Sampling Fraction Research Articles

Applying survey weights to ordinal regression models for improved inference in outcome-dependent samples with ordinal outcomes.

Researchers often use outcome-dependent sampling to study the exposure-outcome association. The case-control study is a widely used example of outcome-dependent sampling when the outcome is binary. When the outcome is ordinal, standard ordinal regression models generally produce biased coefficients when the sampling fractions depend on the values of the outcome variable. To address this problem, we studied the performance of survey-weighted ordinal regression models with weights inversely proportional to the sampling fractions. Through an extensive simulation study, we compared the performance of four ordinal regression models (SM: stereotype model; AC: adjacent-category logit model; CR: continuation-ratio logit model; and CM: cumulative logit model), with and without sampling weights under outcome-dependent sampling. We observed that when using weights, all four models produced estimates with negligible bias of all regression coefficients. Without weights, only stereotype model and adjacent-category logit model produced estimates with negligible to low bias for all coefficients except for the intercepts in all scenarios. In one scenario, the unweighted continuation-ratio logit model also produced estimates with low bias. The weighted stereotype model and adjacent-category logit model also produced estimates with lower relative root mean square errors compared to the unweighted models in most scenarios. In some of the scenarios with unevenly distributed categories, the weighted continuation-ratio logit model and cumulative logit model produced estimates with lower relative root mean square errors compared to the respective unweighted models. We used a study of knee osteoarthritis as an example.

Improved Standard Addition Method for Measuring Stable Isotopic Compositions and Its Application to Sulfur Isotope Composition.

The standard addition method (SAM) is widely used to measure the isotopic compositions of natural samples, particularly those with a complex matrix. However, traditional SAM has limitations for isotope systems with significant variations in isotope composition due to its reliance on approximation in calculation and the requirement for a priori estimates of analyte isotopic compositions and accurate concentrations. To overcome the issues, our work proposes an improved SAM that explicitly calculates isotope ratio R (i.e., XE/YE, 34S/32S for example) instead of approximating R* (mass number of isotope X divided by total mass number of all isotopes of an element) with R in SAM. Additionally, the sample fraction within standard-sample mixture in improved SAM is determined using the isotope compositions of standards, sample-standard mixtures, and the mixtures of both standards, rather than relying on sample concentrations and volumes. Both improvements not only overcome the shortcomings of traditional SAM but also empowered the approach's ability to accurately determine sample concentrations. To validate its effectiveness, we applied the improved SAM to natural samples with substantial sulfur (S) isotope variation (1.94 to 27.19‰) and low S concentration (0.81 to 3.47 μg g-1). The calculated δ34S values and concentrations of these samples are consistent with direct measurements within the error ranges while reducing sample sizes to 20% of those required for direct measurement. Moreover, our method achieves higher accuracy in δ34S values compared with traditional SAM. Both comparisons affirm the reliability and superiority of improved SAM.

A description of lineage 1 Mycobacterium tuberculosis from papua, Indonesia

Indonesia has the third highest number of tuberculosis (TB) patients infected with Mycobacterium tuberculosis (MTB) Lineage 1 (L1). Most of these MTB L1 cases can be found in Indonesia's remote easternmost province of Papua, one of Indonesia's most underdeveloped provinces with a particularly high burden for TB. In this study, we sequenced and described 42 MTB L1 isolates from a well-characterized cohort of patients. We found a genetically diverse MTB L1 population with no association between pathogen genetic relatedness and place of residence or pathogen genetic relatedness and patient ethnicity, which could reflect mixing between different locales and ethnicities or our low sampling fraction. Only a small number showed genetic variants associated with drug resistance (5/42, 11.9 %), probably due to a lack of effective treatment programs. The Papuan isolates showed similarities to other Island Southeast Asian Countries due to the high proportion of L1.2.1.2.1 (30/42, 71.4 %), especially East Timor and the Philippines. This study fills a research gap of MTB L1 in Indonesian Papua and should serve as a stepping stone for further research in the region.

