Sample Selection Method Research Articles

Application SIMPUS (Sistem Informasi Manajamen Puskesmas) with TAM Theory (Technology Acceptance Model) at Puskesmas Setabelan in Surakarta

Based on the results of the preliminary study, Puskesmas Setabelan in implementing the SIMPUS application has not been maximized because at the end of each month the internet network is often erroneous because it does not have a good provider, there are still new employees who have not received socialization related to the use of the SIMPUS application, and the patient's online registration has not been opened due to the condition of the community who are still unfamiliar with technology. So the researcher is interested in analyzing how effective the acceptance of the use of the SIMPUS (Puskesmas Management Information System) application is using the TAM (Technology Acceptance Model) theory at the Setabelan Health Center in Surakarta City. This type of research is qualitative and descriptive with data collection methods in-depth interviews with 11 informants including SIMPUS coordinators, SIMPUS programmers, nurses, midwives, pharmacists, dental nurses and administrative staff. The sample selection method used purposive sampling method.

Analisis Faktor-Faktor yang Mempengaruhi Auditor Switching di Indonesia Studi Empiris pada Perusahaan Manufaktur yang Terdaftar di Bursa Efek Indonesia

This research aims to analyze the factors that influence auditor switching in manufacturing companies. This research is quantitative research. The data used is secondary data from manufacturing company financial reports. The sample for this research is manufacturing companies listed on the Indonesia Stock Exchange for the 2017-2021 period. The sample selection method used was the purposive sampling method. The total sample for this research is 52 companies from 2017-2021 as the year of observation. The amount of data analyzed was 250 data. The analytical method used in this research is descriptive statistics and logistic regression testing using the SPSS Version 22 program. The results of the research show that audit opinion has an effect on auditor switching. Meanwhile, management changes and KAP size have no effect on auditor switching.

Prediction of deep low permeability sandstone seismic reservoir based on CBAM-CNN

The prediction of sand body is a key focus in evaluating reservoir distribution, playing a crucial role in oil and gas exploration and development. To clarify the development characteristics of the sand body in the Huangyan structural belt of the Xihu Sag and effectively identify the hidden channel, a new approach is proposed. This approach incorporates a Convolutional Block Attention Module (CBAM) into a Convolutional Neural Network (CNN). Well logging and seismic data were used to predict the distribution of sand body in the lower section of the Huagang Formation (H12). Firstly, based on known sand-stratum ratio data and well-side seismic data, the seismic attributes that are sensitive to the reservoir response are preferred through correlation analysis, which are used to construct a Polynomial Linear Regression (PLR) model to obtain the preliminary sand distribution prediction results. Secondly, the grid is divided according to this result. Then, three sample selection methods, namely proportional, fixed-range, and random, are used to construct three sample sets in conjunction with the geologic model guide. Finally, CBAM-CNN, CNN, Random Forest (RF), Support Vector Machines (SVM), and Backpropagation Neural Network (BPNN) are utilized for sand body prediction. The results indicate that when using the same model, the sample set selected by the fixed-range selection method yielded the best prediction outcome. When using the same sample set, the CBAM-CNN model outperformed the others. Among various strategies, training the CBAM-CNN model with the sample set derived from the fixed-range selection method led to the highest test set R2 of 0.913. The results of the sand body distribution indicate that fine river channels are more continuous, and reservoir boundaries are clearer, significantly outperforming other schemes. This outcome can serve as a guide for further reservoir delineation.

Considering the effect of non-landslide sample selection on landslide susceptibility assessment

Crafting landslide susceptibility mapping is pivotal for the effective management of landslide risks. However, the influence of non-landslide sample selection on the modeling performance of landslide susceptibility assessment models remains a crucial challenge to overcome. This article employs Huize County as the research area and identifies 12 factors that exert influence. In this study, we utilized Extreme Gradient Boosting and Random Forest algorithms, and four methods (Whole-area random selection method, Buffer method, Frequency Ratio method, and Analysis Hierarchy Process) were employed to select non-landslide samples for constructing the landslide susceptibility assessment model. The findings revealed that the model performance derived from different non-landslide sample selections exhibited significant variations, and the models obtained using the buffer zone method, frequency ratio method, and AHP method performed better than the full-area random selection model. Among the evaluated models, the AHP method for non-landslide sample selection demonstrated the most optimal performance, with an AUC of 92.17% for XGBoost-AHP and 91.64% for RF-AHP. Based on the SHapley Additive explanation (SHAP), the main variables impacting landslide danger in the research area were elevation, NDVI, and peak seismic acceleration. This study provides theoretical support for the selection of non-landslide samples in landslide susceptibility assessments and interpretable AI research.

