ANALISIS REGRESI ROBUST ESTIMASI M DENGAN PEMBOBOT HUBER DAN ESTIMASI LTS DALAM MENGATASI PENCILAN DATA (STUDI KASUS : FAKTOR-FAKTOR YANG MEMPENGARUHI PENYAKIT ANEMIA)

Dzahabiyyah Muthmainnah, NIM.: 21106010080 (2025) ANALISIS REGRESI ROBUST ESTIMASI M DENGAN PEMBOBOT HUBER DAN ESTIMASI LTS DALAM MENGATASI PENCILAN DATA (STUDI KASUS : FAKTOR-FAKTOR YANG MEMPENGARUHI PENYAKIT ANEMIA). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (ANALISIS REGRESI ROBUST ESTIMASI M DENGAN PEMBOBOT HUBER DAN ESTIMASI LTS DALAM MENGATASI PENCILAN DATA (STUDI KASUS : FAKTOR-FAKTOR YANG MEMPENGARUHI PENYAKIT ANEMIA)) 21106010080_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (6MB) | Preview
	Text (ANALISIS REGRESI ROBUST ESTIMASI M DENGAN PEMBOBOT HUBER DAN ESTIMASI LTS DALAM MENGATASI PENCILAN DATA (STUDI KASUS : FAKTOR-FAKTOR YANG MEMPENGARUHI PENYAKIT ANEMIA)) 21106010080_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (7MB) | Request a copy

Abstract

Outliers in data can lead to inaccurate regression analysis results, especially when using the Ordinary Least Squares (OLS) method. This study aims to analyze the effectiveness of robust regression methods, specifically M-estimation with Huber weights and the Least Trimmed Squares (LTS) estimation, in handling outliers in anemia data. Anemia itself is a condition characterized by low levels of hemoglobin in the blood, which can lead to fatigue and reduced immune function. The data were analyzed using classical linear regression assumptions, including tests for homoscedasticity, normality, autocorrelation, and multicollinearity, before outlier detection was conducted using leverage, DFFITS, R-student, and Cook’s Distance. The case study for this research is anemia data from Alok Healthcare Ltd hospital located in Dhaka, Bangladesh. The data were uploaded by Mayen Uddin Mojumdar on Mendeley Data. The results showed that the LTS estimation method had the smallest Residual Standard Error (RSE) of 0.046 and the highest coefficient of determination of 0.998, making it the most optimal method for handling outliers compared to M-estimation and OLS. The factors influencing pediatric anemia include Red Blood Cell (RBC), Packed Cell Volume (PCV), Mean Corpuscular Hemoglobin (MCH), Mean Corpuscular Volume (MCV), and Mean Corpuscular Hemoglobin Concentration (MCHC).

Share this knowledge with your friends :

Actions (login required)

View Item