Small Sample Set Research Articles

The Refinement of a Common Correlated Effect Estimator in Panel Unit Root Testing: An Extensive Simulation Study

The Common Correlated Effect (CCE) estimator is widely used in panel data models to address cross-sectional dependence, particularly in nonstationary panels. However, existing estimators have limitations, especially in small-sample settings. This study refines the CCE estimator by introducing new proxy variables and testing them through a comprehensive set of simulations. The proposed method is simple yet effective, aiming to improve the handling of cross-sectional dependence. Simulation results show that the refined estimator eliminates cross-sectional dependence more effectively than the original CCE, with improved power properties under both weak- and strong-dependence scenarios. The refined estimator performs particularly well in small sample sizes. These findings offer a more robust framework for panel unit root testing, enhancing the reliability of CCE estimators and contributing to further developments in addressing cross-sectional dependence in panel data models.

Support Vector Machines With Uncertainty Option and Incremental Sampling for Kriging

ABSTRACTThis paper presents a novel approach to pollution assessment by investigating support vector machines (SVM) with an uncertainty option to overcome the limitations of traditional kriging. While kriging is a major tool for geostatistical modelling, allowing to estimate the distribution of contaminants in a region from a small set of samples, it does not allow to extract also the uncertainty map. An uncertainty map is of great interest, as it allows to identify regions of high uncertainty where one should sample in order to reduce high level of uncertainties. In this paper, we propose two variants of the SVM with an uncertainty option, each using a different hinge loss to improve the accuracy and efficiency. These losses allow to estimate different levels of contaminations, as well as uncertainty, such as the three levels: positive, uncertain and negative, namely for pollution estimation: high‐pollution, uncertain and low‐pollution. In addition to the exploration of SVM variants, we propose an innovative active sample selection strategy based on the uncertainty criterion. This strategy is designed to systematically reduce uncertainties in pollution assessment, thus providing adaptability to dynamic environmental changes. An incremental SVM with an uncertainty option is introduced to further optimise the sample selection process. Furthermore, the decision‐making process is refined through the introduction of a novel three‐hinge loss. The corresponding optimization problem and its resolution allow for a more nuanced contamination assessment with multiple levels of estimation, providing a valuable tool for characterising contamination levels with increased granularity. Extensive experiments on synthetic and real data validate the proposed methodology. Synthetic data simulations assess the quality of the approach, while real data from a two‐dimensional porosity measurement demonstrate practical applicability. This research contributes to the advancement of pollution assessment methodologies, providing an adaptable solution for environmental monitoring.

Applying support vector machines to a diagnostic classification model for polytomous attributes in small-sample contexts.

Over several years, the evaluation of polytomous attributes in small-sample settings has posed a challenge to the application of cognitive diagnosis models. To enhance classification precision, the support vector machine (SVM) was introduced for estimating polytomous attribution, given its proven feasibility for dichotomous cases. Two simulation studies and an empirical study assessed the impact of various factors on SVM classification performance, including training sample size, attribute structures, guessing/slipping levels, number of attributes, number of attribute levels, and number of items. The results indicated that SVM outperformed the pG-DINA model in classification accuracy under dependent attribute structures and small sample sizes. SVM performance improved with an increased number of items but declined with higher guessing/slipping levels, more attributes, and more attribute levels. Empirical data further validated the application and advantages of SVMs.

Selecting the Best Pharmacokinetic Models for a Priori Model-Informed Precision Dosing with Model Ensembling.

