Statistical Implications Research Articles

A more holistic view of the logarithmic dose-response curve offers greater insights into insulin responses

The stimulus-response curve is usually modeled by the Hill function due to its simplicity and clear molecular mechanisms (Michaelis-Menten type of kinetics). Unfortunately, the mechanisms do not explain why the stimulus is ubiquitously measured by logarithmic dose rather than the dose itself and why the log(dose)-response curve possesses such fine properties as symmetry and wide adjustability. Here, the dose response is considered from a holistic perspective spanning multiple biological levels from molecules to the whole organism, which reveals that an appropriate model for log(dose) response is the cumulative normal distribution (CND) function, which had only statistical implication previously but now possess mechanistic-statistical duality. The present CND model establishes a connection between single-cell all-or-none responses and the graded response at the tissue/organism level, reveals the raison d'être of the logarithmic transformation, explains why log(dose)-response curve possesses many fine properties, and reveals new mechanisms of tissue/organism dose-response, including homogeneity-induced sensitivity. It also provides new insights into vital biological processes, such as the insulin dose response.

Extropy and statistical features of dual generalized order statistics’ concomitants arising from the Sarmanov family

Abstract In this study, we disclose several statistical properties of concomitants of dual generalized order statistics (DGOSs) under a generic setting from the Sarmanov family of bivariate distributions. For this family, cross-moments and joint distributions of concomitants of DGOSs are explored. These results' implications for order statistics and record values are examined. Extropy and cumulative residual extropy (CRE), two well-known information measures, are also investigated. This study offers a few beautiful symmetrical relationships that these inaccuracy measurements satisfy. In addition, based on the concomitants of DGOSs, the issue of estimating the negative cumulative residual extropy (NCRE), empirical NCRE and NCE are investigated using the empirical technique. Lastly, a set of bivariate data from the real world is examined.

Optimal survival analyses with prevalent and incident patients.

Period-prevalent cohorts are often used for their cost-saving potential in epidemiological studies of survival outcomes. Under this design, prevalent patients allow for evaluations of long-term survival outcomes without the need for long follow-up, whereas incident patients allow for evaluations of short-term survival outcomes without the issue of left-truncation. In most period-prevalent survival analyses from the existing literature, patients have been recruited to achieve an overall sample size, with little attention given to the relative frequencies of prevalent and incident patients and their statistical implications. Furthermore, there are no existing methods available to rigorously quantify the impact of these relative frequencies on estimation and inference and incorporate this information into study design strategies. To address these gaps, we develop an approach to identify the optimal mix of prevalent and incident patients that maximizes precision over the entire estimated survival curve, subject to a flexible weighting scheme. In addition, we prove that inference based on the weighted log-rank test or Cox proportional hazards model is most powerful with an entirely prevalent or incident cohort, and we derive theoretical formulas to determine the optimal choice. Simulations confirm the validity of the proposed optimization criteria and show that substantial efficiency gains can be achieved by recruiting the optimal mix of prevalent and incident patients. The proposed methods are applied to assess waitlist outcomes among kidney transplant candidates.

Statistical implication analysis: a novel approach to understand the reciprocal relationships between outcomes in early psychosis.

Patients can respond differently to intervention in the early phase of psychosis. Diverse symptomatic and functional outcomes can be distinguished and achieving one outcome may mean achieving another, but not necessarily the other way round, which is difficult to disentangle with cross-sectional data. The present study's goal was to evaluate implicative relationships between diverse functional outcomes to better understand their reciprocal dependencies in a cross-sectional design, by using statistical implication analysis (SIA). Early psychosis patients of an early intervention program were evaluated for different outcomes (symptomatic response, functional recovery, and working/living independently) after 36 months of treatment. To determine which positive outcomes implied other positive outcomes, SIA was conducted by using the Iota statistical implication index, a newly developed approach allowing to measure asymmetrical bidirectional relationships between outcomes. Two hundred and nineteen recent onset patients with early psychosis were assessed. Results at the end of the three-years in TIPP showed that working independently statistically implied achieving all other outcomes. Symptomatic and functional recovery reciprocally implied one another. Living independently weakly implied symptomatic and functional recovery and did not imply independent working. The concept of implication is an interesting way of evaluating dependencies between outcomes as it allows us to overcome the tendency to presume symmetrical relationships between them. We argue that a better understanding of reciprocal dependencies within psychopathology can provide an impetus to tailormade treatments and SIA is a useful tool to address this issue in cross-sectional designs.

