| dc.contributor |
Fakultas Matematika dan Ilmu Pengetahuan Alam |
|
| dc.creator |
Apriliyanti, Fitri |
|
| dc.creator |
Yanti, Teti Sofia |
|
| dc.date |
2021-01-21 |
|
| dc.date.accessioned |
2021-03-15T03:45:21Z |
|
| dc.date.available |
2021-03-15T03:45:21Z |
|
| dc.identifier |
http://karyailmiah.unisba.ac.id/index.php/statistika/article/view/25633 |
|
| dc.identifier |
10.29313/.v7i1.25633 |
|
| dc.identifier.uri |
http://hdl.handle.net/123456789/28856 |
|
| dc.description |
Abstract. The method to determine the relationship between the response variable and several predictor variables is linear regression. When the response variable is binary, the method used is binary logistic regression. Several approaches to developing models for explaining binary regression models are logit models and probit models. Logit models and probit models are commonly used to analyze the relationship between one response variable which is categorical data and several predictor variables. In this study, we want to know the best model between the binary logit model and the binary probit model using coronary heart disease risk data in the City of Framingham, America. From the results of the analysis that has been done, it can be concluded that the factors that influence the risk of coronary heart disease are gender, age, active smokers, cholesterol levels, BMI and glucose. The classification accuracy value of the binary logit regression method is 84.95% and the classification accuracy value of the binary probit method is 84.92%. From the comparison of the classification accuracy between the binary logit regression method and the binary probit method are relatively the same.Keywords: Binary Logit Model Regression, Binary Probit Model Regression, Coronary Heart Disease.Abstrak. Metode untuk mengetahui hubungan variabel respon dan beberapa variabel prediktor adalah regresi linier. Ketika variabel respon adalah biner, metode yang digunakan adalah regresi logistik biner. Beberapa pendekatan untuk mengembangkan model untuk menjelaskan model regresi biner adalah model logit dan model probit. Model logit dan model probit biasa digunakan untuk menganalisis hubungan antara satu variabel respon yang merupakan data kategorik dan beberapa variabel prediktor. Penyakit jantung kronis merupakan salah satu penyebab kematian nomor satu di dunia. Dalam penelitian ini, ingin mengetahui model terbaik antara model logit biner dan model probit biner dengan menggunakan data risiko penyakit jantung koroner di Kota Framingham Amerika. Dari hasil analisis yang telah dilakukan, dapat disimpulkan bahwa faktor yang mempengaruhi risiko penyakit jantung koroner adalah jenis kelamin, usia, perokok aktif, kadar kolesterol, IMT dan glukosa. Nilai ketepatan klasifikasi metode regresi logit biner sebesar 84,95% dan nilai ketepatan klasifikasi metode probit biner sebesar 84,92%. Dari hasil perbandingan ketepatan klasifikasi antara metode regresi logit biner dan metode probit biner relatif sama.Kata Kunci: Regresi Model Logit Biner, Regresi Model Probit Biner, Penyakit Jantung Koroner. |
|
| dc.format |
application/pdf |
|
| dc.language |
eng |
|
| dc.publisher |
Universitas islam Bandung |
|
| dc.relation |
http://karyailmiah.unisba.ac.id/index.php/statistika/article/view/25633/pdf |
|
| dc.rights |
Copyright (c) 2021 Prosiding Statistika |
|
| dc.source |
Prosiding Statistika; Vol 7, No 1, Prosiding Statistika (Februari,2021); 87-94 |
|
| dc.source |
Prosiding Statistika; Vol 7, No 1, Prosiding Statistika (Februari,2021); 87-94 |
|
| dc.source |
2460-6456 |
|
| dc.source |
10.29313/.v7i1 |
|
| dc.subject |
Statistika |
|
| dc.subject |
Regresi Model Logit Biner, Regresi Model Probit Biner, Penyakit Jantung Koroner. |
|
| dc.title |
Perbandingan Ketepatan Klasifikasi Analisis Regresi Model Logit Biner dan Model Probit Biner terhadap Faktor-Faktor yang Mempengaruhi Risiko Penyakit Jantung Koroner |
|
| dc.type |
info:eu-repo/semantics/article |
|
| dc.type |
info:eu-repo/semantics/publishedVersion |
|
| dc.type |
Peer-reviewed Article |
|
| dc.type |
Kuantitatif |
|