When utilizing population pharmacokinetic (popPK) models for a priori dosage individualization, selecting the best model is crucial to obtain adequate doses. We developed and evaluated several model-selection and ensembling methods, using external evaluation on the basis of therapeutic drug monitoring (TDM) samples to identify the best (set of) models per patient for a priori dosage individualization. PK data and models describing both hospitalized patients (n = 134) receiving continuous vancomycin (26 models) and patients (n = 92) receiving imatinib in an outpatient setting (12 models) are included. Target attainment of four model-selection methods was compared with standard dosing: the best model based on external validation, uninformed model ensembling, model ensembling using a weighting scheme on the basis of covariate-stratified external evaluation, and model selection using covariates in decision trees that were subsequently ensembled. Overall, the use of PK models improved the proportion of patients exposed to concentrations within the therapeutic window for both cohorts. Relative improvement of proportion on target for best model, unweighted, weighted, and decision trees were - 7.0%, 2.3%, 11.4%, and 37.0% (vancomycin method-development); 23.2%, 7.9%, 15.6%, and, 77.2% (vancomycin validation); 40.7%, 50.0%, 59.5%, and 59.5% (imatinib method-development); and 19.0%, 28.5%, 38.0%, and 23.8% (imatinib validation), respectively. The best (set of) models per patient for a priori dosage individualization can be identified using a relatively small set of TDM samples as external evaluation. Adequately performing popPK models were identified while also excluding poor-performing models. Dose recommendations resulted in more patients within the therapeutic range for both vancomycin and imatinib. Prospective validation is necessary before clinical implementation.

Pottery from Motion – A Refined Approach to the Large-Scale Documentation of Pottery Using Structure from Motion

Abstract In recent years, interest in the usage of computer-based methods in archaeology, especially regarding field documentation, has grown significantly. In 2021, Göttlich et al. presented a new large-scale three-dimensional (3D) capture method for the documentation of pottery using structure from motion. This method, however, was only tested on a very small sample set and never truly conducted in a large-scale documentation surrounding. Consequently, we decided to test this workflow on a large-scale basis during three field campaigns (March 2022, November 2022, and March 2023) in Lebanon, documenting more than 4,000 sherds in total. In this article, I will present the results and observations of these campaigns, critically discuss the workflow involved (documentation and processing), and propose a refined workflow for this methodology. This article focuses solely on the relevant documentation and 3D processing.

Bootstrap inference on a factor model based average treatment effects estimator

We propose a novel bootstrap procedure for conducting inference for factor model-based average treatment effects estimators. Our method overcomes bias inherent to existing bootstrap procedures and substantially improves upon existing large sample normal inference theory in small sample settings. The finite sample improvements arising from the use of our proposed procedure are illustrated via a set of Monte Carlo simulations, and formal justification for the procedure is outlined.

Building a Turkish UCCA dataset

Abstract Semantic representation is the task of conveying the meaning of a natural language utterance by converting it to a logical form that can be processed and understood by machines. It is utilised by many applications in natural language processing (NLP), particularly in tasks relevant to natural language understanding (NLU). Due to the widespread use of semantic parsing in NLP, many semantic representation schemes with different forms have been proposed; Universal Conceptual Cognitive Annotation (UCCA) is one of them. UCCA is a cross-lingual semantic annotation framework that allows easy annotation without requiring substantial linguistic knowledge. UCCA-annotated datasets have been released so far for English, French, German, Russian, and Hebrew. In this paper, we present a UCCA-annotated Turkish dataset of 400 sentences that are obtained from the METU-Sabanci Turkish Treebank. We provide the UCCA annotation specifications defined for the Turkish language so that it can be extended further. We followed a semi-automatic annotation approach, where an external semantic parser is utilised for the initial annotation of the dataset, which is manually revised by two annotators. We used the same semantic parser model to evaluate the dataset with zero-shot and few-shot learning, demonstrating that even a small sample set from the target language in the training data has a notable impact on the performance of the parser (15.6% and 2.5% gain over zero-shot for labelled and unlabelled results, respectively).

A Semi-Supervised Active Learning Method for Structured Data Enhancement with Small Samples

In order to solve the problems of the small capacity of structured data and uneven distribution among classes in machine learning tasks, a supervised generation method for structured data called WAGAN and a cyclic sampling method named SACS (Semi-supervised and Active-learning Cyclic Sampling), based on semi-supervised active learning, are proposed. The loss function and neural network structure are optimized, and the quantity and quality of the small sample set are enhanced. To enhance the reliability of generating pseudo-labels, a Semi-supervised Active learning Framework (SAF) is designed. This framework redistributes class labels to samples, which not only enhances the reliability of generated samples but also reduces the influence of noise and uncertainty on the generation of false labels. To mine the diversity information of generated samples, an uncertain sampling strategy based on spatial overlap is designed. This strategy incorporates the idea of spatial overlap and uses global and local sampling methods to calculate the information content of generated samples. Experimental results show that the proposed method performs better than other data enhancement methods on three different datasets. Compared to the original data, the average F1macro value of the classification model is improved by 11.5%, 16.1%, and 19.6% relative to compared methods.