Implications of Water Quality Index and Multivariate Statistics for Improved Environmental Regulation in the Irtysh River Basin (Kazakhstan)

The selection of sites for permanent environmental monitoring of natural water bodies should rely on corresponding source apportionment studies. Tools like the water quality index (WQI) assessment may support this objective. This study aims to analyze a decade-long dataset of measurements of 26 chemical components at 26 observation points within the Irtysh River Basin, aiming to identify priority zones for stricter environmental regulations. It was achieved through the WQI tool integrated with geoinformation systems (GISs) and multivariate statistical techniques. The findings highlighted that both upstream sections of tributaries (Oba and Bukhtarma rivers) and the mainstream of the basin are generally in good condition, with slight fluctuations observed during flooding periods. Areas in the basin experiencing significant impacts from mining and domestic wastewater treatment activities were identified. The rivers Glubochanka (GL) and Krasnoyarka (KR) consistently experienced marginal water quality throughout the observation period. Various contaminant sources were found to influence water quality. The impact of domestic wastewater treatment facilities was represented by twofold elevated concentrations of chemical oxygen demand, reaching 22.6 and 27.1 mg/L for the KR and GL rivers, respectively. Natural factors were indicated by consistent slight exceedings of recommended calcium levels at the KR and GL rivers. These exceedances were most pronounced during the cold seasons, with an average value equal to 96 mg/L. Mining operations introduced extremal concentrations of trace elements like copper, reaching 0.046–0.051 mg/L, which is higher than the threshold by 12–13 times; zinc, which peaked at 1.57–2.96 mg/L, exceeding the set limit by almost 50–100 times; and cadmium, peaking at levels surpassing 1000 times the safe limit, reaching 0.8 mg/L. The adverse impact of mining activities was evident in the Tikhaya, Ulba, and Breksa rivers, showing similar trends in trace element concentrations. Seasonal effects were also investigated. Ice cover formation during cold seasons led to oxygen depletion and the exclusion of pollutants into the stream when ice melted, worsening water quality. Conversely, flooding events led to contaminant dilution, partially improving the WQI during flood seasons. Principal component analysis and hierarchical cluster analysis indicated that local natural processes, mining activities, and domestic wastewater discharge were the predominant influences on water quality within the study area. These findings can serve as a basis for enhanced environmental regulation in light of updated ecological legislation in Kazakhstan, advocating for the establishment of a comprehensive monitoring network and the reinforcement of requirements governing contaminating activities.

The Effect of Training on Localizing HoloLens-Generated 3D Sound Sources.

Sound localization is a crucial aspect of human auditory perception. VR (virtual reality) technologies provide immersive audio platforms that allow human listeners to experience natural sounds based on their ability to localize sound. However, the simulations of sound generated by these platforms, which are based on the general head-related transfer function (HRTF), often lack accuracy in terms of individual sound perception and localization due to significant individual differences in this function. In this study, we aimed to investigate the disparities between the perceived locations of sound sources by users and the locations generated by the platform. Our goal was to determine if it is possible to train users to adapt to the platform-generated sound sources. We utilized the Microsoft HoloLens 2 virtual platform and collected data from 12 subjects based on six separate training sessions arranged in 2 weeks. We employed three modes of training to assess their effects on sound localization, in particular for studying the impacts of multimodal error, visual, and sound guidance in combination with kinesthetic/postural guidance, on the effectiveness of the training. We analyzed the collected data in terms of the training effect between pre- and post-sessions as well as the retention effect between two separate sessions based on subject-wise paired statistics. Our findings indicate that, as far as the training effect between pre- and post-sessions is concerned, the effect is proven to be statistically significant, in particular in the case wherein kinesthetic/postural guidance is mixed with visual and sound guidance. Conversely, visual error guidance alone was found to be largely ineffective. On the other hand, as far as the retention effect between two separate sessions is concerned, we could not find any meaningful statistical implication on the effect for all three error guidance modes out of the 2-week session of training. These findings can contribute to the improvement of VR technologies by ensuring they are designed to optimize human sound localization abilities.