Pengaruh Sales Growth, Tax Planning, dan Ukuran Perusahaan Terhadap Manajemen Laba (Studi Empiris pada Perusahaan Manufaktur Sektor Industri Dasar dan Kimia yang terdaftar di Bursa Efek Indonesia tahun 2019-2021)

Earnings Management is the process of taking certain deliberate steps within the limits of generally accepted accounting principles to produce the desired level of reported profits. The data used in this research is secondary data from financial report data of Basic Manufacturing and Chemical companies listed on the Indonesia Stock Exchange. The sample in this study consisted of 13 companies that were consistent in reporting financial reports and had been selected using several sample observation criteria. The sample selection method is using purposive sampling, namely a sampling method with certain criteria. The analytical method used is Multiple Linear Analysis and Coefficient of Determination. The hypothesis testing method in this research uses the t-test and F-test. The results of this research show that the Sales Growth variable shows a t-count value of 1.783. The significance level shows 0.005 which is smaller than the significance level of 0.004. This means that H1 is accepted and it can be concluded that Sales Growth independently has a significant effect on Profit Management.

Pengaruh Kepemilikan Manajerial, Kepemilikan Institusional, Ukuran Perusahaan Terhadap Kinerja Keuangan Dimoderasi Struktur Modal

This study aims to determine the effect of managerial ownership, institutional ownership and firm size on financial performance with capital structure as a moderating variable in manufacturing companies listed on the Indonesia Stock Exchange in 2017 - 2021. The sample selection method used is purposive sampling. The total observations in this study were 115 samples consisting of 23 companies. The data analysis technique used in this study is Moderated Regression Analysis (Interaction Test) using the SPSS 26 analysis tool. The results of this study indicate that managerial ownership, institutional ownership, firm size and capital structure simultaneously affect on financial performance. Partially, institutional ownership has a positive influence on financial performance, while managerial ownership and firm size have no influence on financial performance. Capital structure is able to moderate and strengthen the relationship between firm size on financial performance, while capital structure is unable to moderate the effect of managerial ownership and institutional ownership on financial performance.

The effect of firm size and transfer pricing on tax aggressiveness with institutional ownership as a moderating variable

This study aims to empirically prove the influence of firm size and transfer pricing on tax aggressiveness with institutional ownership as a moderating variable. The independent variables used in this research are firm size and transfer pricing. The dependent variable used in this research is tax aggressiveness and the moderating variable uses institutional ownership. The population in this study are basic materials sector companies listed on the Indonesia Stock Exchange in 2018-2022. The sample selection method used purposive sampling, based on this method 14 (fourteen) companies were obtained, the data that was successfully used as a research sample was 8 (eight) companies with observations for 5 (five) years. The data used in this research is secondary data in the form of annual financial reports. The results of this research indicate that Firm Size and Transfer Pricing simultaneously have a significant effect on Tax Aggressiveness. The results of research conducted partially state that Firm Size and Transfer Pricing influence Tax Aggressiveness. Apart from that, Institutional Ownership is unable to moderate the influence of firm size and transfer pricing on Tax Aggressiveness.

Calibration transfer between NIR instruments using optimally predictive calibration subsets.

In this study, a new approach for the selection of informative standardization samples from the original calibration set for the transfer of a calibration model between NIR instruments is proposed and evaluated. First, a calibration model is developed, after variable selection by the Final Complexity Adapted Models (FCAM) method, using the significance of the PLS regression coefficients (FCAM-SIG) as selection criterion. Then, the resulting model is used for the selection of the best fitting subset of calibration samples with optimally predictive ability, called the optimally predictive calibration subset (OPCS). Next, the standardization samples are selected from the OPCS. The spectra on the slave instruments are transferred to corresponding spectra on the master instrument by the widely used Piecewise Direct Standardization (PDS) method. Thereafter, for the test set on the slave instrument, a 3D response surface plot is drawn for the root mean squared error of prediction (RMSEP) as a function of the number of OPCS samples and window sizes used for the PDS method. Finally, the smallest set of calibration samples, in combination with the optimal window size, providing the optimal RMSEP, is selected as standardization set. The proposed OPCS approach for the selection of standardization samples is tested on two real-life NIR data sets providing 13 X-y combinations to model. The results show that the obtained numbers of OPCS-based standardization samples are statistically significantly lower than those obtained with the widely used representative sample selection method of Kennard and Stone, while the predictive performances are similar.