Computational Cost Reduction in Multi-Objective Feature Selection Using Permutational-Based Differential Evolution

Feature selection is a preprocessing step in machine learning that aims to reduce dimensionality and improve performance. The approaches for feature selection are often classified according to the evaluation of a subset of features as filter, wrapper, and embedded approaches. The high performance of wrapper approaches for feature selection is associated at the same time with the disadvantage of high computational cost. Cost-reduction mechanisms for feature selection have been proposed in the literature, where competitive performance is achieved more efficiently. This work applies the simple and effective resource-saving mechanisms of the fixed and incremental sampling fraction strategies with memory to avoid repeated evaluations in multi-objective permutational-based differential evolution for feature selection. The selected multi-objective approach is an extension of the DE-FSPM algorithm with the selection mechanism of the GDE3 algorithm. The results showed high resource savings, especially in computational time and the number of evaluations required for the search process. Nonetheless, it was also detected that the algorithm’s performance was diminished. Therefore, the results reported in the literature on the effectiveness of the strategies for cost reduction in single-objective feature selection were only partially sustained in multi-objective feature selection.

Optimising fisheries monitoring for rare and protected species: A south-eastern Australian case study shows low levels of interaction with a critically endangered species

Scientific observer programs are often the only means to estimate the total number and circumstances of interactions (including the life status at the time of the interaction) between commercial fisheries and threatened, endangered and protected species (TEPS). However, without estimating the precision of predefined sampling fractions, the accuracy of estimates are often poorly understood. We present a methodology to estimate appropriate sampling fractions using historical observer data from the New South Wales (Australia) ocean trap and line fishery, and implement an on-board monitoring program to estimate contemporary rates of interactions with TEPS in the fishery to evaluate the effectiveness of management measures implemented to reduce interactions. A total of 327 fishing trips (∼61,150 hook deployments) were sampled over 31 months with a single observed interaction each with the critically endangered grey nurse shark (Carcharius taurus) and scalloped hammerhead (Sphyrna lewini) recorded along with the capture of six seabirds. Observed catches included 97 species (70 finfish, 23 elasmobranchs, 1 invertebrate and 3 birds), of which 74 and 57 species were retained and discarded, respectively. Current fishing practices, combined with declines is reported effort targeting ‘large sharks’ following management reform, spatial protection measures, and gear regulations, were found to be minimising interactions between the main fishing method and TEPS. However, regular monitoring and research may be required to continually assess the effectiveness of mitigation strategies. The logic and methodology for determining appropriate sample fractions using existing data before implementing on-board sampling is relevant to the monitoring of other commercial fisheries.

Confluence-based suspended sediment fingerprinting: an exploratory approach to determining source to sink sediment contributions in the Tsitsa River catchment, Eastern Cape, South Africa

ABSTRACT In the Tsitsa River catchment of the Eastern Cape Province, South Africa, concerns regarding the sedimentation of a proposed large, multipurpose, in-channel water storage scheme prompted investigations of sub-catchment suspended sediment loads and yields. Confluence-based fingerprinting and source apportionment was undertaken to explore whether this simple approach could identify relative sub-catchment contributions to downstream sediment loads, supplementing modelling and direct sampling. In November 2018, fine sediment sequestered in bed substrates was sampled above and below confluences, using a resuspension technique. The < 63 µm sample fraction underwent analysis of mineral magnetic properties, gamma emitting radionuclide activities and geochemistry to identify suitable tracers. Conservatism and range tests were used to select different combinations of composite fingerprints at seven confluences. Bivariate source apportionment using an unmixing model showed that the approach could be used as a preliminary means of determining relative sub-catchment sediment contributions. Catchment characteristics such as geology and land cover, as well as land tenure and management, were considered as explanatory factors for the difference in sediment contributions. The results for most sub-catchments were broadly similar to those from other studies. Shortcomings of this approach included the reliance on a single sampling effort, and uncertainty associated with sub-catchment sediment transport and residence times.

Muon beamtest results of high-density glass scintillator tiles

To achieve the physics goal of precisely measure the Higgs, Z, W bosons and the top quark, future electron-positron colliders require that their detector system has excellent jet energy resolution. One feasible technical option is the high granular calorimetery based on the particle flow algorithm (PFA). A new high-granularity hadronic calorimeter with glass scintillator tiles (GSHCAL) has been proposed, which focus on the significant improvement of hadronic energy resolution with a notable increase of the energy sampling fraction by using high-density glass scintillator tiles. The minimum ionizing particle (MIP) response of a glass scintillator tile is crucial to the hadronic calorimeter, so a dedicated beamtest setup was developed for testing the first batch of large-size glass scintillators. The maximum MIP response of the first batch of glass scintillator tiles can reach up to 107 p.e./MIP, which essentially meets the design requirements of the CEPC GSHCAL. An optical simulation model of a single glass scintillator tile has been established, and the simulation results are consistent with the beamtest results.

