Claim Missing Document
Check
Articles

Found 3 Documents
Search

Control Chart of T² Hotelling on Quality Control Activities of Crude Palm Oil (CPO) at PT Cipta Graha Garwita, Seluma Regency, Bengkulu Province Pangesti, Riwi Dyah; Alus Ahmad Suhaimi; Etis Sunandi; Istiqomah Rabithah Alam Islami
Journal of Statistics and Data Science Vol. 3 No. 1 (2024)
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/jsds.v3i1.36217

Abstract

PT Cipta Graha Garwita (CGG) is a palm oil producer focused on product quality, especially crude palm oil (CPO) for both food and non-food applications. Despite CGG's good reputation, variability in quality characteristics such as Free Fatty Acid (FFA) and moisture can affect the final quality of CPO. This study aims to apply a statistical quality control system to monitor and improve the consistency of CPO quality using T² Hotelling control charts. Statistical quality control methods ensure that products meet standards by reducing variability. One such tool is the T² Hotelling control chart, effective for monitoring multivariate variables using mean vectors and variance-covariance matrices. This study involves steps from data collection, testing multivariate normality assumptions, calculating T² Hotelling control charts, to determining control limits. Testing for multivariate normality assumptions showed the data met normal distribution criteria. The first and second stage T² Hotelling control charts identified several out-of-control observations. These out-of-control observations were excluded, and further analysis showed that after their removal, all data were within statistical control limits. This study recommends further analysis to determine the causes of out-of-control observations using Ishikawa diagrams and process capability evaluation to ensure consistent product quality.
Ordinal Logistic Regression Model for Human Development Index: A Case Study of Provinces in The southern part of Sumatra Suhaimi, Alus Ahmad; Novianti, Pepi; Pangesti, Riwi Dyah
JURNAL SINTAK Vol. 4 No. 1 (2025): SEPTEMBER 2025
Publisher : LPPM-ITEBA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62375/jsintak.v4i1.723

Abstract

Ordinal logistic regression is a statistical method used to analyze ordinal dependent variables with three or more categories. This study aims to model the Human Development Index (HDI) in the southern Sumatra region, which includes the provinces of Bengkulu, Bangka Belitung, Jambi, South Sumatra, and Lampung. HDI is categorized into three groups: low, medium, and high. The predictor variables used include Gross Regional Domestic Product (GRDP), poverty rate, access to safe drinking water, open unemployment rate (OUR), and labor force participation rate (LFPR). The analysis results indicate that three variables significantly influence HDI: the percentage of the poor population, the proportion of households with access to safe drinking water, and the open unemployment rate (OUR). This study did not conduct a spatial heterogeneity test; therefore, it is recommended that future research incorporate such a test
COMPARISON OF BINARY PROBIT REGRESSION AND FOURIER SERIES NONPARAMETRIC LOGISTIC REGRESSION IN MODELING DIABETES STATUS AT HAJJ GENERAL HOSPITAL SURABAYA Otok, Bambang Widjanarko; Zulfadhli, Muhammad; Pangesti, Riwi Dyah; Kurniawan, Muhammad Idham; Haryanto, Albertus Eka Putra; Darwis, Darwis; Kurniawan, Iwan
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 1 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss1pp0255-0270

Abstract

Diabetes mellitus is a chronic disease with a rising global prevalence, including in Indonesia. Early detection and accurate modeling are crucial for effective prevention and management. Binary Logistic Regression (BLR) is commonly used for binary outcome modeling; however, in practice, the relationship between binary outcomes and continuous predictors is often nonlinear, making BLR less suitable. To address these limitations, alternative methods such as Binary Probit Regression (BPR) and Flexible Semiparametric Nonlinear Binary Logistic Regression (FSNBLR) have been developed. This study aims to compare the performance of BLR, BPR, and FSNBLR models in classifying diabetes mellitus cases at Hajj General Hospital Surabaya. All three models were estimated using the Maximum Likelihood Estimation (MLE) method. Since the resulting estimators do not have closed-form solutions, numerical iteration using the Newton-Raphson method was applied. Model performance was assessed using Area Under the Curve (AUC), accuracy, sensitivity, and specificity. The FSNBLR model outperformed both the BLR and BPR models. It achieved the highest AUC value of 81.86%, while BLR (66.30%) and BPR (66.30%). That is indicated FSNBLR superior discriminative ability. In addition, the FSNBLR model recorded higher accuracy, sensitivity, and specificity compared to the other two models. The FSNBLR model demonstrated better predictive performance in identifying diabetes mellitus cases, especially in scenarios involving nonlinear relationships between predictors and the outcome variable. These findings suggest that flexible semiparametric approaches offer greater effectiveness in medical classification tasks, particularly for chronic conditions like diabetes mellitus.