Open and FAIR: Trends in scientific publishing and the implications for official statistics

The FAIR data principles have emerged as a major focus in the world of scientific research data, but have not had as large an impact on official statistics. While there are good reasons for this, FAIR developments within the research community may be of interest to official statistical organizations. These include the increased availability of research data, improvements in the area of machine-actionable metadata, and a focus on provenance information which could lead to increased transparency and data quality. Some activities of interest are described as a starting point for those in official statistics who may wish to follow these developments.

NHS national data opt-outs: trends and potential consequences for health data research.

The English NHS data opt-out allows people to prevent use of their health data for purposes other than direct care. In 2021, the number of opt-outs increased in response to government-led proposals to create a centralised pseudonymised primary care record database. To describe the potential impact of NHS national data opt-outs in 2021 on health data research. We conducted a descriptive analysis of opt-outs using publicly available data and the potential consequences on research are discussed. Trends in opt-outs in England were described by age, sex, and region. Using a hypothetical study, we explored statistical and epidemiological implications of opt-outs. During the lead up to a key government-led deadline for registering opt-outs (from 31 May 2021-30 June 2021), 1 339 862 national data opt-outs were recorded; increasing the percentage of opt-outs in England from 2.77% to 4.97% of the population. Among females, percentage opt-outs increased by 83% (from 3.02% to 5.53%) compared with 76% in males (from 2.51% to 4.41%). Across age groups, the highest relative increase was among people aged 40-49 years, which rose from 2.89% to 6.04%. Considerable geographical variation was not clearly related to deprivation. Key research consequences of opt-outs include reductions in sample size and unpredictable distortion of observed measures of the frequency of health events or associations between these events. Opt-out rates varied by age, sex, and place. The impact of this and variation by other characteristics on research is not quantifiable. Potential effects of opt-outs on research and consequences for health policies based on this research must be considered when creating future opt-out solutions.

Green policies and financial development in G7 economies: An in‐depth analysis of environmental regulations and green economic growth

AbstractThis comprehensive study explores the nuanced relationship between financial development and its determinants within the G7 nations, spanning the years 1990 to 2020. Motivated by the need to understand long‐term financial trends, we meticulously analyze key variables including total natural resource rent, Environmental Policy Stringency Index, total energy consumption, green gross domestic product (GDP), and foreign direct investment inflow. Employing rigorous diagnostic tests to ensure the robustness of our findings, advanced methodologies such as “Method of Moment Quantile Regression,” along with simulations of “Bootstrap Quantile Regression," “Panel Corrected Standard Errors,” and “Feasible Generalized Least Squares” regressions uncover the statistical significance and practical implications of our results. Our pivotal findings carry substantial implications for both individual G7 member states and the collective group. Highlighting a positive correlation between stringent environmental policies, measured by the Environmental Policy Stringency Index, and financial development, our study emphasizes the imperative for these nations to align economic and environmental policies. Striking a harmonious balance between resource management and sustainable environmental regulations not only fosters financial growth but also addresses global environmental concerns. Furthermore, the adverse impact of total energy consumption on financial development underscores the urgent need for G7 nations to prioritize energy efficiency and transition to sustainable sources, aligning with the global trend towards eco‐friendly practices. In response to these critical findings, we propose actionable policy measures. To align with the growing climate crisis and standardize green finance practices, we advocate for the establishment of a jointly funded Climate Resilience and Adaptation Fund and a unified Green Bond Framework within the G7. These measures not only enhance climate resilience and streamline sustainable investments but also demonstrate the G7's collective commitment to a greener and more prosperous future.

Quantifying how much host, pathogen, and other factors affect human protective adaptive immune responses.

Recognizing the "essential" factors that contribute to a clinical outcome is critical for designing appropriate therapies and prioritizing limited medical resources. Demonstrating a high correlation between a factor and an outcome does not necessarily imply an essential role of the factor to the outcome. Human protective adaptive immune responses to pathogens vary among (and perhaps within) pathogenic strains, human individual hosts, and in response to other factors. Which of these has an "essential" role? We offer three statistical approaches that predict the presence of newly contributing factor(s) and then quantify the influence of host, pathogen, and the new factors on immune responses. We illustrate these approaches using previous data from the protective adaptive immune response (cellular and humoral) by human hosts to various strains of the same pathogenic bacterial species. Taylor's law predicts the existence of other factors potentially contributing to the human protective adaptive immune response in addition to inter-individual host and intra-bacterial species inter-strain variability. A mixed linear model measures the relative contribution of the known variables, individual human hosts and bacterial strains, and estimates the summed contributions of the newly predicted but unknown factors to the combined adaptive immune response. A principal component analysis predicts the presence of sub-variables (currently not defined) within bacterial strains and individuals that may contribute to the combined immune response. These observations have statistical, biological, clinical, and therapeutic implications.