The Correlation Between Knowledge of Local Food Utilization and Clean, Healthy Living Behavior with Nutritional Status of Toddlers

Background: Nutritional status issues in toddlers are caused by insufficient food intake and diseases. The most important primary prevention effort involve various human activities and behaviors, including meeting nutritional needs and implementing the Clean Healthy Living Behavior program. Method: This study employed a quantitative approach with a Cross-sectional research design. The sample consisted of 74 mothers of toddlers aged 6-59 months in Panembangan Village, Cilongok District, Banyuma Regency, selected using the Sampling Fraction Per Cluster technique. Data were analyzed using the Chi-Square test. Results: The study found that the most dominant level of education was junior hight school (39,2%), and most mother were housewives (87,8%). Most parents in Panembangan Village had good knowladge of local food utilization (70,3%), and there was a significant correlation between parental knowladge and nutritional status, with Continuity Correction of 0.037. In terms of Clean, Healthy Living Behavior (CHLB), most respondents in Panembangan Village exhibited good behavior (94,6%), and there was a significant relationship between CHLB and the nutritional status of toddlers, with a Fisher’s Exact Test of 0,046. Conclusion: There is a correlation between knowledge of local food utilization and clean, healthy living behavior with nutritional status of toddlers.

Optimising high-throughput sequencing data analysis, from gene database selection to the analysis of compositional data: a case study on tropical soil nematodes

Optimising high-throughput sequencing data analysis, from gene database selection to the analysis of compositional data: a case study on tropical soil nematodes

Inference of Infectious Disease Transmission through a Relaxed Bottleneck Using Multiple Genomes Per Host.

In recent times, pathogen genome sequencing has become increasingly used to investigate infectious disease outbreaks. When genomic data is sampled densely enough amongst infected individuals, it can help resolve who infected whom. However, transmission analysis cannot rely solely on a phylogeny of the genomes but must account for the within-host evolution of the pathogen, which blurs the relationship between phylogenetic and transmission trees. When only a single genome is sampled for each host, the uncertainty about who infected whom can be quite high. Consequently, transmission analysis based on multiple genomes of the same pathogen per host has a clear potential for delivering more precise results, even though it is more laborious to achieve. Here, we present a new methodology that can use any number of genomes sampled from a set of individuals to reconstruct their transmission network. Furthermore, we remove the need for the assumption of a complete transmission bottleneck. We use simulated data to show that our method becomes more accurate as more genomes per host are provided, and that it can infer key infectious disease parameters such as the size of the transmission bottleneck, within-host growth rate, basic reproduction number, and sampling fraction. We demonstrate the usefulness of our method in applications to real datasets from an outbreak of Pseudomonas aeruginosa amongst cystic fibrosis patients and a nosocomial outbreak of Klebsiella pneumoniae.

Doctor’s Communication Skills and Mode of Communication as Determinants of Quality Patient Care Management in Two Selected Teaching Hospitals in Southwest Nigeria

Quality patient care management is a systematic way to measuring, recording, monitoring, and continually improving efficiency, accessibility to high-quality healthcare, and patient satisfaction. Doctors in the teaching hospitals are at the center of research activities since intense patient care management are usually carried out by them. Previous studies have found that doctors seem not to be working towards quality patient care management in their teaching hospitals which could largely be attributed to certain factors such as doctor’s communication skills and doctors’ mode of communication. Using descriptive research design of the correlational type, the population comprised 658 doctors in two teaching hospitals namely Ekiti State University teaching hospital (EKSUTH) and OBAFEMI AWOLOWO UNIVERSITY TEACHING HOSPITAL (OAUTHC). Two stage stratified sampling technique (proportional type) was used to select samples from the population of the three doctors cadre in the two selected teaching hospitals. A sample fraction of 3/10 was used across all the cadre to get a total size of 197 for both selected teaching hospitals. A self-structured questionnaire comprising five sections was validated. Out of the 197 copies of the questionnaire administered, 187 representing 94.9% were retrieved and used for analysis. Descriptive statistics of frequency counts, percentages and means were used to analyze the research questions, while correlation and regression were used to test the hypotheses at 0.05 level of significance. There is positive weak relationship between doctors’ communication skills and quality patient care management (r = 0.357, p&lt; 0.05). Doctors’ communication skills, and doctors mode of communication play vital roles in quality patient care management. Associations have been identified between these factors and quality patient care management. It is established by the study that doctors’ communication skills and modes monotonically influenced quality patient care management. Doctors’ communication skills and modes of doctor’s communication has positive effect while no effect on the quality of patient care management. Therefore, it is recommended that the hospital should channel more efforts and resources to improve the standard of communication skills of the doctors.

