Article Per Year (5 Year)
p-Index From 2020 - 2025
1.383
P-Index
This Author published in this journals
All Journal Jurnal Statistika Universitas Muhammadiyah Semarang Jurnal Matematika dan Statistika serta Aplikasinya (Jurnal MSA) Jurnal Informatika BAREKENG: Jurnal Ilmu Matematika dan Terapan Jurnal Statistika dan Aplikasinya Data Sciences Indonesia (DSI) Prosiding Seminar Nasional Official Statistics STATISTIKA
Istiana, Nofita
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Energy Engineering Environmental Science Mathematics Mechanical Engineering Medicine & Pharmacology Physics Social Sciences Transportation Other

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

 1 
Perbandingan Metode Klasifikasi pada Data dengan Imbalance Class dan Missing Value Istiana, Nofita; Mustafiril, Arief
Jurnal Informatika Vol 10, No 2 (2023): October 2023
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/inf.v10i2.15540

Abstract

Imbalance class dan missing value merupakan beberapa permasalahan dalam metode klasifikasi. Imbalance class berdampak pada hasil prediksi dimana kelas minoritas sering disalahklasifikasikan sebagai kelas mayoritas. Missing value menyebabkan beberapa algoritma dalam metode klasifikasi tidak dapat dijalankan. Pada penelitian ini, imbalance class ditangani dengan SMOTE, sedangkan missing value ditangani dengan imputasi rataan dan binning peubah. Metode klasifikasi yang dibandingkan dalam kasus ini adalah regresi logistik, bagging, boosting, random forest, dan support vector machine yang diaplikasikan pada data dummy status kolektibilitas debitur. Metode klasifikasi tersebut akan cenderung memprediksi data kelas mayor (debitur berstatus kolektibilitas baik), sehingga prediksi kelas minor (debitur berstatus kolektibilitas buruk) cenderung sedikit. Metode yang memberikan akurasi tertinggi yaitu random forest (missing value diimputasi dengan nilai rataan), yang menghasilkan akurasi sebesar 0.801, sensitivitas sebesar 0.593, dan spesivitas sebesar 0.807. Imbalance class and missing value are some of the problems in classification method. Imbalance class causes the prediction of the minority class to be misclassified as the majority class. Missing value causes several algorithms in classification method cannot be run. In this study, imbalance class is handled by SMOTE, while missing value is handled by mean imputation and binning variable. The classification methods being compared in this study are logistic regression, bagging, boosting, random forest, and support vector machines which are applied to dummy data on debtors' collectibility status with total data 12459. The data contains 97.48 debtors with good collectibility status and 2.52 percent of debtors with bad collectibility status. The method that provides the highest accuracy is random forest (missing value imputed by mean value), which results in accuracy of 80.1 percent, sensitivity of 59.3 percent, and specificity of 80.7 percent. 
Pendugaan Indikator Rasio Angka Partisipasi Sekolah Anak Disabilitas terhadap Nondisabilitas di Pulau Nusa Tenggara Tahun 2023 Kholiq, Adit; Putri, Afriani Kartika; Simangunsong, Sri Rohmanisa; Dewi, Isnaini Rahma; Nuraini, Fayza Zaki Asmi; Istiana, Nofita
Statistika Vol. 24 No. 2 (2024): Statistika
Publisher : Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Islam Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/statistika.v24i2.4536

Abstract

ABSTRAK Salah satu target dalam tujuan pembangunan berkelanjutan (SDGs) adalah menghapuskan diskriminasi di bidang pendidikan, termasuk bagi penyandang disabilitas. Ukuran yang digunakan pemerintah untuk menilai pencapaian target ini adalah rasio angka partisipasi sekolah (APS) anak penyandang disabilitas terhadap nondisabilitas usia 7 – 17 tahun. Namun, pendugaan langsung menghasilkan standard error yang besar. Tujuan penelitian ini adalah melakukan pendugaan rasio angka partisipasi sekolah anak disabilitas terhadap nondisabilitas berusia 7 – 17 tahun pada tingkat kabupaten/kota di Pulau Nusa Tenggara tahun 2023. Penelitian ini menerapkan metode Small Area Estimation (SAE) dengan pendekatan Hierarchical Bayes (HB). Data penelitian bersumber dari Badan Pusat Statistik. Hasil penelitian ini menunjukkan model SAE-HB menghasilkan pendugaan yang lebih presisi daripada pendugaan langsung pada anak disabilitas. Diketahui pula, rasio angka partisipasi sekolah anak disabilitas terhadap nondisabilitas berusia 7 – 17 tahun di Pulau Nusa Tenggara berada pada rentang 40,47 sampai 78,15 dengan Kabupaten Sumba Barat dan Kabupaten Rote Ndao berstatus perlu perhatian. ABSTRACT One of the targets set out in the Sustainable Development Goals (SDGs) is to eliminate discrimination in education, including for people with disabilities. The measure used to assess the achievement of this target is the ratio of school enrollment rates (APS) of children with disabilities to those without disabilities aged 7-17 years. However, direct estimation results in a large standard error. The objective of this study is to predict the school enrollment ratio of children with disabilities to non-disabled children aged 7-17 years at the district/city level in Nusa Tenggara Island in 2023. This research employs the Small Area Estimation (SAE) method with the Hierarchical Bayes (HB) approach. The research data is sourced from the Badan Pusat Statistik. The findings of this study indicate that the SAE-HB model yields more precise predictions than direct estimation of children with disabilities. Additionally, the school enrollment ratio of children with disabilities to those without disabilitie aged 7-17 years on Nusa Tenggara Island is estimated to be within the range of 40.47 to 78.15, with West Sumba Regency and Rote Ndao Regency identified as requiring attention.
Pendugaan Area Kecil Persentase Anak Usia 0-17 Tahun yang Hidup di Bawah Garis Kemiskinan Tingkat Kabupaten/Kota di Pulau Jawa Tahun 2023 Puspitasari, Dwi Ajeng; Herlan, Mumtahanah Ceisa; Fatah, Saifullah; Sedana Nugraha, I Gusti Ngurah Yogi; Manik, Rizky Wahyuda; Istiana, Nofita; Yuniasih, Aisyah Fitri
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.1967

