Varying Sample Sizes Research Articles

EEG-Based Emotion Recognition Using Trainable Adjacency Relation Driven Graph Convolutional Network

In recent years, there has been a growing research interest in using deep learning to resolve the issue of Electroencephalogram (EEG)-based emotion recognition. Current research emphasizes exploiting the useful information from each single EEG channel or each individual set of multi-channel EEG, but overlooks the correlation information among different multi-channel EEG sets. To explore such discriminative correlation information, we propose a novel and effective method“, Trainable Adjacency Relation Driven Graph Convolutional Network (TARDGCN)", which contains two complementary modules, TAR and GCN. TAR optimizes the local pair-wise positions of multi-channel EEG sets, which helps form an improved graphic representation for GCN to learn the global correlation among these sets for classification. The proposed method is capable of dealing with the problem of small sample size but large data variation in this issue. Our experimental results conducted on the databases DREAMER and DEAP in the subject-dependent and subject-independent modes show that TARDGCN outperforms the state-of-the-art approaches in classifying all of valence, arousal, and dominance.

Resolving inconsistencies in environmental impact assessments of organic farming: a comparison of two meta-analyses.

Abstract CONTEXT: In the midst of the growing popularity of organic farming, persistent questions surround its environmental effects. A 2017 meta-analysis suggested elevated acidification and eutrophication potentials per land area for organic farming relative to conventional farming, influencing policy and individual choices. However, a recent 2023 meta-analysis contradicted these findings, revealing reduced or comparable impacts across various environmental indicators, including acidification and eutrophication potentials. OBJECTIVE: These discrepant findings from these studies highlight the need for a comprehensive understanding of the underlying causes and implications. This study seeks to unravel the source of these disparities. METHODS: Initially, we scrutinized whether the differences in findings could be attributed to variations in the agricultural products selected for analysis. Subsequently, we explored the possibility that disparities were influenced by distinct averaging methods employed in the two studies. To address the impact of sample size, our investigation considered whether differences in findings could be attributed to varying sample sizes. RESULTS AND CONCLUSIONS: This study reveals that the disparities between these meta-analyses stem from differences in averaging methods and sample sizes. The 2023 meta-analysis, employing a more robust averaging method and a larger sample size, emerges as a more reliable source of information. Researchers are encouraged to incorporate the 2023 findings into their investigations, potentially necessitating a reconsideration of agricultural policies and dietary choices to align with updated environmental impact assessments. SIGNIFICANCE: By resolving inconsistencies in environmental impact assessments of organic farming, this study facilitates more effective societal and individual decision-making for greater sustainability.

Impact of Listening to Indian Classical Music, or Rāgas, on the Electroencephalogram: A Meta-Analysis.

Ancient Indian classical music (ICM) has long been lauded and recognized for influencing emotional responses by influencing the human body's resonance. A meta-analysis of prospective case studies published in the last ten years on the effect of ancient Indian music rāgas on brain waves is investigated. This meta-analysis aimed to analyze published prospective studies investigating the effect of ancient Indian rāgas on EEG in healthy subjects. The present study included prospective studies published since 2012. Studies were obtained by searching four databases, such as PsychINFO, PubMed, Google Scholar, and JSTOR, and searching related journals. Eligibility criteria included studies assessing the impact of listening to Indian classical music on the EEG. Primary outcomes were changes in the brain waves, frequency, and power and their relationship to activity-related arousal, attention, and mental tasks. The studies were analyzed according to the PRISMA guidelines. There were a total of five included studies with 71 participants in the age range of 19-30, and the conditions for the test groups were generally similar except for varying types of rāgas used and time of day. Analysis of the data collected from 71 participants revealed that music interventions had statistically significant effects on increasing alpha activity and attention scores. Fractal analysis was sensitive enough to detect EEG brainwave changes while and after listening to the rāga musical intervention. Rāgas stimulate arousal in different areas of the brain, depending on the emotions they are designed to evoke. However, the synchronized studies together could not highlight a significant relationship between rāgas and EEG fractal dimension values. Although the meta-analysis failed to reproduce the same results from the individual studies, potentially due to the small sample size and study variation, the meta-analysis opens doors to the potential of rāgas to elicit distinct emotions and serve as robust predictors of emotional response. Future studies can explore the therapeutic potential of various rāgas in the clinical setting, such as in the management of cognitive disorders and stress or in modulating heart rate variability and cognitive performance.