GSHCAL at future [formula omitted] Higgs factories

The excellent jet energy resolution is crucial for the precise measurement of the Higgs properties at future e+e− Higgs factories, such as the Circular Electron Positron Collider (CEPC). For this purpose, a novel design of the particle flow oriented hadronic calorimeter based on glass scintillators (GSHCAL) is proposed. Compared with the designs based on gas or plastic scintillators, the GSHCAL can achieve a higher sampling fraction and more compact structure in a cost-effective way, benefiting from the high density and low cost of glass scintillators. In order to explore the physics potential of the GSHCAL, its intrinsic energy resolution and the contribution to the measurement of the hadronic system was investigated by Monte Carlo simulations. Preliminary results show that the stochastic term of hadronic energy resolution can reach around 24% and the Boson Mass Resolution (BMR) can reach around 3.38% when the GSHCAL is applied. Besides, the key technical R&D of high-performance glass scintillator tiles is also introduced.

A comparison of likelihood-based methods for size-biased sampling

Three likelihood approaches to estimation under informative sampling are compared using a special case for which analytic expressions are possible to derive. An independent and identically distributed population of values of a variable of interest is drawn from a gamma distribution, with the shape parameter and the population size both assumed to be known. The sampling method is selection with probability proportional to a power of the variable with replacement, so that duplicate sample units are possible. Estimators of the unknown parameter, variance estimators and asymptotic variances of the estimators are derived for maximum likelihood, sample likelihood and pseudo-likelihood estimation. Theoretical derivations and simulation results show that the efficiency of the sample likelihood approaches that of full maximum likelihood estimation when the sample size n tends to infinity and the sampling fraction f tends to zero. However, when n tends to infinity and f is not negligible, the maximum likelihood estimator is more efficient than the other methods because it takes the possibility of duplicate sample units into account. Pseudo-likelihood can perform much more poorly than the other methods in some cases. For the special case when the superpopulation is exponential and the selection is probability proportional to size, the anticipated variance of the pseudo-likelihood estimate is infinite.

A new imputation method for population mean in the presence of missing data based on a transformed variable with applications to air pollution data in Chiang Mai, Thailand

Introduction: Chiang Mai’s air pollution has risen to number one in the world for the highest level of fine particulate matter which further exacerbates the damage to human health. Fine particulate matter can enter the human body and blood circulation, destroying organ systems, increasing the risk for chronic disease and cancer, despite not having smoking habits or other morbidities. The Thai government must sort out this issue before it is too late as the whole nation’s health is at risk due to excessive dust levels higher than standard guidelines. Collection of pollution data can help us to come up with solutions and prevent it from turning into a hazardous situation. Unfortunately, pollution data are missing and need to be dealt with before analysis to obtain accurate results. Materials and methods: A new method of imputation for estimating population mean based on a transformed variable has been suggested under simple random sampling without replacement and the uniform nonresponse mechanism. The bias and mean square error of the proposed estimator are investigated up to the first order of approximation. The performance of the proposed estimator is studied via applications to air pollution data in Chiang Mai, Thailand. Results: The proposed estimator shows the best performance, giving the least bias and mean square error for all levels of sampling fractions. For the results from application the estimated value of sulfur dioxide from Particulate Matter 2.5 (PM2.5), the Percentage Relative Efficiency (PRE) is higher than all existing estimators by at least 16%. For the estimated PM2.5 from PM10 the PRE is higher than all existing estimators by at least 1600%, an extremely significant difference exhibiting similarity to real values. Conclusion: The proposed imputation technique based on the transformed auxiliary variable can be helpful for imputing missing values and improving the efficiency of the estimators.