Abstract

Poverty is a problem that continues to confront various countries in the world, with no exception in Indonesia. Poverty reduction is the main focus of the Sustainable Development Goals (SDGs) and the 2020-2024 National Medium-Term Development Plan (RPJMN), with the main focus not only on the poverty of the national population but also the children who live in it. It is known that 47.39 percent, or almost half, of poor children in Indonesia are dominated by Java Island. Therefore, to be able to realize this target, it is necessary to have data availability in small areas, especially areas with a high percentage of poor children on Java Island. This study aims to estimate the percentage of children aged 0-17 years living below the poverty line at the city district level using the Small Area Estimation Hierarchical Bayes (SAE HB) method. Based on the results, estimation using the SAE HB method is able to produce a better Relative Standard Error (RSE) than direct estimation results.
Perbandingan Metode Klasifikasi dengan Teknik Resampling pada Kejadian Gagal Ginjal Kronis di Kalimantan Utara Putri Ramatillah Ramadhana; Istiana, Nofita
Data Sciences Indonesia (DSI) Vol. 5 No. 1 (2025): Article Research Volume 5 Issue 1, June 2025
Publisher : Yayasan Cita Cendikiawan Al Kharizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/dsi.v5i1.6002

Abstract

Gagal ginjal kronis adalah penyakit tidak menular yang menjadi permasalahan global. Di Indonesia, Kalimantan Utara memiliki prevalensi kejadian gagal ginjal kronis tertinggi yaitu sebesar 0,64%. Penduduk usia produktif di provinsi tersebut merupakan salah satu kelompok penduduk yang rentan terhadap penyakit ini. Gagal ginjal kronis lebih banyak terjadi pada perempuan, namun perkembangan keparahannya lebih cepat pada laki-laki dimana prevalensi penduduk laki-laki yang melakukan hemodialisis adalah sebesar 18,41% sementara perempuan 0%. Fakta ini disayangkan karena penduduk laki-laki lebih banyak yang bekerja dibanding perempuan dan memiliki produktivitas lebih tinggi. Oleh karena itu, penelitian ini bertujuan mengetahui variabel penting yang berperan pada kejadian gagal ginjal kronis penduduk laki-laki usia produktif melalui pemodelan klasifikasi dan penerapan teknik resampling terbaik. Penerapan teknik resampling perlu dilakukan karena data yang digunakan memiliki kasus ketidakseimbangan kelas. Teknik resampling yang dibandingkan adalah SMOTE dan SMOTE + Tomek Links dengan metode klasifikasi Random Forest, Naïve Bayes, regresi logistik, dan regresi logistik Firth. Hasil penelitian ini, metode klasifikasi terbaik adalah Naïve Bayes dan teknik resampling terbaiknya adalah SMOTE. Variabel penting yang berperan pada kejadian gagal ginjal kronis laki-laki usia produktif ini adalah usia, konsumsi minuman energi, klasifikasi wilayah, konsumsi makanan instan, dan konsumsi minuman manis.
MULTIDIMENSIONAL POVERTY OF OLDER ADULTS IN JAVA ISLAND: A MULTILEVEL BINARY LOGISTIC REGRESSION ANALYSIS Putra, Dwima Agus Nurcahya; Istiana, Nofita
Jurnal Statistika dan Aplikasinya Vol. 9 No. 1 (2025): Jurnal Statistika dan Aplikasinya
Publisher : LPPM Universitas Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/JSA.09105

