TY  - THES
N1  - Sri Utami Zuliana, S.Si., M.Sc., Ph.D
ID  - digilib71783
UR  - https://digilib.uin-suka.ac.id/id/eprint/71783/
A1  - Dzahabiyyah Muthmainnah, NIM.: 21106010080
Y1  - 2025/06/22/
N2  - 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).
PB  - UIN SUNAN KALIJAGA YOGYAKARTA
KW  - Regresi Robust
KW  -  Estimasi M
KW  -  Estimasi LTS
KW  -  Pencilan
KW  -  Anemia
M1  - skripsi
TI  - ANALISIS REGRESI ROBUST ESTIMASI M DENGAN PEMBOBOT HUBER DAN ESTIMASI LTS DALAM MENGATASI PENCILAN DATA (STUDI KASUS : FAKTOR-FAKTOR YANG MEMPENGARUHI PENYAKIT ANEMIA)
AV  - restricted
EP  - 88
ER  -