Prognostic value of lymphocyte-to-monocyte ratio in gastric cancer patients treated with immune checkpoint inhibitors: a systematic review and meta-analysis.

Emerging evidence suggests a correlation between the lymphocyte-monocyte ratio (LMR) and the prognosis in patients with gastric cancer (GC) undergoing immune checkpoint inhibitor (ICI) therapy. Nevertheless, the existing findings remain contentious. A comprehensive search of literature was conducted in databases including PubMed, Embase, Web of Science, and the Cochrane Library, spanning from the inception of each database to August 30, 2023 to collect studies exploring the interplay between LMR and clinical outcomes. Eligible studies were selected following predefined inclusion and exclusion criteria. Primary outcomes encompassed progression-free survival (PFS) and overall survival (OS), which were estimated using hazard ratios (HR) and corresponding 95% confidence intervals (CI). Our analysis incorporated eight cohort studies, involving 815 patients. Aggregate data revealed associations between an elevated LMR at baseline and prolonged PFS (HR=0.58; 95% CI: 0.47-0.71, p<0.00001) and improved OS (HR=0.51, 95% CI: 0.33-0.79; p=0.003). Furthermore, LMR exhibited a favorable association with PFS after treatment (HR=0.48; 95% CI: 0.29-0.79; p= 0.004), while such a correlation was not evident in the OS analysis. Importantly, a high level of LMR was associated with prolonged PFS across varying sample sizes, follow-up duration, treatment combinations, line of therapy, and cut-off values. A high pre-treatment LMR is associated with improved OS and PFS in GC patients treated with ICIs. LMR emerges as a potent biomarker for prognostic assessment in these patients, offering valuable insights for informed treatment decisions within the domain of GC immunotherapy. PROSPERO, identifier CRD42021228512.

Impact of Strategic Leadership, Entrepreneurial Orientation, and Organizational Innovation on Organizational Performance: Harnessing Data to Understand the Mediating Role of Knowledge Management: A Case Study of SMEs in Pakistan,

In the current era of competitiveness and digitalization SME’s can play an important role in economic development of a country like Pakistan. The aim of this study is to investigate the impact of strategic leadership, Entrepreneurial and orientation organizational innovation on SME’s performance in Pakistan with the mediation role of knowledge management. A self-administered survey questionnaire is used to collect the data from SME’s Managers and owners. PLS is used for data analysis. The findings of the study reveal that there is a significant relationship between strategic leadership, Entrepreneurial orientation and organizational innovation and organizational performance. Moreover, Knowledge management has significant relationship with organizational performance. Further, statistical values show that knowledge management fully mediate the relationship. It is a unique study to test this combination of variables in the context of SME’s of Pakistan. As there are very limited studies available to discuss about SME’s performance specifically in the context of Pakistan. Current study will help the policy makers to develop the effective policies for SME’s sector development. Moreover, use of knowledge management as mediator indicate the novelty of current study. Conclusively, current study is limited to Pakistan in future researchers may use this framework to other developing countries with the variation of sample size and industrial sector.

Weighted adaptive CUSUM mean chart with variable sample size and sampling interval

The classical CUSUM (C) chart is designed by assuming that the size of the shift in the process, in which a quick detection is important, is known a priori. However, this assumption is often violated in practice, as the actual shift size is rarely known even though it may vary within a certain interval. The adaptive C (AC) chart gives better protection against process shifts in a certain interval than the classical C chart. In this paper, we propose a new weighted AC (WAC) chart with the variable sample size and sampling interval (VSSI) feature, which encompasses the fixed sampling rate (FSR), variable sample size (VSS) and variable sampling interval (VSI) based WAC charts. The Monte Carlo simulations are adopted in the run-length computations of the considered charts, where the newly developed (VSS and VSSI based) charts outperform the existing (FSR and VSI) WAC charts when detecting small shifts in the process mean. An illustrative example shows the implementation of the existing and proposed WAC charts.