Reconstructing the digital twin of forests from a 3D library: Quantifying trade-offs for radiative transfer modeling

Radiative transfer models that use spatially explicit 3D models to represent forest structure can simulate highly realistic Earth Observation (EO) data. Such simulations at the forest stand scale (≥ 1-ha) allow for more direct calibration and validation of EO products. Explicitly reconstructing 3D forest structures at scales that can be compared directly with satellite EO data (i.e., dozens to hundreds of meters) is challenging. Reconstructing large forest areas (≥ 1-ha) using a representative subset (i.e., forest subsampling) is a potentially more practical and feasible method. However, the impacts of forest subsampling on radiative transfer (RT) modeling were never formally tested in the spatially explicit forest scene.This study quantified the trade-offs involved in two main subsampling approaches when reconstructing the spatially explicit scene of a real forest for RT modeling. The two subsampling approaches were: (1) subplot subsampling - area-based, using the subplot (i.e. a fixed area) as the basic sampling and reconstruction unit; and (2) tree library subsampling - tree-based, using the individual tree as the basic sampling and reconstruction unit. We used the Discrete Anisotropic Radiative Transfer Model (DART) to simulate the Bidirectional Reflectance Factor (BRF) of the completely reconstructed 1-ha 3D-explicit forest scene, as well as the simplified forest scenes built from various subsets of the same forest. The simulated reflectance deviation of the simplified forest scenes was evaluated by comparing it with the fully reconstructed forest scene.The results showed that for subplot subsampling, as the sampling fraction increased from 10% to 90%, the normalized mean BRF deviation of radiative transfer simulations decreased from −2.7% to −0.0034% and its standard deviation decreased from 7.7% to 0.54%. Additionally, as the sampling fraction increased from 10% to 90%, the normalized mean BRF deviation of tree library subsampling decreased from −7.4% to −1.3% and its standard deviation decreased from 2.8% to 0.51%.Overall, sampling 20% of the forest area using the subplot subsampling method was an effective reconstruction strategy for the temperate deciduous forest. This strategy ensured a normalized mean BRF deviation of −2.9% and a standard deviation of 3.7% in the forest stand studied, with a relatively low reconstruction effort.This study shows that the forest subsampling approach allows for reconstructing 3D-explicit forest scenes for RT modeling at the forest stand scale (≥ 1-ha). Accordingly, highly realistic EO data can be modeled at the forest stand scale, which allows for more direct calibration and validation of EO products.

The utility of SARS-CoV-2 genomic data for informative clustering under different epidemiological scenarios and sampling.

Clustering pathogen sequence data is a common practice in epidemiology to gain insights into the genetic diversity and evolutionary relationships among pathogens. We can find groups of cases with a shared transmission history and common origin, as well as identifying transmission hotspots. Motivated by the experience of clustering SARS-CoV-2 cases using whole genome sequence data during the COVID-19 pandemic to aid with public health investigation, we investigated how differences in epidemiology and sampling can influence the composition of clusters that are identified. We performed genomic clustering on simulated SARS-CoV-2 outbreaks produced with different transmission rates and levels of genomic diversity, along with varying the proportion of cases sampled. In single outbreaks with a low transmission rate, decreasing the sampling fraction resulted in multiple, separate clusters being identified where intermediate cases in transmission chains are missed. Outbreaks simulated with a high transmission rate were more robust to changes in the sampling fraction and largely resulted in a single cluster that included all sampled outbreak cases. When considering multiple outbreaks in a sampled jurisdiction seeded by different introductions, low genomic diversity between introduced cases caused outbreaks to be merged into large clusters. If the transmission and sampling fraction, and diversity between introductions was low, a combination of the spurious break-up of outbreaks and the linking of closely related cases in different outbreaks resulted in clusters that may appear informative, but these did not reflect the true underlying population structure. Conversely, genomic clusters matched the true population structure when there was relatively high diversity between introductions and a high transmission rate. Differences in epidemiology and sampling can impact our ability to identify genomic clusters that describe the underlying population structure. These findings can help to guide recommendations for the use of pathogen clustering in public health investigations.

A species richness estimator for sample‐based incidence data sampled without replacement

