Soenarnatalina Soenarnatalina
Fakultas kesehatan Masyarakat, Universitas Airlangga

Published : 2 Documents
Articles

Found 2 Documents
Search

Pemodelan Bayesian Model Averaging (BMA) Pada Kasus Pneumonia Balita Sofia, Debbiyatus; Kuntoro, Kuntoro; Soenarnatalina, Soenarnatalina
Biometrika dan Kependudukan Vol 3, No 1 (2014): Jurnal Biometrika dan Kependudukan
Publisher : Biometrika dan Kependudukan

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

Abstract

ABSTRACTBayesian method is known as a better method than other methods because it combines the information from the sample data and the information from the previous distribution (prior). There are several methods in the Bayesian able to choose the best models involving uncertainty models and one of them is Bayesian Model Averaging (BMA). BMA is a method that can predict the best model based on the weighted average of all models. BMA goal is to combine model uncertainty in order to get the best model. The purpose of the study was to determine the linear regression model of the BMA in cases of pneumonia. Design research is applied research. The experiment was conducted in Situbondo in May-June 2014. Sampling was done by total sampling 0f 17 health centers throughout Situbondo. BMA results indicate that there were 27 models selected with the 5 best models from the 2048 model is formed. BMA Model was produced 9 significant variable predictor of the response variable. These variables were not smoke in the house, healthy household, exclusive breastfeeding, infants received vitamin A, DPT immunization coverage, low birth weight, malnutrition children, number of posyandu and toddler health services. Variables were not significant are clean and healthy living behavior and infant visits.Keyword : linear regression, bayesian model averaging, pneumonia   
Multivariate Adaptive Regression Spline Approach for the Classification Accuracy of Drugs User in East Java Wenno, Stefanny Zulistya; Kuntoro, Kuntoro; Soenarnatalina, Soenarnatalina
Health Notions Vol 1, No 2 (2017): April-June
Publisher : Humanistic Network for Science and Technology (HNST)

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

Abstract

Background: Classification method is a statistical method for grouping or classifying the systematically arranged data into a group so we can know that an individual are in a particular group. Multivariate Adaptive Regression Spline (MARS) introduced by (Friedman, 1991) is a methodology for approximating functions of many input variables given the value of the function at a collection of points in the input space. Although training times for this method tend to be much faster than feed forward neural networks using back propagation, it can still be fairly slow for large problems that require complex approximations (many units). Methods: This was a nonreactive study, which is a measurement which individuals surveyed did not realize that they are part of a study. Result: Based on the best model selection criteria MARS then the selected is with model BF 20, MI 1 and MO 0 with the form Y = 0.929944 + 0.912438 * BF1 - 0.218729 * BF2 + 0.886429 * BF3 + 0.215575 * BF4 + 0.0745423 * BF5 - 0.232014 * BF6 + 0.0472966 * BF7 - 0.0367996 * BF8 + 0.0188678 * BF9 + 0.0304537 * BF11. Accuracy of drugs user rehabilitation classification that non relapse and relapse status based on MARS model is calculated using precision classification value. The accuracy level of drugs user rehabilitation classification in East Java using MARS method produces accuracy of 95,71% and misclassification of 4,29%. The magnitude of the above classification accuracy is due to the large prediction in the nonrelapse class that as many as 269 people with nonrelapse status are appropriately predicted in the nonrelapse status class. Conclusion: There are four important variables included in the best MARS model that is age of first use of drugs, how to use drugs, marital status and jobs. The accuracy level of drugs user rehabilitation classification in East Java using MARS method produces accuracy of 95,71% and misclassification of 4,29%. Keywords: Multivariate adaptive regression spline, Classification accuracy, Drugs user.