HAPPINESS AND ACADEMIC PERFORMANCE OF POST GRADUATE STUDENTS: A PREDICTIVE STUDY

The study aimed at exploring the correlation of happiness level of postgraduate university students and their academic performance. Data was gathered from students in the second semester of their courses, using the fish bowl method for random sample selection. After collecting the data, SPSSv26 was utilized for descriptive analysis and regression analysis. The research findings indicated no significant difference in happiness levels based on gender of postgraduate students. Furthermore, an insignificant positive correlation was observed between happiness and academic achievement. The regression analysis confirmed that happiness does not serve as a significant predictor for the academic success of postgraduate students at Jammu University.

A Noisy Sample Selection Framework Based on a Mixup Loss and Recalibration Strategy

Deep neural networks (DNNs) have achieved breakthrough progress in various fields, largely owing to the support of large-scale datasets with manually annotated labels. However, obtaining such datasets is costly and time-consuming, making high-quality annotation a challenging task. In this work, we propose an improved noisy sample selection method, termed “sample selection framework,” based on a mixup loss and recalibration strategy (SMR). This framework enhances the robustness and generalization abilities of models. First, we introduce a robust mixup loss function to pre-train two models with identical structures separately. This approach avoids additional hyperparameter adjustments and reduces the need for prior knowledge of noise types. Additionally, we use a Gaussian Mixture Model (GMM) to divide the entire training set into labeled and unlabeled subsets, followed by robust training using semi-supervised learning (SSL) techniques. Furthermore, we propose a recalibration strategy based on cross-entropy (CE) loss to prevent the models from converging to local optima during the SSL process, thus further improving performance. Ablation experiments on CIFAR-10 with 50% symmetric noise and 40% asymmetric noise demonstrate that the two modules introduced in this paper improve the accuracy of the baseline (i.e., DivideMix) by 1.5% and 0.5%, respectively. Moreover, the experimental results on multiple benchmark datasets demonstrate that our proposed method effectively mitigates the impact of noisy labels and significantly enhances the performance of DNNs on noisy datasets. For instance, on the WebVision dataset, our method improves the top-1 accuracy by 0.7% and 2.4% compared to the baseline method.

Mitigating data imbalance and noise: A divergence-based approach with enhanced sample selection

Label noise and distribution imbalance are common challenges in real-world datasets. To address noisy labels, sample selection methods are typically used. These methods identify small-loss data as correctly labeled and utilize only these clean samples for updating parameters during training. However, our thorough analysis shows that in scenarios with a long-tailed distribution, methods based on small-loss tend to favor samples from dominant classes, leading to a significant drop in performance. To tackle this issue, we introduce a divergence-based separation mechanism coupled with prototype distance for clean sample identification across each class, effectively mitigating the adverse effects of distribution imbalance on sample selection. Furthermore, drawing on recent theoretical insights that highlight the benefits of pseudo-labels in managing class imbalances, we enhance our approach by integrating semi-supervised and contrastive learning techniques. Comprehensive tests conducted on two synthetic noisy long-tailed datasets and one real-world dataset demonstrate the efficacy of our method in dealing with label noise and long-tailed distributions.

The Effect Of Market Segmentation And Product Distribution On Product Sales Volume PT. Garuda Mas Perkasa Medan

This research aims to determine and analyze the effect of market segmentation and product distribution on sales volume at PT Garuda Mas Perkasa Medan. The type of research in this study is quantitative with an associative approach. The population of this study were employees of PT Garuda Mas Perkasa Medan. The sample selection method uses saturated sampling, the number of samples used is 50 sample data. Before conducting research, first test the instrument with validity test and reliability test. Prerequisite test analysis includes normality test, multicollinearity test and heteroscedasticity test. The data analysis method uses multiple linear regression. The results of this study are in accordance with the first hypothesis, that market segmentation affects sales volume. This can be seen from the test results which show that the value of 3.915 is greater than 2.010 with a significance value of 0.000 less than 0.05. The results of this study are in accordance with the second hypothesis, that product distribution has an effect on sales volume. This can be seen from the test results which show that the value of 3.580 is greater than 2.010 with a significance value of 0.000 smaller than 0.05. The results of the study are in accordance with the third hypothesis, that market segmentation and product distribution simultaneously affect sales volume. This can be seen from the F test which shows a significance value smaller than 0.05, which is 0.000. Then Fcount> Ftable (26.845> 3.190).