Management and treatment outcomes of rheumatoid arthritis in the era of biologic and targeted synthetic therapies: evaluation of 10-year data from the KURAMA cohort

BackgroundAdvances in rheumatoid arthritis (RA) treatment, highlighted by biological disease-modifying antirheumatic drugs (bDMARDs) and targeted synthetic DMARDs (tsDMARDs), have altered the paradigm of RA treatment in the last decade. Therefore, real-world clinical evidence is needed to understand how treatment strategies and outcomes have changed.MethodsUsing an observational cohort of RA from 2012 to 2021, we collected cross-sectional data of RA patients annually to analyze a trend in RA management. For patients who initiated b/tsDMRDs, we evaluated treatment outcomes between b/tsDMARDs. Mixed-effect models were applied to examine the statistical implications of changes over time in treatment outcomes with a background adjustment.ResultsWe analyzed annual cross-sectional data from 5070 patients and longitudinal data from 1816 patients in whom b/tsDMARDs were initiated between 2012 and 2021. b/tsDMARD use increased, whereas glucocorticoid use decreased from 2012 to 2021. Disease activity and functional disability measures improved over time. The percentage of tsDMARD prescriptions considerably increased. All b/tsDMARDs showed clinical improvements in disease activity and functional disability. Statistically, TNFi showed better short-term improvements in b/tsDMARD-naïve patients, while IL6Ri demonstrated significant long-term benefits. IL6Ri had better retention rates in switched patients. After adjustment for patient characteristics, the annual change of RA disease activity and functional disability fared significantly better from 2012 to 2021.ConclusionsWith the development of new RA therapeutics, overall treatment outcomes advanced in the past decade.

Bridging the gap: Assessing death certification competency in Bulgarian healthcare education

BACKGROUND: In Bulgaria, procedural protocols following a citizen’s death are governed by an intricate network of normative documents. Despite the presumed alignment between international and national guidelines, practical experiences reveal shortcomings in the proficiency of healthcare providers, particularly in cases involving prior medical interventions or systemic vulnerabilities.
 AIM: This study aimed to assess the readiness of final-year medical students and early-career physicians in navigating death certification intricacies, including their responses, documentation precision, and postmortem procedures for bereaved families, with implications for national health statistics.
 MATERIALS AND METHODS: By employing a mixed-methods approach, this study distributed questionnaires to sixth-year medical students and practicing physicians, including those in emergency medicine centers and general practice. Data collection included paper-based and digital questionnaires, ensuring anonymity and ethical compliance. Statistical analysis, employing parametric (t-test) and nonparametric (Chi-square) tests, forms the basis for actionable recommendations and educational material development.
 RESULTS: This study included 143 participants, of which 41% expressed apprehension about managing out-of-hospital deaths. Approximately 44% claimed familiarity with death certification regulations, with students displaying higher theoretical confidence but lacking practical knowledge. Remarkably, 74% of physicians never received formal training in death certification. Discrepancies in issuing death certificates, timing, and notification procedures were identified.
 CONCLUSION: Findings reveal varying practices among physicians according to their specialties. Issues related to documentation, timing, and notification were prevalent. The study emphasizes the need for improved training, particularly for medical students. Emergency medicine doctors exhibited higher preparedness levels. Medical students and early-career physicians urgently require enhanced education in death certification preparedness. Incorporating these topics into medical curricula, offering specialized courses, and disseminating instructional materials can significantly enhance effectiveness. Future studies should assess the quality and accuracy of recorded causes of death, which affect healthcare statistics, public service, and legal procedures, underscoring the societal and administrative significance of death certification practices.