Dealing with small samples in disability research: Do not fret, Bayesian analysis is here.

Small sample sizes are a common problem in disability research. Here, we show how Bayesian methods can be applied in small sample settings and the advantages that they provide. To illustrate, we provide a Bayesian analysis of employment status (employed vs. unemployed) for those with disability. Specifically, we apply empirically informed priors, based on large-sample (N = 95,593) July 2019 Current Population Survey (CPS) microdata to small subsamples (average n = 26) from July 2021 CPS microdata, defined by six specific difficulties (i.e., hearing, vision, cognitive, ambulatory, independent living, and self-care). We also conduct a sensitivity analysis, to illustrate how various priors (i.e., theory-driven, neutral, noninformative, and skeptical) impact Bayesian results (posterior distributions). Bayesian findings indicate that people with at least one difficulty (especially ambulatory, independent living, and cognitive difficulties) are less likely to be employed than people with no difficulties. Overall, results suggest that Bayesian analyses allow us to incorporate known information (e.g., previous research and theory) as priors, allowing researchers to learn more from small sample data than when conducting a traditional frequentist analysis. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

P-418 What is the optimal midluteal phase circulating progesterone level during a fresh IVF cycle? The answer differs from what one expects in a natural cycle

Abstract Study question Do midluteal phase circulating progesterone (P4) levels relate to the fresh embryo transfer clinical outcome and is rescue P4 useful in such cases? Summary answer Live birth rate (LBR) was significantly lower when P4 levels were below 20ng/ml and did not seem to benefit from rescue intramuscular P4. What is known already Preceding literature on the predictive value of midluteal P4 for LBR has shown conflicting results and frequently included small sample sets and heterogeneous ovarian stimulation protocols. The findings reported ranged from the lack of an association between P4 serum levels and clinical outcome to worse success rates seen either in the groups with the highest or the lowest P4 in midluteal phase. Furthermore, while rescue P4 has been empirically proposed, it has lacked formal assessment thus far. Study design, size, duration In total, 652 patients who underwent a fresh single blastocyst transfer in an IVF cycle in our center between 2014 and 2021 were included in this retrospective cohort study. All were GnRH-antagonist cycles using hCG trigger and luteal support with micronized vaginal progesterone 200mg twice daily. Rescue intramuscular progesterone was systematically administered whenever low midluteal P4 (below 1 standard deviation of the center’s mean) levels were detected. Participants/materials, setting, methods The cycles were subdivided into three groups according to the midluteal P4 levels: <10ng/ml, 10-20ng/ml and >20ng/ml. The primary outcome assessed was LBR, with secondary outcomes including clinical pregnancy (CPR) and pregnancy loss rates. Maternal age and body mass index (BMI), year of treatment, ovarian response, endometrial thickness, cause of infertility and embryo quality were controlled for using multivariable logistic regression. Main results and the role of chance The mean age ± standard deviation of patients was 36.8±3.8 years, while mean weight and BMI were 63.2±11.5kg and 23.3±3.9kg/m2, respectively. LBR in the group with P4>20ng/ml (46.5%) was significantly higher than in the groups with low and intermediate P4 serum levels (23.1% and 28.1%, respectively, p < 0.001). The same was true for CPR (54.5%, 30.8% and 37.9%, respectively, p < 0.001). Conversely, the rate of pregnancy loss in the group with P4>20ng/ml (23.8%) was significantly lower than in the groups with low and intermediate P4 levels (42.6% and 37.5%, respectively, p = 0.018). The multivariable logistic regression confirmed that, after controlling for the confounding variables described above, P4>20ng/ml remained significantly associated with a higher LBR (OR: 2.285; 95% CI: 1.506-3.469) and a lower pregnancy loss rate (OR: 0.488; 95% CI: 0.273-0.873), irrespective of the use of rescue IM P4. Finally, a multivariable linear regression analysis of the patients baseline characteristics suggested that the only parameter predictive of midluteal P4 levels was the female patients’ weight, with an inverse relationship (adjusted regression coefficient: -0,012; 95% CI: -0,016/-0,009). Limitations, reasons for caution As the pituitary suppression, ovulation trigger and luteal support protocols used in the cycles included in the study were homogeneous (in order to maximize the internal validity of the results), this limits the extrapolibility of the results to other stimulation protocols. Furthermore, we caution that this is a retrospective study. Wider implications of the findings The usefulness of both midluteal P4 serum measurements and rescue P4 should continue to be assessed. The reasons behind the need for higher levels of P4 in a fresh cycle, when compared to natural cycles, must also be investigated. Luteal support may require personalization according to female body weight. Trial registration number Not Applicable