The Effect of Compensation, Work Environment, and Career Development on Employee Turnover Intention of PT XYZ Final Assembly Department

This research aims to analyze the effect of compensation, work environment, and career development on turnover intention among employees in the Final Assembly Department at PT XYZ. Involving 87 respondents who are employees of the department, this research employs a saturated sampling method for sample selection. Data collection is conducted through the distribution of questionnaires using Google Form. Analysis is performed using Multiple Linear Regression Analysis, with t and f statistical tests to test hypotheses. The results indicate that compensation, work environment, and career development partially have a significant negative effect on employees' intention to leave their jobs. Additionally, simultaneously, these three factors also have a significant impact on turnover intention. This study provides a deeper understanding of the factors affecting turnover intention among employees in the Final Assembly Department PT XYZ, and it offers important implications for human resource management in efforts to retain competent and quality employees.

Dynamic selection for reconstructing instance-dependent noisy labels

As an inevitable issue in annotating large-scale datasets, instance-dependent label noise (IDN) can cause serious overfitting in neural networks. To combat IDN, label reconstruction methods have been developed with noise transition matrices or DNNs to simulate the transition from clean labels to noisy labels. Nevertheless, the absence of correct supervisions will lead to learning wrong noise transitions. This motivates us to select samples with clean labels to fetch the correct supervisions. However, the difficulty in obtaining prior knowledge of the noise rate prohibits the use of existing sample selection methods. To this end, we propose a dynamic sample selection method, namely Identity Mapping (IdMap), to overcome this limitation. Inspired by the feature-dependent characteristic of IDN, we first introduce the extracted instance features and pseudo-ground-truth labels to reconstruct noisy labels. A partial identity mapping between two labels is then established and samples with consistent identity mapping output are selected as clean data to update the classifier. Extensive experiments on both artificial and real-world noisy datasets demonstrate the superiority of IdMap compared with other state-of-the-art methods.

The influence of sales growth and capital intensity on tax aggressiveness with inventory intensity as a moderating variabel

This research aims to empirically prove the influence of sales growth and capital intensity on tax aggressiveness, with inventory intensity as a moderating variable. The independent variables used in this research are sales growth and capital intensity, while the dependent variable is tax aggressiveness, and inventory intensity serves as the moderating variable. The population of this research consists of Consumers Non-Cylicals sector companies listed on the Indonesia Stock Exchange from 2018 to 2022. The sample selection method is purposive sampling, yielding 12 companies or 60 observation samples. The data used are secondary data in the form of audited annual financial statements of each company. This research use Quantitative data analysis methods and associative problem formulation methods with causal relationships are used with the aid of E-views 12 software. The results indicate that sales growth and capital intensity simultaneously effect on tax aggressiveness. Partially, sales growth has a effect on tax aggressiveness, while capital intensity does not have a effect on tax aggressiviness. Additionally, the results indicate that inventory intensity does not moderate (weaken) the effect of sales growth on tax aggressiveness, nor does it moderate (weaken) the effect of capital intensity on tax aggressiveness.

Analysis of the influence of CAR, NPF, FDR AND BOPO on the financial performance (ROA) of banking in Indonesia

This article analyzes the influence of CAR, NPF, FDR and BOPO on banking financial performance (ROA) in Indonesia, which is the aim of this research. The sample selection method uses a purposive sampling technique at Sharia Commercial Banks registered with Bank Indonesia (BI) for the 2017-2022 period. The sample in this study consisted of 10 companies with a total sample data of 58. The data analysis technique used was multiple linear regression with the help of SPSS version 25. The results of the study showed that the NPF variable had an effect on financial performance (ROA), while CAR, FDR and BOPO did not. influence on financial performance (ROA). The selection of research objects at Sharia Commercial Banks resulted in limitations in the number of samples in this research. Apart from that, the independent variables in this study can only explain 19.8% of the independent variables.

Mask-Guided Vision Transformer for Few-Shot Learning.