Airborne laser scanning to optimize the sampling efficiency of a forest management inventory in South-Eastern Germany

Effective forest stewardship relies on comprehensive field-inventories describing forest resources. Increasing demands for data and indicators that improve understanding of climate change impacts, timber production, and ecosystem processes make access to robust field inventories crucial. A trade-off between cost and statistical efficacy exists however, necessitating that practitioners be familiar with the spatial and structural composition and variability of their management areas. Remotely sensed data, like airborne laser scanning (ALS), can improve data availability and sampling efficiency. In this study, we simulate sampling approaches and provide an indication of the benefits of incorporating ALS-derived auxiliary data. We evaluate the ability of sub-samples from an existing field-inventory to accurately estimate ALS structural metrics. Additionally, we explore data-driven approaches to allocate new field plots, reducing bias and improving accuracy. The Monte Carlo simulation compared the local pivotal method (LPM), Latin hypercube sampling (LHS), and simple random sampling (SRS) at a variety of sample sizes. Precision and variability measures were used to comparatively assess the efficacy of sampling method and sample size. Results demonstrate the value of ALS as an auxiliary dataset, with LPM and LHS achieving sampling efficiencies over SRS of up to 88.6% and 94.3%, respectively. By applying the adapted Latin hypercube evaluation of a legacy sample (AHELS) algorithm, we reduced the mean average percent deviation (MAPD) by over 20% between sample measures and wall-to-wall ALS metrics. These methods can aid practitioners in planning cost-effective and statistically rigorous forest inventory campaigns, particularly in determining where to re-sample within an existing plot network.

Exponentially Generated Modified Chen Distribution with Applications to Lifetime Dataset

In this paper, the exponentially generated system was used to modify a two-parameter Chen distribution to a four-parameter distribution with better performance. The property of complete probability distribution function was used to verify the completeness of the resulting distribution, which shows that the distribution is a proper probability distribution function. A simulation study involving varying sample sizes was used to ascertain the asymptotic property of the new distribution. Small and large sample sizes were considered which shows the closeness of the estimates to the true value as the sample size increases. Lifetime dataset were used for model comparison which shows the superiority of exponentially generated modify Chen distribution over some existing distributions. It is therefore recommended to use the four-parameter Chen distribution in place of the well-known two-parameter Chen distribution.

A systematic review and meta-regression analysis of technical efficiency in Ethiopian wheat farming

Replications are important for science, both statistically and philosophically. A plethora of empirical studies that have been done so far show that there are always variations, errors and inconclusive findings on the technical efficiency (TE) scores of wheat output in Ethiopia. In this study, we intend to contribute to these controversies by providing the first thorough investigation of the magnitude of mean-effect size and the underlying factors of mean technical efficiency variations in wheat production across studies in Ethiopia. These efficiency scores are retrieved from 31 studies, or a household size of 12,754 over the years 2011–2022. The analysis of meta-regression was done using a random effect model using Comprehensive Meta-analysis (CMA-4) software. The Begg and Mazumdar rank-correlation test, egger test, and funnel plot were used to determine publication bias across studies. Since 2022, we have utilized the classic fail-safe-N test. One issue with publication bias is the omission of some non-significant studies from the analysis, which, if they were included, would cancel out the observed effect. Further, the missing study problem or “file drawer” problem, of the study would also be computed using the “Trim and Fill” estimation approach. To evaluate heterogeneity, a forest plot is used. The effect size is also determined using the random effect model along with the I-squared statistic, the tau-squared and tau, and the Q-test. As a result, a mean effect size of 71.6% with a 95% confidence interval of 67.9%−75.3% is observed. The meta-regression demonstrates that the 31 mean technical efficiency studies included in the research had varying efficiency scores due to variations in sample size, methodologies used, publication status, and study range. It suggests that, with all other factors held constant, a 1% change in these regressors causes a 0.01%, 10.88%, 21.22%, and 6.74% change, respectively, in the mean technical efficiency scores across studies in Ethiopia. In addition, the technical efficiency score across studies is also affected by the location in which the study is conducted.

Sample size and predictive performance of machine learning methods with survival data: A simulation study.

Prediction models are increasingly developed and used in diagnostic and prognostic studies, where the use of machine learning (ML) methods is becoming more and more popular over traditional regression techniques. For survival outcomes the Cox proportional hazards model is generally used and it has been proven to achieve good prediction performances with few strong covariates. The possibility to improve the model performance by including nonlinearities, covariate interactions and time-varying effects while controlling for overfitting must be carefully considered during the model building phase. On the other hand, ML techniques are able to learn complexities from data at the cost of hyper-parameter tuning and interpretability. One aspect of special interest is the sample size needed for developing a survival prediction model. While there is guidance when using traditional statistical models, the same does not apply when using ML techniques. This work develops a time-to-event simulation framework to evaluate performances of Cox regression compared, among others, to tuned random survival forest, gradient boosting, and neural networks at varying sample sizes. Simulations were based on replications of subjects from publicly available databases, where event times were simulated according to a Cox model with nonlinearities on continuous variables and time-varying effects and on the SEER registry data.