Global Statistics and Data Sciences (GSDS), BeiGene USA, Fulton, MD

Pediatric cancer consists of a diverse group of rare diseases. Due to limited patient populations, standard randomized and controlled trials are often infeasible. As a result, single-arm trials are common in pediatric oncology and the use of external controls is often desirable or necessary to help generate actionable evidence and contextualize trial results. In this paper, we illustrate unique features in pediatric oncology clinical trials and describe their impact on the use of external controls. Various types of relevant external control data sources are described in terms of their utility and drawbacks. Statistical methodologies and design implications with external control are discussed. Two recent case studies using external controls to support pediatric oncology drug development are described in detail.

Global Statistics and Data Sciences (GSDS), BeiGene USA, Fulton, MD

Pediatric cancer consists of a diverse group of rare diseases. Due to limited patient populations, standard randomized and controlled trials are often infeasible. As a result, single-arm trials are common in pediatric oncology and the use of external controls is often desirable or necessary to help generate actionable evidence and contextualize trial results. In this paper, we illustrate unique features in pediatric oncology clinical trials and describe their impact on the use of external controls. Various types of relevant external control data sources are described in terms of their utility and drawbacks. Statistical methodologies and design implications with external control are discussed. Two recent case studies using external controls to support pediatric oncology drug development are described in detail.

The power of representation: Statistical analysis of diversity in US Alzheimer's disease genetics data.

Alzheimer's disease (AD) is a complex disease influenced by genetics and environment. More than 75 susceptibility loci have been linked to late-onset AD, but most of these loci were discovered in genome-wide association studies (GWAS) exclusive to non-Hispanic White individuals. There are wide disparities in AD risk across racially stratified groups, and while these disparities are not due to genetic differences, underrepresentation in genetic research can further exacerbate and contribute to their persistence. We investigated the racial/ethnic representation of participants in United States (US)-based AD genetics and the statistical implications of current representation. We compared racial/ethnic data of participants from array and sequencing studies in US AD genetics databases, including National Institute on Aging Genetics of Alzheimer's Disease Data Storage Site (NIAGADS) and NIAGADS Data Sharing Service (dssNIAGADS), to AD and related dementia (ADRD) prevalence and mortality. We then simulated the statistical power of these datasets to identify risk variants from non-White populations. There is insufficient statistical power (probability <80%) to detect single nucleotide polymorphisms (SNPs) with low to moderate effect sizes (odds ratio [OR]<1.5) using array data from Black and Hispanic participants; studies of Asian participants are not powered to detect variants OR <= 2. Using available and projected sequencing data from Black and Hispanic participants, risk variants with OR = 1.2 are detectable at high allele frequencies. Sample sizes remain insufficiently powered to detect these variants in Asian populations. AD genetics datasets are largely representative of USADRDburden. However,there is a wide discrepancy between proportional representation and statistically meaningful representation.Most variation identified in GWAS of non-Hispanic White individuals have low to moderate effects. Comparable risk variants in non-White populations are not detectable given current sample sizes, which could lead to disparities in future studies and drug development. We urge AD genetics researchers and institutions to continue investing in recruiting diverse participants and use community-based participatory research practices.

Methodological Complexity: A Both/And Approach to Address Tool Validity and Reliability for Assessment of Cultural Responsiveness in Indigenous Serving Schools

This article presents the first psychometric validation of the Culturally Responsive Assessment of Indigenous Schooling (CRAIS) tool, alongside a call for methodological complexity when engaged in research with and in Indigenous contexts. We examined the 23 culturally responsive schooling (CRS) principles underlying the newly created CRAIS tool in independent samples of curriculum units produced by teachers. Of these, 22 principles loaded into two factors. We further investigated the rationale for all 23 items through a review of the literature and robust discussions about the lived experiences of the authors and the Indigenous teachers with whom we work. We suggest that this both/and approach of quantitative and qualitative analysis results in a richer and more nuanced tool, as compared to what one single method would have rendered. Embracing this methodological complexity allows us to both center Indigenous lived experiences and maintain fidelity to the statistical implications of our work.

Modelling variation in test sensitivity for monitoring leptospirosis in beef cattle

When Bayesian latent class analysis is used for diagnostic test data in the absence of a gold standard test, it is common to assume that any unknown test sensitivities and specificities are constant across different populations. Indeed this assumption is often necessary for model identifiability. However there are a number of practical situations, depending on the type of test and the nature of the disease, where this assumption may not be true. We present a case study of using a microscopic agglutination test to diagnose leptospiroris infection in beef cattle, which strongly suggests that sensitivity in particular varies among herds. We develop and fit an alternative model in which sensitivity is related to within-herd prevalence, and discuss the statistical and epidemiological implications.