Enhancing fluid classification using meta-learning and transformer through small-sample drilling data to interpret well logging data

As geological exploration and oil and gas development continue to advance, improvement in fluid prediction becomes increasingly crucial. Drilling data often suffer from limited sample size, challenging traditional machine learning methods to fully harness these data. Consequently, a more adaptable and versatile approach is required. In response to this issue, we introduce the meta-ViT (Vision Transformer) method—a novel framework that merges meta-learning with the ViT. Meta-learning's parameter updating mechanism refines the model's ability to discern patterns and nuances across tasks, while ViT, powered by meta-learning, achieves an enhanced grasp of geological exploration characteristics, boosting fluid detection efficiency. The support set supplies meta-learning insights, while the query set assesses generalization. ViT excels at identifying subterranean fluids. Meta-learning replicates varied tasks and data distributions, fortifying model adaptability. Meanwhile, Transformers' self-attention mechanism captures distant dependencies that traditional long short-term memory struggle to manage. Their residual connections and layer normalization also address gradient challenges, simplifying training. Hence, our model effectively interprets intricate drilling data features, improving predictive accuracy and adaptability. In our experiments using a small drilling data sample set, we compared meta-ViT against other models. The results reveal superior performance of our model with limited data, affirming its efficacy and prominence in fluid classification tasks. Overall, our proposed solution excels in fluid classification tasks involving small-sample drilling data by utilizing available samples to enhance model adaptability and predictive performance.

FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations

Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of real images within a local region. Acting as loss surrogates, these synthetic samples are aggregated on the server side to uncover the global loss landscape and enable global optimization. Building upon these insights, we offer a new perspective to enforce record-level differential privacy in FL. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes while achieving an improved trade-off between privacy and utility. Extensive experiments validate the superiority of our approach across various datasets with highly skewed distributions in both DP and non-DP settings. Beyond the promising performance, our approach presents a faster convergence speed compared to typical gradient-sharing methods and opens up the possibility of trading communication costs for better performance by sending a larger set of synthetic images. The source is available at https://github.com/a514514772/FedLAP-DP.

Improving small sample prediction performance via novel nonlinear interpolation virtual sample generation with self-supervised learning

In the early stages of production processes, due to expensive experimental costs and demanding experimental conditions, the amounts of collected samples are relatively limited. Information and knowledge extracted from minimal experimental data may be distorted and unreliable. Tackling this task, some researchers have recommended virtual sample generation (VSG), aiming at improving prediction accuracy of forecasting models for small sample sets by creating informative artificial samples. To more effectively capture nonlinear feature representations in small data, in this paper, we propose a promising VSG method based on self-supervised learning architecture to generate optimal, feasible virtual samples. The suggested technology considers distilling nonlinear feature representations using a manifold algorithm. Based on these representations, we integrated Newton’s divided difference and Chebyshev interpolation to create nonlinear interpolation points. We feed those interpolation points into a U-net model and an encoder-decoder net model to produce virtual sample inputs and output, respectively. Additionally, in this paper, we developed a Siamese network model to select virtual samples resembling original data. In the experiments, two industrial datasets were utilized to demonstrate efficacy of the proposed method. These experimental results show that the proposed method can more successfully boost prediction accuracy compared to the other three cutting-edge VSG methods.

