Claim Missing Document
Check
Articles

PENGGUNAAN PROPENSITY SCORE STRATIFICATION-SUPPORT VECTOR MACHINE UNTUK MENGESTIMASI EFEK PERLAKUKAN AKTIVITAS OLAHRAGA PADA PENDERITA DIABETES MELITUS Ernawati Ernawati; Bambang Widjanarko Otok; Sutikno Sutikno
Indonesian Journal of Statistics and Applications Vol 4 No 3 (2020)
Publisher : Departemen Statistika, IPB University dengan Forum Perguruan Tinggi Statistika (FORSTAT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/ijsa.v4i3.653

Abstract

Randomized Controlled Trial (RCT) is not possible to do in observational studies, mainly in health cases, because it is directly related to human life. Actually, good randomization is needed to make the treatment and control groups have no large differences in the observed variables, so it results from unbiased treatment One alternative method that is increasingly used in statistical analysis in the field of health is the Propensity Score (PS). If the propensity score had estimated using the SVM method and divided into groups of strata that have a similar propensity score, it is known as the Propensity Score Stratification (PSS-SVM). The purpose of the PSS-SVM is to balance the observed variables between the treatment group and the control group by dividing them into several strata groups so that a balanced trend is obtained or the propensity score is called balance. This eliminates the influence of the confounding variables and unbalance of the treatment and control groups and obtain an unbiased estimation of the treatment effect. In this Research, the PSS-Method applied in case of disease complication in patients with Diabetes Mellitus Type 2 at the Regional Public Hospital of Pasuruan with respondents who counted 96 patients. The purpose of using PSS-SVM, in this case, is to reduce the confounding effects (sports activity) that influence disease complications. In strata of 4 reduce the largest bias with the percent bias reduction (PBR) is 86.39% with the smallest standard error is 0.103.
Determination of Home Purchase Decisions with Technology Adoption as a Moderating Variable Wati, Nurul Linda; Otok, Bambang Widjanarko
Research Horizon Vol. 5 No. 3 (2025): Research Horizon - June 2025
Publisher : LifeSciFi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54518/rh.5.3.2025.505-520

Abstract

The residential property market in Indonesia has experienced significant growth, with a 1.89% increase in the Residential Property Price Index and a 31.16% rise in sales in the first quarter of 2024, though Surabaya recorded the lowest price growth in Java at 0.34%. This study aims to examine the determinants of home purchase decisions, including purchasing power, price, location, marketing advertisements, and developer brand image, with technology adoption as a moderating variable. Using a quantitative approach, data were collected from 225 respondents across four housing projects in Gresik, East Java, through questionnaires analyzed with Moderated Structural Equation Modeling. The findings reveal that all determinants significantly influence home purchase decisions, with developer brand image having the strongest effect. Technology adoption enhances these relationships by improving information access and consumer trust through digital platforms. The study concludes that developers should prioritize digital marketing strategies, such as virtual tours and social media campaigns, to boost consumer engagement and address declining sales trends. These insights offer strategic guidance for enhancing marketing effectiveness in the evolving digital landscape of the housing sector.
Effectiveness of Esports Sponsorship in Mobile Legends Professional League on Brand Association and Purchase Intention Nathanel, Jeshen Oktavian; Otok, Bambang Widjanarko
Jurnal Impresi Indonesia Vol. 4 No. 8 (2025): Indonesian Impression Journal (JII)
Publisher : Riviera Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58344/jii.v4i8.6918

Abstract

The esports industry has experienced significant growth in recent years, attracting the attention of various sponsors to utilize these platforms in achieving their business goals. This study aims to analyze the effectiveness of esports sponsorship in the Mobile Legends Professional League (MPL) on brand associations and consumer purchase intentions. Using a quantitative approach and Structural Equation Modeling (SEM) techniques through SmartPLS, data was collected from 160 respondents who are active in the esports community in Indonesia. The results showed that positive attitudes towards sponsors (?=0.461, p<0.001) and sincerity of sponsorship motives (?=0.177, p=0.039) had a significant effect on brand association. Sponsor-event suitability (?=0.241, p=0.030) and activity engagement (?=0.240, p=0.004) were also shown to strengthen brand associations. For purchase intent, attitudes towards sponsors (?=0.391, p<0.001), sincerity of motives (?=0.223, p=0.013), and activity involvement (?=0.197, p=0.037) showed significant influences. This research model was able to explain 88.3% of brand association variance and 85% of purchase intention variance. These findings provide strategic insights for esports sponsors to optimize their investments through an authentic and relevant approach to the target audience.
SIMILARITY CHECKING OF CCTV IMAGES USING PEARSON CORRELATION: IMPLEMENTATION WITH PYTHON Mulyanto, Angga Dwi; Otok, Bambang Widjanarko; Aqsari, Hasri Wiji; Harini, Sri; Astuti, Cindy Cahyaning
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 4 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss4pp2703-2712

