Claim Missing Document
Check
Articles

Found 23 Documents
Search

Pemodelan Regresi Binomial Negatif menggunakan Estimator Jackknife Negative Binomial Ridge Regression pada Data Angka Kematian Bayi Provinsi Sulawesi Selatan Palinoan, Kezia Agra; Jaya, Andi Kresna; Islamiyati, Anna
Basis : Jurnal Ilmiah Matematika Vol. 3 No. 2 (2024): BASIS: Jurnal Ilmiah Matematika
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/basis.v3i2.1140

Abstract

Analisis regresi Binomial Negatif adalah metode yang digunakan untuk menganalisis hubungan antara variabel prediktor terhadap variabel respon yang berdistribusi Poisson. Namun, regresi Poisson tidak dapat digunakan untuk memodelkan data dengan overdispersi maupun terdapat multikolinearitas. Untuk menyelesaikan masalah tersebut digunakan regresi Binomial Negatif dengan estimator Jackknife Negative Binomial Ridge Regression. Dalam penelitian ini, estimasi parameter regresi Binomial Negatif dengan estimator Jackknife Negative Binomial Ridge Regression diterapkan pada data tingkat kematian bayi di Sulawesi Selatan tahun 2017. Metode Jackknife berperan untuk mereduksi bias sehingga dapat diperoleh penaksiran parameter dengan bias yang kecil sedangkan metode ridge untuk menangani multikolinearitas. Metode pemilihan parameter ridge menggunakan nilai MSE terkecil. Model terbaik terbentuk pada model dengan parameter ridge k = 0.0081. Berdasarkan estimasi parameter yang terbentuk menunjukkan bahwa variabel jumlah bayi dengan berat badan lahir rendah (X1), jumah bayi yang diberi ASI eksklusif (X2), jumlah bayi yang mendapatkan vitamin A (X3), jumlah cakupan pelayanan K4 pada ibu hamil (X4), jumlah ibu hamil yang menerima imunisasi TT2+ (X5), dan jumlah kelahiran (X6) signifikan mempengaruhi jumlah kematian bayi.
Comparison of Naive Bayes Classification Methods Without and With Kernel Density Estimation Hermawan, Agus; Siswanto, Siswanto; Jaya, Andi Kresna
Jurnal Varian Vol. 7 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/varian.v7i2.3199

Abstract

Halal certification is important to give confidence to Muslim consumers around the world regarding the halalness of products. The Halal Product Assurance Organizing Body (BPJPH) is the official auditor in Indonesia that is responsible for the halal certification process. This study aims to address the need for verification and validation of data for halal certification applications in Indonesia by using the data science approach and machine learning technology. In this study, the Naïve Bayes classification method was used to optimize the data verification and validation process. However, this method needs to be improved by applying optimization methods such as Kernel Density Estimation (KDE) to improve classification results. The results showed that the Naïve Bayes classification method with KDE optimization produced better performance than the Naïve Bayes method without optimization. The performance of the Naïve Bayes classification model without optimization achieves 87.6% Accuracy, 85.4% Recall, 88.8% Precision, and 87.1% Fmeasure. Meanwhile, the Naïve Bayes classification model with KDE optimization achieves 97.5% Accuracy, 95.9% Recall, 98.9% Precision, and 97.8% Fmeasure. Thus, it can be concluded that the Naïve Bayes classification algorithm with KDE optimization results in a performance increase of 9.9% compared to the Naïve Bayes method without optimization. This research has important implications in handling complex and non-normally distributed data and providing solutions for BPJPH in the process of verifying halal certification.
Pemodelan Kasus Kematian Demam Berdarah Dengue di Provinsi Sulawesi Selatan dengan Menggunakan Model GWZIPR Aicha, Andi Ummi Melin Aicha; Islamiyati, Anna; Jaya, Andi Kresna
ESTIMASI: Journal of Statistics and Its Application Vol. 7, No. 1, Januari, 2026 : Estimasi
Publisher : Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/ejsa.v7i1.25215

Abstract

Dengue Hemorrhagic Fever (DHF) has spread widely throughout the region with the number of districts/cities being infected increasing to remote areas. Data on the spread or death rate from DHF in certain locations includes spatial data. The number of deaths due to DHF cases in South Sulawesi in 2019 contained 66.67% zero value, so the Geographically Weighted Zero Inflated Poisson Regression (GWZIPR) model was used to deal with spatial data that contains many zero-value observations. Based on the simultaneous test, it was found that the GWZIPR model was feasible to use with a deviation value of 100.1557. Districts/cities in South Sulawesi have various significant variables due to spatial variations between observations and areas that are closer give greater weight so that several districts/cities have the same significant variables. In the GWZIPR model with adaptive bisquare kernel weights, the variables that affect DHF mortality in all districts/cities are the percentage of drinking water facilities that meet health requirements and population density.