Abstract

Population aging is a global phenomenon, including in Indonesia, which poses socio-economic challenges. Many older adults still belong to the lowest 40% of household expenditure groups, indicating poor quality of life. Previous studies have generally used monetary measurements, while poverty in older adults is multidimensional, involving health, education, and living standards. This study addresses this gap by analyzing multidimensional poverty among older adults in Java in 2022 using multilevel binary logistic regression with a hierarchical data structure (individuals at level 1 and districts at level 2). The data sources include SUSENAS March 2022 and Province in Figures 2023. The results show that individual factors such as gender, marital status, type of occupation, functional impairment, savings ownership, and residential area, as well as regional factors like GRDP per capita and healthcare facilities ratio, significantly affect multidimensional poverty status among adults. The Intraclass Correlation Coefficient (ICC) is 0.383, confirming substantial variation at the district level, highlighting the importance of multilevel analysis. Furthermore, the model’s goodness-of-fit test concluded that the model is appropriate for explaining the multidimensional poverty status among older adults in Java in 2022. The findings provide comprehensive insights into targeted policy interventions to improve older adults' welfare.
ECONOMIC GLOBALIZATION, ECONOMIC GROWTH, AND HUMAN CAPITAL : EMPIRICAL EVIDENCE USING THREE STAGE LEAST SQUARE IN INDONESIA Huda, Qorinul; Istiana, Nofita
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 3 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss3pp1483-1496

Abstract

The pace of globalization is increasing rapidly and dynamically as time goes by. Indonesia, located takes advantage of globalization to encourage economic growth. However, over the last decade, from 2000 to 2019, Indonesia's economic globalization index has tended to decline along with the increase in the global economic globalization index. Indonesia's economic growth has been relatively stagnant. Human capital, as the primary input in Indonesia's economic system, is suspected to be suboptimal. In the National Medium-Term Development Plan (RPJMN) for 2020-2024, economic growth and human capital are the main focus in achieving national prosperity. Human capital in this study uses health indicators as a proxy for assessing productivity and educational investment approaches. Data is transformed to meet the stationarity requirements of time series data. The study employs the Three Stage Least Square (3SLS) simultaneous equation method to examine total and direct effects. The estimation results show that changes in globalization growth are directly influenced by changes in economic growth, exchange rate growth, and inflation. Changes in economic growth are directly influenced by changes in exchange rate growth, globalization index growth, and inflation. Human capital is directly influenced by changes in globalization index growth, changes in economic growth, inflation, previous-year inflation, and changes in unemployment rates
DETERMINANTS OF OUTPATIENT CARE BEHAVIOR OF THE ELDERLY POPULATION IN WEST SULAWESI IN 2022: BACKWARD ELIMINATION LOGISTIC REGRESSION Natasya Auzea Fahyumi, Tengku; Istiana, Nofita
Jurnal Statistika Universitas Muhammadiyah Semarang Vol 13, No 1 (2025): Jurnal Statistika Universitas Muhammadiyah Semarang
Publisher : Department Statistics, Faculty Mathematics and Natural Science, UNIMUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsunimus.13.1.2025.61-73

Abstract

Ageing population is a result of the successful development. It is characterized by an increase in the number and proportion of the elderly population. The elderly population is described as a vulnerable group. As a result of degenerative process in physical, psychological, and social activity aspects, the elderly population has a high risk of experiencing health problems. West Sulawesi is the province with the eighth highest morbidity rate for the elderly. However, this province has the lowest percentage of outpatient care, at 36,39%. Therefore, it is necessary to conduct research on the outpatient care behavior of the elderly in West Sulawesi in 2022. This research uses a binary logistic regression method. The results show that the variables marital status, education level, disability status, and activity impairment have a significant effect on outpatient care behavior in West Sulawesi in 2022. Efforts from the government and the society are needed to increase the awareness about the importance of health checks among the elderly.
Aplikasi Regresi Logistik Biner Pada Kejadian Putus Sekolah Pekerja Anak Di Pulau Sulawesi Rosmini, Nazlia; Istiana, Nofita
Jurnal MSA (Matematika dan Statistika serta Aplikasinya) Vol 13 No 2 (2025): VOLUME 13 NO 2, 2025
Publisher : Universitas Islam Negeri Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/msa.v13i2.57776

Abstract

Children are the future generation of the nation and play a vital role in national development. However, those from low-income families are often forced into child labor, which can hinder their educational attainment. Balancing work and school responsibilities frequently leads to school dropouts among child laborers. Sulawesi Island is one of the regions in Indonesia with a notably high prevalence of child labor. This study found that 16.39% of child laborers on Sulawesi Island dropped out of school. Using logistic regression analysis on data from the March 2022 National Socio-Economic Survey (Susenas), the study identified that a child's gender, age, poverty status, and the education level of the head of the household significantly influence the incidence of school dropout among child laborers.
Co-Authors Aisyah Fitri Yuniasih Dewi, Isnaini Rahma Fatah, Saifullah Herlan, Mumtahanah Ceisa Huda, Qorinul Kholiq, Adit Manik, Rizky Wahyuda Mustafiril, Arief Natasya Auzea Fahyumi, Tengku Nuraini, Fayza Zaki Asmi Puspitasari, Dwi Ajeng Putra, Dwima Agus Nurcahya Putri Ramatillah Ramadhana Putri, Afriani Kartika Rosmini, Nazlia Sedana Nugraha, I Gusti Ngurah Yogi Simangunsong, Sri Rohmanisa