, the precise principle of detection by brightness contrast in such CFAR detectors remains unchanged.Aim. To synthesize a CFAR detector that uses not only the brightness contrast between the test and reference resolution cells, but also the spectral differences of the signals.Materials and methods. The proposed CFAR detector uses estimates of the algebraic moments of the power spectral density of signals in range cells, based on which three decision statistics are calculated containing information about the power, the position of the energy center, and the width of the signal spectrum. The decision about the presence of a target in the test cell is carried out according to the 2/3 rule (2 threshold overshoots out of 3 comparisons).Results. A comparison of the proposed detector with the SO-CFAR detector, performed by computer simulation, showed that, under a signal-to-clutter ratio of -6 dB and a false alarm probability of 10-4, the detection probability of the proposed detector was 0.933 versus 0.708 for the SO-CFAR detector.Conclusion. The article proposes a three-parameter CFAR detector for a synthetic aperture radar system, in which the decision on the presence of a target in the test cell is made via estimation of the first three algebraic moments of the signal spectrum. The synthesized detection algorithm can also be used when detecting moving targets in SAR.

Comparison of MAGIQ, MABAC, MARCOS, and MOORA Methods in Multi-Criteria Problems

Determining the best alternative from many criteria is one of the core problems in decision making, both routine and non-routine problems. One of them is in the problem of determining egg suppliers. Eggs are one of the basic needs of the community so that the demand for eggs is always increasing, this makes the emergence of many egg agents in distributing and fulfilling needs. Selective and careful selection is needed in order to get a supplier that meets the desired expectations. Problems then arise in the selection of egg suppliers that are not in accordance with the expectations of the manager. In determining egg suppliers that have been carried out by UD Taluh Subur, only by means of a simple comparison between several factors such as price, production quantity, and quality without considering other factors. In addition to this, business managers have limited knowledge in statistical and business decision making. To optimize the supplier selection process, a Decision Support System can be used to help provide recommendations for selecting prospective suppliers of fixed eggs. Based on the situation of decision makers who have limited knowledge in statistical decision making, the MAGIQ method is suitable for weighting. To provide a more accurate ranking, additional methods such as the MABAC, MARCOS, and MOORA methods are used. The purpose of this research is to focus on which method is most recommended for the case study faced in the research based on the analysis results of the sensitivity test. The results of the sensitivity test show that the MAGIQ-MABAC method has the highest value of 4.42737%, then the MAGIQ-MOORA method with a value of 2.34415% and the MAGIQ-MARCOS method with a value of 0.45729%.

Some Skorohod-type results

AbstractLet S be a metric space, $$g:S\rightarrow \mathbb {R}$$ g : S → R a Borel function, and $$(\mu _n:n\ge 0)$$ ( μ n : n ≥ 0 ) a sequence of tight probability measures on $$\mathcal {B}(S)$$ B ( S ) . If $$\mu _n=\mu _0$$ μ n = μ 0 on $$\sigma (g)$$ σ ( g ) , there are S-valued random variables $$X_n$$ X n , all defined on the same probability space, such that $$X_n\sim \mu _n$$ X n ∼ μ n and $$g(X_n)=g(X_0)$$ g ( X n ) = g ( X 0 ) for all $$n\ge 0$$ n ≥ 0 . Moreover, $$X_n\overset{a.s.}{\longrightarrow }X_0$$ X n ⟶ a . s . X 0 if and only if $$E_{\mu _n}(f\mid g)\,\overset{\mu _0-a.s.}{\longrightarrow }\,E_{\mu _0}(f\mid g)$$ E μ n ( f ∣ g ) ⟶ μ 0 - a . s . E μ 0 ( f ∣ g ) for each $$f\in C_b(S)$$ f ∈ C b ( S ) . This result, proved in Pratelli and Rigo (J Theoret Probab 36:372-389, 2023) , is the starting point of this paper. Three types of contributions are provided. First, $$\sigma (g)$$ σ ( g ) is replaced by an arbitrary sub-$$\sigma $$ σ -field $$\mathcal {G}\subset \mathcal {B}(S)$$ G ⊂ B ( S ) . Second, the result is applied to some specific frameworks, including equivalence couplings, total variation distances, and the decomposition of cadlag processes with finhite activity. Third, following Hansen et al. (Tempered Bayesian analysis, Unpublished manuscript, 2024), the result is extended to models and kernels. This extension has a fairly natural interpretation in terms of decision theory, mass transportation and statistics.

Does the lived experience of gambling accord with quantitative self-report scores of gambling-related harm?