A Bayesian multi-model inference methodology for imprecise moment-independent global sensitivity analysis of rock structures

Traditional global sensitivity analysis (GSA) neglects the epistemic uncertainties associated with the probabilistic characteristics (i.e. type of distribution type and its parameters) of input rock properties emanating due to the small size of datasets while mapping the relative importance of properties to the model response. This paper proposes an augmented Bayesian multi-model inference (BMMI) coupled with GSA methodology (BMMI-GSA) to address this issue by estimating the imprecision in the moment-independent sensitivity indices of rock structures arising from the small size of input data. The methodology employs BMMI to quantify the epistemic uncertainties associated with model type and parameters of input properties. The estimated uncertainties are propagated in estimating imprecision in moment-independent Borgonovo's indices by employing a reweighting approach on candidate probabilistic models. The proposed methodology is showcased for a rock slope prone to stress-controlled failure in the Himalayan region of India. The proposed methodology was superior to the conventional GSA (neglects all epistemic uncertainties) and Bayesian coupled GSA (B-GSA) (neglects model uncertainty) due to its capability to incorporate the uncertainties in both model type and parameters of properties. Imprecise Borgonovo's indices estimated via proposed methodology provide the confidence intervals of the sensitivity indices instead of their fixed-point estimates, which makes the user more informed in the data collection efforts. Analyses performed with the varying sample sizes suggested that the uncertainties in sensitivity indices reduce significantly with the increasing sample sizes. The accurate importance ranking of properties was only possible via samples of large sizes. Further, the impact of the prior knowledge in terms of prior ranges and distributions was significant; hence, any related assumption should be made carefully.

Time of day dependent symptom onset is not associated with left ventricular function and myocardial damage after ST-segment elevation myocardial infarction

Abstract Background Circadian processes are suggested to influence ischemic injury in ST-segment elevation myocardial infarction (STEMI). Observational data suspect a circadian dependence of the occurrence of microvascular obstruction (MVO) in patients with STEMI. However, these observations derive from a small sample size and circadian variations in left ventricular function and myocardial damage after STEMI are still a matter of controversy. Purpose We aimed to investigate the association of time of day dependent symptom onset with left ventricular ejection fraction (LVEF), infarct size (IS) and MVO in a large cohort of STEMI patients treated with primary percutaneous coronary intervention (PCI). Methods This observational study investigated acute STEMI patients treated with primary PCI. Cardiac magnetic resonance (CMR) imaging was performed within 1 week after the index event for the determination of left ventricular function and infarct characteristics. The time of symptom onset was used to discriminate patients according to LVEF, IS as well as MVO occurrence and extent over a 24 hours cycle to evaluate circadian behavior. Results In final analysis, 889 acute STEMI patients treated with primary PCI with a delay of 189 [120-315] minutes were included. Median age of the overall cohort was 57 [51-66] years and 17% were female. Median LVEF was 49 [42-55]%, IS assumed 15.5 [8.0-24.7]% of left ventricular myocardial mass (LVMM) and MVO occurred in 57% of STEMI patients. No hourly differences between symptom onset and MVO occurrence (p=0.108), MVO extent (p=0.735), LVEF (p=0.644) and IS (p=0.722) have been evaluated. When comparing 3 hourly segments of symptom onset, no variations in MVO occurrence (p=0.114), MVO extent (p=0.308), LVEF (p=0.547) and IS (p=0.405) were observed. Conclusions No circadian variations in symptom onset and the occurrence and extent of MVO, LVEF and IS were observed in this large cohort of STEMI patients treated with primary PCI. Further research is needed to investigate the complex interplay between circadian processes and ischemic injury in this patient population.