Abstract The accurate estimation of species richness in a target region is still a statistical challenge, especially in a highly heterogeneous community. Most richness estimators have been developed based on the assumption that data are randomly sampled with replacement or that data are sampled from an infinite population. However, in reality, most sampling schemes in the field are implemented as sampling without replacement (SWOR). As such, estimators derived based on sampling with replacement may cause overestimation as the sampling fraction increases and not converge to the true richness as the sampling fraction approaches one. Sample‐based incidence data, in which the sampling unit is a plot, and only the presence or absence of a species in each chosen plot is recorded, is one of the most commonly used data types for assessing species diversity in ecological studies. In this manuscript, according to sample‐based incidence data collected through SWOR, a new richness estimator is proposed using a truncated beta‐binomial mixture model. The new estimator was obtained through the moment approach, which avoids using iterative numerical algorithms for parameter estimation and presents a closed‐form estimator as an alternative to the maximum likelihood method. Although the newly proposed method is a parametric‐based richness estimator, similar to nonparametric estimators, only the rare species in the sample (i.e. the frequencies of uniques and duplicates) are required to estimate undetected richness. Based on the hypothetical models, the statistical performances of the proposed estimator are evaluated under varying degrees of heterogeneity and different mean species detection rates. Compared to other widely used nonparametric and parametric estimators, the simulation results indicate that the proposed estimator has a smaller bias and lower root mean square error when the sampling fraction is greater than 10%, particularly in highly heterogeneous communities. In addition, one ForestGEO permanent forest plot dataset is used to evaluate and compare the proposed approach with other estimators discussed in the study. The results demonstrate that the proposed estimator, in comparison to other widely used estimators, produces less biased estimate of true richness, along with more accurate 95% confidence interval.

Improved Ratio Type Estimators using some Prior Information in Sample Surveys: A Case Study of Fine Particulate Matter in Thailand

Air pollution affects Thai people's health and social life nowadays as it exceeds the standards levels of both Thailand and the World Health Organization. Estimating air pollution data can benefit understanding and determining policies to help deal with this issue. Prior knowledge from past surveys or censuses could be useful for increasing the effect of the estimation. Improved ratio estimators utilizing prior knowledge in simple random sampling without replacement have been advocated. The property of the mean square error of the proposed class of estimators is obtained. We applied the proposed estimators to the fine particulate matter data in Dindang in 2019. The results from the air pollution data illustrate the improved ratio type estimators work better with respect to the existing estimator using some prior information. Existing knowledge of the quartile average and the median of the auxiliary variable gives rise to the best estimators with the lowest mean square errors for estimating fine particulate matter. Nevertheless, the proposed estimators are useful for small sampling fractions which can help in financial and time-consuming.

Calyceraceae: Unexpected diversification pattern in the Southern Andes

Calyceraceae comprises 46 species mostly endemic to the Andes and Patagonia in Southern South America, and it is the sister family of Asteraceae, one of the largest Angiosperm families. With a robust phylogeny and with an exceptionally good sampling fraction, we performed macroevolution and biogeographic analyses to understand paleodiversity dynamics through time and space, and its potential drivers. We address the impact of the Andean uplift, global temperature, life forms, and biogeography on Calyceraceae diversification through a time-calibrated phylogeny. Calyceraceae diversification was homogeneous through time and followed a low speciation rate for the last 24 Mya, with no lineage differing much in their diversification dynamics. In accordance with the homogeneous speciation rate, we found that neither the Andean uplift, nor the evolution of global average temperature, nor the different life forms have affected its diversification. The Southern Andes is the centre of origin of the family and major clades within it, and most dispersal events occurred from the Andes to Patagonia. Most Calyceraceae species seem to have originated, evolved, and dispersed within the Argentinean Arid Diagonal, indicating that niche conservatism could have played an important role in the evolution of Calyceraceae. Differences in macroevolution dynamics could explain the asymmetry of species richness in the two sister families Asteraceae-Calyceraceae.

Adaptive Learning and Integrated Use of Information Flow Forecasting Methods

This research aims to improve quality indicators in solving classification and regression problems based on the adaptive selection of various machine learning models on separate data samples from local segments. The proposed method combines different models and machine learning algorithms on individual subsamples in regression and classification problems based on calculating qualitative indicators and selecting the best models on local sample segments. Detecting data changes and time sequences makes it possible to form samples where the data have different properties (for example, variance, sample fraction, data span, and others). Data segmentation is used to search for trend changes in an algorithm for points in a time series and to provide analytical information. The experiment performance used actual data samples and, as a result, obtained experimental values of the loss function for various classifiers on individual segments and the entire sample. In terms of practical novelty, it is possible to use the obtained results to increase quality indicators in classification and regression problem solutions while developing models and machine learning methods. The proposed method makes it possible to increase classification quality indicators (F-measure, Accuracy, AUC) and forecasting (RMSE) by 1%–8% on average due to segmentation and the assignment of models with the best performance in individual segments. Doi: 10.28991/ESJ-2023-07-03-03 Full Text: PDF