A broad quantitative literature has explored the extent and distribution of gambling-related harm. However, any quantitative measure involves a number of statistical decisions around item selection and weighting that may affect its ability to provide an accurate summary of a gambler’s lived experience. This may especially be an issue with a condition as varied and multifaceted as gambling-related harm. The present research therefore used qualitative methods to validate the categorization of gamblers into four levels of harm via the Gambling Harms Scale (10-items) (GHS-10) through an analysis of 30 semi-structured interviews with gamblers. Results showed that unharmed gamblers saw gambling as just another leisure activity, which relieved stress and brought them closer to other people. Low harm gamblers were similar but could experience emotional stresses over their level of gambling expenditure. Just under half of all moderate harm gamblers experienced occasional severe financial impacts and emotional stresses from their gambling. Finally, all high harm gamblers experienced chronic financial impacts and emotional stresses, which spilled over into relationship problems for three quarters of this group, and negative impacts on health or work/study for around half of this group. These results showed that the severity of participants’ lived experience of gambling increased with their GHS-10 score, providing a qualitative validation for this quantitative self-report measure. This qualitative validation for a quantitative scale is argued to be a promising avenue for future gambling research.

Effect of street trees shade on perceived thermal comfort in a south temperate climate: The sidewalks of Montevideo (Uruguay)

The use of vegetation in cities is one of the most promising strategies for urban climate change adaptation and mitigation. Tree shade influences heat storage from surfaces reducing long wave radiation emission which directly affects people. People 's heat perception depends more on insolation and the temperature of surrounding objects than on air temperature itself. There is a need for analyzes that include the combined effects of physical and human variables on thermal comfort, as well as location-based studies to address its climatic and social conditions. In order to compare the effect of the trees on microenvironmental temperature and perceived thermal comfort, we measured physical parameters and performed structured interviews on three downtown streets of Montevideo, Uruguay, which had sections with and without trees on four dates during the summer. Generally, people surveyed under both treatments stated they did not feel fully comfortable due to summer heat, but the proportion of people who stated feeling in thermal comfort under tree shade was more than double than the unshaded sections.The seasonal ARIMA analysis supported that the tree shade reduced the microenvironmental temperature by its effect on radiant temperature. By using a statistical decision tree methodology that combines all the variables in the same analysis, we found a greater impact of physical variables than personal variables on people's thermal comfort and thermal preferences. We also identified gender as a significant variable that affects people's thermal preferences, where 46.4 % of females preferred a slightly colder environment.

Limits on the accuracy of contact inhibition of locomotion.

Cells that collide with each other repolarize away from contact, in a process called contact inhibition of locomotion (CIL), which is necessary for correct development of the embryo. CIL can occur even when cells make a micron-scale contact with a neighbor-much smaller than their size. How precisely can a cell sense cell-cell contact and repolarize in the correct direction? What factors control whether a cell recognizes it has contacted a neighbor? We propose a theoretical model for the limits of CIL where cells recognize the presence of another cell by binding the protein ephrin with the Eph receptor. This recognition is made difficult by the presence of interfering ligands that bind nonspecifically. Both theoretical predictions and simulation results show that it becomes more difficult to sense cell-cell contact when it is difficult to distinguish ephrin from the interfering ligands, or when there are more interfering ligands, or when the contact width decreases. However, the error of estimating contact position remains almost constant when the contact width changes. This happens because the cell gains spatial information largely from the boundaries of cell-cell contact. We study using statistical decision theory the likelihood of a false-positive CIL event in the absence of cell-cell contact, and the likelihood of a false negative where CIL does not occur when another cell is present. Our results suggest that the cell is more likely to make incorrect decisions when the contact width is very small or so large that it nears the cell's perimeter. However, in general, we find that cells have the ability to make reasonably reliable CIL decisions even for very narrow (micron-scale) contacts, even if the concentration of interfering ligands is ten times that of the correct ligands.

A hierarchical recursive feature elimination algorithm to develop brain computer interface application of user behavior for statistical reasoning and decision making

BackgroundWith the aid of a brain computer interface (BCI), users can communicate and receive signals wirelessly or over wired connections to operate smart devices. A BCI classifier's architecture is quite difficult since numerous elements should be combined. These elements are made up of brain signals, which also include high levels of weak sounds that could provide reliable participant recordings of daily activities. We must use computer vision techniques to create a model in order to control those information. The high dimension and volume of signals present the classification classifier with its primary obstacles. New methodDue to this, we extracted and classified the brain activity in this study, and we also presented a novel hierarchical recursive feature elimination method that we refer to as HRFE embracing noisy additions. HRFE makes a variety of categorization suggestions to eliminate bias in classifying BCI systems of different types. We put the HRFE to the test on two BCI signal data sets—specifically, dataset I and BCI contests III—using shallow and deep convolution network classification techniques. Just a grid of assets is used to create electrocorticography (ECoG) signals on the contralateral (right) motor cortex, and these signals are recorded in the BCI contests III database. ResultsUsing ECoG signals, we choose the top 20 features that have the biggest effects on distortion and classification selection. Comparison with existing methodsThe simulation findings show that HRFE has a significant computer vision enhancement when compared to comparable feature selection methods in the literature, particularly for ECoG signal, which achieves about 93% reliability.