Fast and accurate method for short-circuit current calculation in distribution network with IIDGs

The fault behavior of Inverter Interfaced Distributed Generators (IIDGs) diverges from that of synchronous generators. When a substantial number of IIDGs are integrated into the distribution network, the conventional short-circuit current calculation technique, grounded in a mechanical framework, struggles to simultaneously satisfy the demands for both rapid computation and precision. This study introduces an alternative approach reliant on data analysis, enabling swift and precise computation of short-circuit currents across the IIDG-infused distribution grid. The investigation delves into the efficacy of multi-output regression techniques and the selection of the foundational learning algorithm. Specifically, two strategies are advanced: Multi-Target Regressor Stacking and Regressor Chains, both utilizing the Light Gradient Boosting Machine as the base learner. The influence of varying sample sizes on the multi-output computational model's performance is assessed. To ascertain the real-world viability of the multi-output regression methodology, two distinct fault characteristics pertaining to data-driven short-circuit current calculation are scrutinized using existing distribution network measurement conditions. The study reveals that, given a known distribution network structure, the proposed method can compute network-wide short-circuit currents across diverse IIDG penetration levels and fault scenarios through a singular model, maintaining a balance between computation precision and speed. If the distribution network's structure undergoes minor modifications, the model demonstrates reasonable adaptability, yet a retraining of the short-circuit current calculation model is recommended to ensure sustained accuracy in the face of significant network changes.

2 Pilot Study of a Cognitive Enhancement Intervention for Substance Abuse Recovery

Objective:This was a pilot study testing a cognitive enhancement program to improve rate of cognitive recovery in early substance abuse treatment. It is hypothesized that if patients were able to accelerate the rate of cognitive improvement, they may be able to better engage in substance abuse treatment and potentially have better long-term outcomes.Participants and Methods:Participants were 47 adults newly admitted to a residential substance abuse treatment facility (74.5% male, 76.6% white, mean age=34.5 years, education=12+ years). All were post-detox. All were being treated for opioid abuse, with the majority in treatment for polysubstance abuse. Participants were randomly assigned to either the intervention group (BrainHQ research cognitive training program) or active control group (inert computer games) and completed 34 training sessions per week for a minimum of 3 weeks. NIH Toolbox cognition battery was administered at baseline and endpoint.Results:Regardless of study group, most participants had a significant improvement in cognitive performance across most subtests and composite scores of the NIH Toolbox cognition battery. The RAVLT and Oral Symbol Digit subtests had the greatest change (p&lt;.001) for both groups, as well as a significant improvement (p=.002) in Cognitive Function Composite Score for both groups. The only difference between the control and intervention group was on the Pattern Comparison subtest, with the intervention group scoring significantly higher at endpoint (p=.004).Conclusions:Although substance abuse is known to cause injury to the brain that may not be fully repaired by sobriety, cognitive recovery was significant in this group of patients during early inpatient treatment for opioid abuse. Although it has yielded significant effect in other patient populations, the BrainHQ program did not show a significant enhancement in cognitive recovery, compared to the active control group, in this pilot study of patients in treatment for opioid abuse. This study was limited by a small sample size and potential future variations should be considered, such as changes to intervention intensity and specific intervention exercises.

The testicular microvasculature in Klinefelter syndrome is immature with compromised integrity and characterized by excessive inflammatory cross-talk.

Does Klinefelter syndrome (KS) lead to a distinct gene expression pattern at single-cell level in the testes that could provide insight into the reported microvascular dysfunction in the testes? A distinct gene expression pattern within microvascular-associated cells of males with KS suggests excessive endothelial cell (EC) activation, disorganized vessel formation, and the presence of immature vessels with compromised integrity. Recent studies show that males with KS exhibit microvascular dysfunction in their testes, which affects blood flow and is associated with lower circulating levels of testosterone. A comparative cross-sectional study of males with KS (n = 6), non-obstructive azoospermia (NOA) (n = 5), cryptozoospermia (n = 3), and controls (n = 15) was carried out. We analyzed publicly available single-cell RNA sequencing data of testicular cells from males with KS, males with NOA, males with cryptozoospermia, and controls. The integration of these datasets allowed us to analyze gene expression profiles and communication patterns among the cell types within the testis and to identify capillary ECs to investigate changes at the microvascular level. Rooted in changes at the single-cell level, our study demonstrates a shift in gene expression forming the foundation for altered cellular communication, microvascular remodeling, and pro-inflammatory responses within the testes of males with KS. We identified genes that were dysregulated in capillary ECs from males with KS (Padj < 0.05). Specifically, the unique microvascular gene expression in males with KS indicated enhanced capillary EC activation and increased inflammatory cross-talk, leading to impaired vessel maturation and increased EC barrier permeability. Our study is constrained by an unbalanced design, with varying sample sizes and number of cells within each group. We acknowledge the restricted access to clinical information. In addition, our findings were deduced from changes in gene expression, which limits us to infer potential biological consequences arising from these alterations. Furthermore, the absence of a pre-pubertal age group limits the generalizability of our findings and warrants further investigation. This study offers novel insights into the testicular pathophysiology in KS and underscores the potential contribution of microvascular dysfunction to the hypogonadism and infertility observed in males with KS. While this study aims to better understand the microvascular dysfunction in KS, the precise connections to testosterone deficiency and testicular atrophy remain to be fully elucidated. A.S. was supported by the Independent Research Fund Denmark (0134-00130B). C.H.G. was supported by Novo Nordisk Foundation (NNF15OC0016474, NNF20OC0060610), 'Fonden til lægevidenskabens fremme', the Familien Hede Nielsen foundation and the Independent Research Fund Denmark (0134-00406A). E.B.J. was supported by Aarhus University and E.B.J. and C.H.G by the Independent Research Fund Denmark (2096-00165A). J.M.K. was supported by Lundbeckfonden (R307-2018-3667), Carlsberg Fonden (CF19-0687), Novo Nordisk Fonden (0073440) and Steno Diabetes Center Aarhus (SDCA). The authors declare no conflicts of interest. N/A.