Prediction of local site influence on seismic vulnerability using machine learning: A study of the 6 February 2023 Türkiye earthquakes

This study uses machine learning to analyze local seismic features' influence on damage from the 6 February 2023 Türkiye Earthquakes.The input features include Vs30 (the average shear wave velocity to a depth of 30 m), f0 (the predominant frequency of the site), A0 (HVSR ratio for the site), and EBd (engineering bedrock depth), along with the target feature of damage status for 44 locations. Machine learning involves Random Forest (RF), K-nearest Neighbor (KNN), Logistic Regression (LR), Decision Trees (DT), Support Vector Machines (SVM), Stochastic Gradient Descent (SGD), and Multilayer Perceptron (MP) algorithms. Also, five-fold cross-validation is employed to acquire suitable hyperparameters, enhancing its efficacy in modeling small sample sets. RF emerged as the most effective in whole performance metrics, presenting recall scores for damage and no damage conditions respectively by a 94% and 92% ratio and achieving a damage status prediction accuracy of 93%. All remaining algorithms also exhibited remarkable performance, reaching a minimum accuracy of 89% by DT, and recall score for no damage condition with 80% by MP and damage condition with 88% by SVM and SGD. The outcomes definitively designate EBd as the most crucial parameter, attributing 52% importance to its role in building damage occurrence within the study area. In contrast, significance values were determined as 24%, 18%, and 6% for f0, Vs30 and A0 respectively. These findings underscore the importance of demonstrating that initial damage estimation in high seismic hazard zones can be effectively carried out using machine learning approaches through seismic-based local site parameters.

Targeted transcriptomic analysis of synovial tissues from horses with septic arthritis treated with immune-activated mesenchymal stromal cells reveals induction of T-cell response pathways.

To investigate mechanistically the reported beneficial effects of immune-activated mesenchymal stromal cell (MSC) therapy to treat equine septic arthritis, leveraging Nanostring technology. 8 Quarter Horses with induced tibiotarsal Staphylococcus aureus septic arthritis treated IA with either Toll-like receptor-3 agonist polyinosinic:polycytidylic acid-activated MSCs + vancomycin antimicrobials (TLR-MSC-VAN; n = 4) or antimicrobials (VAN; 4). Synovial tissues were collected and fixed in neutral-buffered 10% formalin, and formalin-fixed paraffin-embedded synovial and osteochondral tissues were sequenced using a custom-designed 200-gene equine Nanostring nCounter immune panel to directly quantify expression of key immune and cartilage-related genes. Immunohistochemistry to detect CD3+ T cells was performed on synovial tissues to further quantify T-cell infiltration in TLR-MSC-VAN- versus VAN-treated joints. Comparison of synovial transcriptomes between groups revealed moderate changes in differential gene expression, with upregulated expression of 9 genes and downregulated expression of 17 genes with fold change ≥ 2 or ≤ -2 and a significant false discovery rate-adjusted P value of ≤ .05. The most upregulated genes in TLR-MSC-VAN-treated horses included those related to T-lymphocyte recruitment and function, while pathways related to innate immune activation and inflammation were significantly downregulated. Immunohistochemistry and quantitation of CD3+ T-cell infiltrates revealed a numerically greater infiltrate in synovial tissues of TLR-MSC-VAN-treated horses, which did not reach statistical significance in this small sample set (P = .20). Targeted transcriptomic analyses using an equine Nanostring immune and cartilage health panel provided new mechanistic insights into how innate and adaptive immune cells within synovial tissues respond to TLR-activated MSC treatment when used to treat septic arthritis.

Shedding more light on shedders

We report on testing 100 individuals for their shedder status with the aim of demonstrating whether the process of cell staining is reproducible when testing a large number of people. A previous report using the same method was based on 11 donors and indicated that there may be a continuum of shedder types within this small sample set. In this report we also expand the time points post-handwashing to 0, 15, 30, 60, and 180 min. Triplicate samples were collected from both the right and left thumbs. Samples were collected by donors placing a thumb on a clean glass slide and then adding a DNA binding dye. The number of cells were recorded within three separate square millimetre areas (cells/mm2) at 220x magnification. The experiments were conducted in triplicate on three different days, giving a total of 72 thumbprints per individual. Finally, there were 3438 observed frames in the entire dataset. Of the 100 donors, 98 gave consistent and reproducible cell number deposition. There was no difference between the cells deposited by the left and right thumbs in 13 of 15 tested. Males tended to deposit more cells than females. If applying arbitrary boundary to a cell count to definitively determine shedder status, then many of the donors fell within two categories. This study based on 100 individuals strongly suggests that shedder status is a continuum phenomenon.