Optics-based metaheuristic approach to assess critical failure surfaces in both circular and non-circular failure modes for slope stability analysis

In many construction projects, a proactive slope stability evaluation is a prerequisite. Although many deterministic or non-deterministic approaches have been commonly used, metaheuristic approaches have resulted in high precision and significant outcomes for slope stability analysis problems. The current work focuses on the reliable assessment of critical failure surfaces associated with the least factor of safety value in both homogeneous and non-homogeneous slopes using a new simplified meta-heuristic approach called optics-inspired optimization (OIO). The algorithm utilizes six different LEM methods as a fitness function for deriving the factor of safety. Experimental analysis over three benchmark studies has been performed to demonstrate the algorithm's robustness and effectiveness. The implementation found more robust results as compared to previous studies. Meanwhile, the algorithm's statistical implication is conducted using the ANOVA test, which inferred better outcomes. With this interpretation, the approach claims to be suitable and efficient for slope stability analysis.

Data-Driven Thresholding Statistically Biases ATN Profiling across Cohort Datasets

BackgroundWhile the amyloid/tau/neurodegeneration (ATN) framework has found wide application in Alzheimer’s disease research, it is unclear if thresholds obtained using distinct thresholding methods are concordant within the same dataset and interchangeable across cohorts.ObjectivesTo investigate the robustness of data-driven thresholding methods and ATN profiling across cohort datasets.Design and SettingWe evaluated the impact of thresholding methods on ATN profiles by applying five commonly-used methodologies across cohort datasets. We assessed the generalizability of disease patterns discovered within ATN profiles by clustering individuals from different cohorts who were assigned to the same ATN profile.Participants and MeasurementsParticipants with available CSF amyloid-β 1–42, phosphorylated tau, and total tau measurements were included from eleven AD cohort studies.ResultsWe observed high variability among obtained ATN thresholds, both across methods and datasets that impacted the resulting profile assignments of participants significantly. Clustering participants from different cohorts within the same ATN category indicated that identified disease patterns were comparable across most cohorts and biases introduced through distinct thresholding and data representations remained insignificant in most ATN profiles.ConlusionThresholding method selection is a decision of statistical relevance that will inevitably bias the resulting profiling and affect its sensitivity and specificity. Thresholds are likely not directly interchangeable between independent cohorts. To apply the ATN framework as an actionable and robust profiling scheme, a comprehensive understanding of the impact of used thresholding methods, their statistical implications, and a validation of results is crucial.

Individual Variability of Human Cortical Spontaneous Activity by 3T/7T fMRI.

Mapping variability in cortical spontaneous activity (CSA) is an essential goal of understanding various sources of dark brain energy in human neuroscience. CSA was traditionally characterized using resting-state functional MRI (rfMRI) at 1.5T or 3T magnets while recently with 7T-rfMRI. However, the utility and interpretability of 7T-rfMRI must first be established for its variability. By leveraging rfMRI data from the Human Connectome Project (HCP), we derived CSA metrics with 3T-rfMRI and 7T-rfMRI for the same 84 healthy participants (52 females). The 7T-rfMRI produces different CSA metrics at multiple spatial-scales and their variability from the 3T-rfMRI. These differences were spatially dependent and varied according to specific cortical organization. For the amplitude metric, 7T-rfMRI enhanced its spatial contrasts in the anterior cortex but weakened it in the posterior cortex. An opposite pattern was observed for the connectivity metrics. The reliability changes of these metrics were scale dependent, indicating enhanced reliability for connectivity but weakened reliability for amplitude by 7T-rfMRI. These effects were primarily located in the high-order associate cortex, parsing the corresponding changes in individual differences with respect to 7T-rfMRI: (1) higher connectivity variability between participants and the lower connectivity variability within individual participants, and (2) lower amplitude variability between participants and higher amplitude variability within participants. Our work, for the first time, demonstrated the variability of the human CSA across space, rfMRI settings/platforms, and individuals. We discussed the statistical implications of our findings on CSA-based experimental designs and reproducible neuroscience as well as their translational value for personalized applications.