Landslide risk assessment and management using hybrid machine learning‐based empirical models

Landslides are a prevalent geologic phenomenon that substantially threatens human life and infrastructure, resulting in considerable loss and destruction. The practice of landslide susceptibility mapping is crucial for the mitigation of risks connected with this natural disaster. This work aims at investigating the influence of varying sample sizes on the precision of landslide susceptibility modelling using a case study conducted in the Alamout basin, Iran. The researchers used a machine learning methodology based on tree algorithms to construct a model for predicting the likelihood of landslides. Additionally, they adopted a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The integration of the naive Bayes tree (NBTree), random forest (RF), logistic model tree (LMT) and J48 algorithms was performed. The modelling process included using 20 predictive parameters across four distinct scenarios. Four models, labelled S1, S2, S3 and S4, were used in this study. These models utilized 25%, 50%, 75% and 100% of the available inventory data. The research presented in this study is distinguished by using a tree‐based methodology for landslide susceptibility modelling and incorporating a multi‐scenario strategy to address the inherent uncertainty associated with the input data. The findings indicated that the augmentation of the sample size improved the precision of the models. The efficacy of using a multi‐scenario strategy in enhancing the dependability of the model is also underscored. Among the 20 input elements used in the modelling process, it was seen that slope angle accounted for the highest relative significance, constituting 25.60% of the overall influence. Following more closely, distance to fault contributed significantly, with a relative importance of 23.40%. Additionally, rainfall and elevation exhibited notable contributions, with relative volumes of 7.91% and 5.50%, respectively. All four landslide models showed adequate learning and forecasting ability throughout the training and testing phases. During the testing phase, the true skill score (TSS) values exhibited a range of 0.631–0.804, while the area under the receiver operating characteristic curve values showed a range of 0.745–0.921. The susceptibility maps indicated that a significant portion of the region exhibits moderate to very high susceptibility zones, with the northern and eastern sectors displaying greater landslide values than the western region. The model's performance showed improvement from S1 to S4 in both the training and testing phases. The performance of the models exhibited the following trend: in scenario 1, the RF model outperformed the J48, LMT and NBTree models; in scenario 2, the RF model surpassed the NBTree and LMT models, while being on par with the J48 model; in scenarios 3 and 4, the RF model showed superior performance compared to the NBTree, J48 and LMT models. Therefore, the RF model proved to be the most effective among the models evaluated. The findings derived from this research have the potential to serve as valuable references for the purposes of land‐use planning and catastrophe risk management.

Statistical Significance Versus Clinical Relevance: A Head-to-Head Comparison of the Fragility Index and Relative Risk Index.