Learning with little data is challenging but often inevitable in various application scenarios where the labeled data are limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of prior knowledge to new tasks that contain only a few samples. However, for data-intensive models such as vision transformer (ViT), current fine-tuning-based FSL approaches are inefficient in knowledge generalization and, thus, degenerate the downstream task performances. In this article, we propose a novel mask-guided ViT (MG-ViT) to achieve an effective and efficient FSL on the ViT model. The key idea is to apply a mask on image patches to screen out the task-irrelevant ones and to guide the ViT focusing on task-relevant and discriminative patches during FSL. Particularly, MG-ViT only introduces an additional mask operation and a residual connection, enabling the inheritance of parameters from pretrained ViT without any other cost. To optimally select representative few-shot samples, we also include an active learning-based sample selection method to further improve the generalizability of MG-ViT-based FSL. We evaluate the proposed MG-ViT on classification, object detection, and segmentation tasks using gradient-weighted class activation mapping (Grad-CAM) to generate masks. The experimental results show that the MG-ViT model significantly improves the performance and efficiency compared with general fine-tuning-based ViT and ResNet models, providing novel insights and a concrete approach toward generalizing data-intensive and large-scale deep learning models for FSL.

Analysis of Digital Bank Company Value on the Indonesian Stock Exchange

This study investigates how growth opportunity, investment opportunity set, and company size impact the valuation of digital banks that are publicly traded on the Indonesian Stock Exchange from 2018 to 2022. The sample selection method employed was full sampling, consisting of 13 companies as samples, and panel data regression analysis was utilized in this study with the assistance of E-views 12 software. According to the research findings, there are several discoveries. First, growth opportunities do not affect company value. Second, investment opportunity sets do affect company value. Third, the company size affects company value. Keywords: growth opportunity, IOS, ompany size, company value

Corporate Sustainability Performance: The Role of the Gender Diversity of the Board and Enterprise Risk Management

The research objective is to investigate the impact of board gender diversity on corporate sustainability performance, with enterprise risk management (ERM) as a moderating factor within health sector companies listed on the Indonesia Stock Exchange. The study adopts a secondary quantitative research approach and utilizes panel data linear regression analysis conducted through Econometric Views (E-Views). The study population consists of health sector firms listed on the Indonesia Stock Exchange from 2019 to 2022. The sample selection method used is purposive sampling, resulting in a sample size of 10 companies for the study. Secondary data is collected through the documentation method from the Indonesia Stock Exchange and the official websites of the selected companies. The findings reveal a negative relationship between board gender diversity and corporate sustainability performance, with a negative coefficient indicating that higher gender diversity among board members correlates with lower sustainability performance. Additionally, the study demonstrates that ERM strengthens the association between gender diversity and sustainability performance. Companies proficient in ERM implementation are better positioned to leverage the positive effects of gender diversity on sustainability performance. Understanding this interplay can assist organizations in making informed decisions regarding gender diversity policies and enterprise risk management strategies.

The Effect of ESG Risk Ratings, Board Size and Gender Diversity on Financial Performance: Econometric Case Study Indonesia 90 Companies 2020-2023

Aims: This study examines the influence of ESG Risk Ratings and the size of corporate boards on financial results. Furthermore, It investigates the impact of gender diversity on ESG Risk Ratings, Board Size, and the subsequent impact on Financial Performance. Study Design: In this case study, CFP is variable dependent, ESG and BS is variable independent, GD is the moderating variable, while Dar, LV, GR, and SZ are control variables. Place and Duration of Study: This study employs panel data from enterprises that meet the purposive sample requirements for the period of 2020-2023. Methodology: This study employs EViews 12 statistical software to conduct various tests, including the Descriptive Statistical Test, Model Selection Test, Multicollinearity and Heteroscedasticity Test, and Panel Data Regression Test. This study used purposive sampling method for sample selection. FP evaluated by the ratio of net income to total assets (ROA), ESG obtained from Morningstar Sustainalytics, BS determined by the total number of directors who serve on it, and GD is assessed by calculating the proportion of female board members. Result: The results of this inquiry indicate that ESG does not have an impact on FP, as demonstrated by the β = 0.0031 and Prob. = 0.3189 value. A different one independent variable, BS, also has no effect on FP, as evidenced by the value of β = 0.0096 and Prob. = 0.2130. As we transition to the moderation variable, it is evident that the GD variable does not moderate the relationship between ESG and FP (β = -0.011, Prob. = 0.3555). Meanwhile, the relationship between BS and FP is weakened by GD (β = -0.058, Prob. = 0.026). Conclusion: This study conclude that financial performance doesn’t influenced by ESG risk ratings and Board size. Beside, gender diversity weakens relationship between ESG and FP. The findings of this study have significant consequences for corporations, as they shed light on the elements that influence a company's financial performance, particularly with regard to sustainability standards. Further research can include variables such as comparison female directors and others.