Claim Missing Document
Check
Articles

Found 5 Documents
Search

Estimasi Kematian Bayi dan Sebelum Berusia Lima Tahun dengan Metode Brass dan Sullivan di Banten Murti, Fadhaa Aditya Kautsar
Jurnal Kependudukan dan Pembangunan Lingkungan Vol 4 No 1 (2023): Jurnal Kependudukan dan Pembangunan Lingkungan (JKPL)
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jkpl.v4i1.175

Abstract

Ada beberapa metode tidak langsung dalam mengestimasikan kematian bayi dan anak di bawah lima tahun, dua diantaranya adalah metode Brass dan Sullivan. Estimasi tersebut penting dilakukan mengingat keduanya adalah salah satu indikator kemajuan suatu negara. Penelitian ini akan membandingkan kedua metode tersebut dengan menggunakan data 1) Wanita Pernah Kawin (Wi); 2) Anak Lahir Hidup (ALH); dan 3) Anak Masih Hidup (AMH) di Provinsi Banten bersumber dari data Sensus Penduduk 2010. Dengan menggunakan uji t-test berpasangan, ditemukan tidak adanya perbedaan yang signifikan antara kedua metode dengan nilai p-value sebesar 0.069 antara metode Brass P1/P2 dengan Sullivan maupun dengan metode Brass P2/P3 dengan Sullivan dengan p-value 0.063.
Predictive Model Comparison for Predicting Condom Use: Comparison of Conventional Logistic Regression and Other Machine Learning Murti, Fadhaa Aditya Kautsar
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 4 No. 4 (2024): MALCOM October 2024
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v4i4.1489

Abstract

Condom use at first sex remains an important issue as it shapes future sexual behavior. This study aimed to deploy and predict condom use using five different machine learning classification models. Dataset used for this study was from Indonesian Demographic and Health Survey (IDHS) 2017 with a population of interest was male adolescents. We evaluated five different models, namely logistic regression, naïve bayes, K-Nearest Neighbors, support vector machines, and decision tree. Performances of each model were assessed using metrics such as accuracy, specificity, sensitivity, ROC Curve, and AUC Score. Study found that different models exhibit different accuracy, specificity, sensitivity, ROC Curve, and AUC Score. The decision tree and naïve bayes models remained the models with the highest specificity and sensitivity, however the KNN model expressed the highest AUC score. Result from the conventional logistic regression also explained that condom use was associated with education level, age at first sex, and attitude towards condom use. The government is advised to create equal education opportunities for every adolescent and shape better knowledge and condom attitudes. Future studies are advised to enhance the performance of machine learning models using hyperparameter tuning and other methods.
Decomposition of HIV Knowledge In Urban-Rural Areas In Indonesia Murti, Fadhaa Aditya Kautsar; Utami, Asti Annisa; Jangkang, Gastin Gabriel
Jurnal Ilmu Kesehatan Masyarakat Vol. 15 No. 2 (2024): Jurnal Ilmu Kesehatan Masyarakat (JIKM)
Publisher : Association of Public Health Scholars based in Faculty of Public Health, Sriwijaya University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26553/jikm.2024.15.2.234-245

Abstract

HIV/AIDS remains a public health crisis, HIV/AIDS remains a public health crisis, especially among male adolescents in Indonesia. This urgency stems from the rapid increase in cases among adolescents, who often lack adequate access to education and prevention resources. If left unaddressed, the epidemic could continue to spread among younger populations, leading to long-term social and economic consequences. Despite the crucial role of HIV knowledge in prevention, disparities exist between rural and urban areas. This study examines these disparities, identifying factors influencing HIV knowledge. This cross-sectional study employed a total of 10,943 male adolescents enrolled in a survey called Indonesia Demographic Health Survey (IDHS) 2017. To address those disparities, a stratification chi-square based on place of residence was employed. We also employed a multivariate decomposition analysis to examine which variables account for most gaps. Results found that only 15% of adolescents were knowledgeable (9.5% in urban and 5.5% in rural areas). Bivariate Analysis showed that education level and HIV test awareness were associated in both areas ( p-value < 0.05), while wealth quintile and internet use were associated in urban areas only ( p-values < 0.05). The HIV knowledge gap would decrease by 8% if internet use was equalized, by 11% if HIV testing awareness was equalized, by 17% if educational attainment was equalized, and by 24% if wealth quintiles were equalized. This calls for a multi-sectoral intervention targeting such factors for better HIV outcomes in Indonesia.
GENERALIZED GAMMA REGRESSION FOR ANALYZING ALCOHOL CONSUMPTION SURVIVABILITY Murti, Fadhaa Aditya Kautsar
Jurnal Biometrika dan Kependudukan Vol. 13 No. 2 (2024): JURNAL BIOMETRIKA DAN KEPENDUDUKAN
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jbk.v13i2.2024.219-229

Abstract

Alcohol consumption remains a public health problem, affecting various organ systems. Its impact can be detrimental to adolescents, leading to disturbed social and economic development. Gender differences exist, with male adolescents being more affected. This research aims to understand alcohol consumption among male adolescents in Indonesia. This study used pseudo longitudinal data from the 2017 Indonesian Demographic Health Survey (IDHS) and employed a survival analysis method using the generalized gamma approach. A total of 12,373 (weighted) adolescents were analyzed, with 4,573 of them classified as events. A time ratio (TR) was reported. Smoking was identified as the most substantial variable, shortening the survivability of alcohol consumption by 19%. Additionally, living in rural areas, having tried drugs, and having had sex were identified as risk factors, while education level and mobile phone ownership were protective factors. Risk behaviors shorten alcohol consumption survival among adolescents. Cross-sectoral interventions and comprehensive counseling are essential for effective prevention.
Analyzing High-Risk Fertility Behavior for Sustainable Maternal-Child Health: A 2017 Sociodemographic Study in Urban and Rural Indonesia Utami, Asti Annisa; Murti, Fadhaa Aditya Kautsar; Yuniar, Popy; Herdayati, Milla
Kesmas Vol. 20, No. 5
Publisher : UI Scholars Hub

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Indonesia's goal of achieving Indonesia Emas 2045 hinges on improving Maternal-Child Health (MCH), essential for building a healthy and competitive population. Despite some advancements, the Maternal Mortality Rate (MMR) and Under-five Mortality Rate (U5MR) remain high, particularly because of High-Risk Fertility Behavior (HRFB). The HRFB poses significant risks to MCH, affecting both urban and rural women. This study aimed to identify the factors associated with HRFB in these areas to enhance MCH outcomes and support Indonesia's sustainable health goals. This cross-sectional study used a secondary dataset from the 2017 Indonesian Demographic Health Survey. A total of 20,530 women of reproductive age were included in this analysis. The main dependent variable was the HRFB, and the independent variables were split into three factors: individuals, households, and community factors. The overall prevalence of HRFB was 37.0%, with a slightly higher prevalence in urban areas (37.6%) than in rural areas (36.1%). In rural areas, HRFB was significantly associated with the wealth quintile, while in urban areas, it was linked to women's autonomy and education level. Addressing these factors is critical for improving MCH outcomes and reducing HRFB use.