Background In biostatistics, assessing the fragility of research findings is crucial for understanding their clinical significance. This study focuses on the fragility index, unit fragility index, and relative risk index as measures to evaluate statistical fragility. The fragility indices assess the susceptibility of p-values to change significance with minor alterations in outcomes within a 2x2 contingency table. In contrast, the relative risk index quantifies the deviation of observed findings from therapeutic equivalence, the point at which the relative risk equals 1. While the fragility indices have intuitive appeal and have been widely applied, their behavior across a wide range of contingency tables has not been rigorously evaluated. Methods Using a Python software program, a simulation approach was employed to generate random 2x2 contingency tables. All tables under consideration exhibited p-values < 0.05 according to Fisher's exact test. Subsequently, the fragility indices and the relative risk index were calculated. To account for sample size variations, the indices were divided by the sample size to give fragilityand risk quotients. A correlation matrix assessed the collinearity between each metric and the p-value. Results The analysis included 2,000 contingency tables with cell counts ranging from 20 to 480. Notably, the formulas for calculating the fragility indices encountered limitations when cell counts approached zero or duplicate cell counts hindered standardized application. The correlation coefficients with p-values were as follows: unit fragility index (-0.806), fragility index (-0.802), fragility quotient (-0.715), unit fragility quotient (-0.695), relative risk index (-0.403), and risk quotient (-0.261). Conclusion The fragility indicesand fragility quotients demonstrated a strong correlation with p-values below 0.05, while the relative risk index and relative risk quotient exhibited a weak association with p-values below this threshold. This implies that the fragility indices offer limited additional information beyond the p-value alone. In contrast, the relative risk index and risk quotient exhibitindependence from the p-value, indicating that theymay provide important additional information about statistical fragility by evaluating the divergence of observed results from therapeutic equivalence, irrespective of the p-value-based statistical significance.

Modelling recall-based competing risks data with k different models

In competing risks model, subjects are exposed to failure due to more than one cause. In this study, we develop a model for recall-based competing risks data when the causes associated with time to event are assumed to follow different distributions respectively. The chances of an individual recalling an event will be high if elapsed time between monitoring time and time to event is less. This information is utilized by taking non-recall probability as a function of this elapsed time. For point estimation, an expectation-maximization based algorithm is developed. For interval estimation, we construct the observed Fisher information matrix by using the missing information principle. The study is further extended to the Bayesian paradigm under suitable choices of prior distributions. The samples from full conditionals are drawn using a Gibbs sampling-based algorithm. To assess the performance of proposed estimators, an extensive simulation study is carried out for different proportions of non-recall and censored data with varying sample sizes under uniform and exponential monitoring patterns. Finally, the median duration of breastfeeding cessation for US women is estimated.

Frequentist and Bayesian tolerance intervals for setting specification limits for left-censored gamma distributed drug quality attributes.

Tolerance intervals from quality attribute measurements are used to establish specification limits for drug products. Some attribute measurements may be below the reporting limits, that is, left-censored data. When data has a long, right-skew tail, a gamma distribution may be applicable. This paper compares maximum likelihood estimation (MLE) and Bayesian methods to estimate shape and scale parameters of censored gamma distributions and to calculate tolerance intervals under varying sample sizes and extents of censoring. The noninformative reference prior and the maximal data information prior (MDIP) are used to compare the impact of prior choice. Metrics used are bias and root mean square error for the parameter estimation and average length and confidence coefficient for the tolerance interval evaluation. It will be shown that Bayesian method using a reference prior overall performs better than MLE for the scenarios evaluated. When sample size is small, the Bayesian method using MDIP yields conservatively too wide tolerance intervals that are unsuitable basis for specification setting. The metrics for all methods worsened with increasing extent of censoring but improved with increasing sample size, as expected. This study demonstrates that although MLE is relatively simple and available in user-friendly statistical software, it falls short in accurately and precisely producing tolerance limits that maintain the stated confidence depending on the scenario. The Bayesian method using noninformative prior, even though computationally intensive and requires considerable statistical programming, produces tolerance limits which are practically useful for specification setting. Real-world examples are provided to illustrate the findings from the simulation study.

Variation of heat flow rate of vertically arranged plumbene sheets with number of layers and sample size

Plumbene is recently drawing the interests of researchers around the globe due to its marvelous properties. Earlier researchers have noticed that thermal conductivity of plumbene fluctuates with variation in sample sizes. We find that with a surge in the number of layers heat current flowing across plumbene dwindles. Between layers 1 and 2, the variation of heat flow rate is too fast, then from layers 2 to 4 slightest decrease is accounted. Deliberate gain in heat flow rate for plumbene from sample sizes 600[Formula: see text]Å, 650[Formula: see text]Å, 700[Formula: see text]Å, 750[Formula: see text]Å, 800[Formula: see text]Å, 850[Formula: see text]Å, 950[Formula: see text]Å and 1000[Formula: see text]Å is noticed. But a remarkable increment is observed at 900[Formula: see text]Å.