Abstract

Video surveillance technology, such as CCTV, is increasingly common in various applications, including public safety and business surveillance. Analyzing and comparing images from CCTV systems is essential for ensuring safety and security. This research implements the Pearson Correlation method in Python to measure the similarity of CCTV images. Pearson Correlation, which assesses the linear relationship between two variables, is employed to compare the pixel values of two images, resulting in a coefficient that indicates the degree of similarity. We used a quantitative approach with experiments on two scenarios to test the program's effectiveness in measuring image similarity. The results demonstrate that Pearson Correlation is highly effective in distinguishing between identical and other images, providing a more accurate and comprehensive assessment of image similarity compared to histogram analysis. However, the findings are constrained by the specific scenarios and dataset utilized. Further research with more diverse empirical data is required to generalize these results across a broader range of CCTV conditions.
SEM-PLS Training at Universitas Islam Negeri Maulana Malik Ibrahim Otok, Bambang Widjanarko; Astuti, Cindy Cahyaning; Mulyanto, Angga Dwi; Purhadi, Purhadi; Andari, Shofi; Choiruddin, Achmad; Purnami, Santi Wulan
JRCE (Journal of Research on Community Engagement) Vol 7, No 1 (2025): Journal of Research on Community Engagement
Publisher : Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrce.v7i1.32959

Abstract

At Universitas Islam Negeri Maulana Malik Ibrahim Malang in 2024 SEM-PLS training will develop data analysis capabilities for lecturers and students to enhance their work on quality scientific publications. The Department of Mathematics at Faculty of Science and Technology conducted the session on May 21, 2024, where 40 people participated. Training and mentoring stands as the service method which features instruction about SEM-PLS theory alongside practical utilization of SmartPLS software for implementation. Observation activities together with documentation assessment and satisfaction questionnaire responses determine the program's outcome. Participant satisfaction reached an exceptional level because they showed positive feedback about the material presented. Time constraints together with a constrained space area negatively affected  this event. This training achieved success in providing extensive SEM-PLS understanding to students and lecturers. The activity builds campus research capacity. The organization of similar consecutive training courses is highly suggested because it will boost academic knowledge in data analysis fields.
Model Regresi Gamma untuk Menganalisis Indeks Pengeluaran Kabupaten/Kota di Pulau Sumatra Otok, Bambang Widjanarko; Rini, Dyah Setyo; Fadhilah, Rahmi
Limits: Journal of Mathematics and Its Applications Vol. 22 No. 1 (2025): Limits: Journal of Mathematics and Its Applications Volume 22 Nomor 1 Edisi Ma
Publisher : Pusat Publikasi Ilmiah LPPM Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/limits.v22i1.3375

Abstract

Gamma regression is part of Generalised Linear Models (GLMs) that can model data that is positive and asymmetric. The occurrence of data asymmetry is common in everyday life, for example in Human Development Index (HDI) data. The HDI has indicators called the Human Development Dimension Index, including the expenditure index, the education index and the life expectancy index. This study aims to model the expenditure index of districts/cities in Sumatra using Gamma regression because the expenditure index data is positive and non-symmetric. In modelling the Expenditure Index, the predictor variables used are the percentage of poor population, population density, percentage of population using their own toilet, and open unemployment rate in each district/city in Sumatra in 2023. The data used were obtained from the BPS website of the province corresponding to the regency/city in Sumatra. Based on the results of the analysis, all the predictor variables used had a significant effect on the expenditure index at the 1% and 5% significance levels, and the standard error value of each parameter estimate was small. In addition, the MSE of the model is also classified as small, which is 0.00163. This can prove that the model is supported by the data, although the coefficient of determination of the model ( ) in this study is only 47.59%.
RANDOM EFFECTS META-REGRESSION USING WEIGHTED LEAST SQUARES (CASE STUDY: EFFECTIVENESS OF ACCEPTANCE AND COMMITMENT THERAPY IN REDUCING DEPRESSION) Arumningtyas, Felinda; Otok, Bambang Widjanarko; Purnami, Santi Wulan
MEDIA STATISTIKA Vol 18, No 1 (2025): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/medstat.18.1.49-60

Abstract

Meta-analysis is a statistical method for synthesizing quantitative data from multiple related studies, yet heterogeneity among studies often complicates interpretation. Meta-regression extends this approach by incorporating study-level covariates to explain variations in outcomes. With the global increase in depression, Acceptance and Commitment Therapy(ACT) has attracted attention as an effective psychological intervention. Therefore, a deeper understanding of the factors that influence its effectiveness across studies is needed. However, to date, only a few meta-analyses have quantitatively examined moderator variables that influence ACT outcomes using a random effects meta-regression approach. This study aims to fill this gap. This study estimated the model parameters using the Weighted Least Squares (WLS) method. Thirty-three published studies testing the effectiveness of ACT in reducing depression were collected from PubMed, Google Scholar, and Science Direct. The homogeneity test results showed significant heterogeneity, supporting the use of a random effects model. The combined effect size of -0.321 indicates that ACT significantly reduces depression levels compared to the control group. Meta-regression analysis revealed that variation in effect size was significantly influenced by differences in the average age of patients and duration of therapy. These findings provide new insights into the conditions and characteristics that make ACT therapy more effective.