Physics-guided neural network for grinding temperature prediction

Creep-feed grinding is a high-efficiency, high-precision grinding process widely used in the manufacturing of aviation engines. However, the workpiece burn and other quality issues caused by high processing temperature limit the yield of grinding. Therefore, the accurate model of grinding temperature has become the key to improving processing efficiency and quality. Different from the traditional physical or data-driven models, this paper attempts to combine both perspectives based on Physics-Guided Neural Networks (PGNN) to accurately predict grinding temperature with a small number of experiments. At the level of data acquisition, real grinding experiment data was obtained and a data augmentation method had been proposed. At the level of neural network structure, optimisation processes were implemented to enhance prediction performance, and a physics-guided loss function was inserted to guide network training. The experiment results shows that PGNN had better prediction accuracy than the physical model, while also mitigating the limitations of data-driven models on small sample sets. PGNN also performed better with noisy data and predictions out of the training data range, this reveals the benefits of PGNN for small sample problems in processing scenarios.

High-Throughput Compound Quality Assessment with High-Mass-Resolution Acoustic Ejection Mass Spectrometry: An Automatic Data Processing Toolkit.

Pharmacological screening heavily relies on the reliability of compound libraries. To ensure the accuracy of screening results, fast and reliable quality control (QC) of these libraries is essential. While liquid chromatography (LC) with ultraviolet (UV) or mass spectrometry (MS) detection has been employed for molecule QC on small sample sets, the analytical throughput becomes a bottleneck when dealing with large libraries. Acoustic ejection mass spectrometry (AEMS) is a high-throughput analytical platform that covers a broad range of chemical structural space. In this study, we present the utilization of an AEMS system equipped with a high-resolution MS analyzer for high-throughput compound QC. To facilitate efficient data processing, which is a key challenge for such a high-throughput application, we introduce an automatic data processing toolkit that allows for the high-throughput assessment of the sample standards' quantitative and qualitative characteristics, including purity calculation with the background processing option. Moreover, the toolkit includes a module for quantitatively comparing spectral similarity with the reference library. Integrating the described high-resolution AEMS system with the data processing toolkit effectively eliminates the analytical bottleneck, enabling a rapid and reliable compound quality assessment of large-scale compound libraries.

Statistical methods to control for confounders in rare disease settings that use external control

ABSTRACT In the drug development for rare disease, the number of treated subjects in the clinical trial is often very small, whereas the number of external controls can be relatively large. There is no clear guidance on choosing an appropriate statistical method to control baseline confounding in this situation. To fill this gap, we conduct extensive simulations to evaluate the performance of commonly used matching and weighting methods as well as the more recently developed targeted maximum likelihood estimation (TMLE) and cardinality matching in small sample settings, mimicking the motivating data from a pediatric rare disease. Among the methods examined, the performance of coarsened exact matching (CEM) and TMLE are relatively robust under various model specifications. CEM is only feasible when the number of controls far exceeds the number of treated, whereas TMLE has better performance with less extreme treatment allocation ratios. Our simulations suggest bootstrap is useful for variance estimation in small samples after matching.

An Automated "Hands-Off" Method for Sampling Mainstream Smoke from Cannabis Cigarettes.

A simple-to-use, portable, and relatively inexpensive system for characterizing the chemical components of mainstream smoke from cannabis cigarettes was developed and tested by using commercial hemp cigarettes. The system is described, and its performance for reproducing actual user puff topographies is shown along with extensive chemical analysis data, including PAHs, carbonyls, and organic and elemental carbon, for a small set of initial samples. By using a solid-state flow meter and fast-response mass flow controller, the prototype can reproduce measured puff topography with excellent fidelity, which will allow users to accurately reproduce the actual inhalation patterns for various types of smoking products and consumers, and to collect samples of mainstream smoke without the need to bring test subjects or controlled substances into a laboratory.