PERBANDINGAN KINERJA METODE REGRESI ROBUST (MM, S, DAN LTS) DALAM ANALISIS INDEKS PEMBANGUNAN MANUSIA PADA DATA PROVINSI DI INDONESIA

Juliana Nur Azizah, NIM.: 22106010063 (2026) PERBANDINGAN KINERJA METODE REGRESI ROBUST (MM, S, DAN LTS) DALAM ANALISIS INDEKS PEMBANGUNAN MANUSIA PADA DATA PROVINSI DI INDONESIA. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PERBANDINGAN KINERJA METODE REGRESI ROBUST (MM, S, DAN LTS) DALAM ANALISIS INDEKS PEMBANGUNAN MANUSIA PADA DATA PROVINSI DI INDONESIA) 22106010063_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (7MB) | Preview
	Text (PERBANDINGAN KINERJA METODE REGRESI ROBUST (MM, S, DAN LTS) DALAM ANALISIS INDEKS PEMBANGUNAN MANUSIA PADA DATA PROVINSI DI INDONESIA) 22106010063_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (16MB) | Request a copy

Abstract

Outliers in regression analysis can distort parameter estimation and reduce model accuracy, potentially leading to invalid conclusions about influential factors. Outliers caused by measurement or data entry errors should be corrected, while outliers reflecting genuine regional conditions should be retained to preserve important information. Robust regression is used to address outliers without discarding such observations. This study compares the performance of MM-estimator, S-estimator, and Least Trimmed Squares (LTS) in modeling the Human Development Index (HDI) across 38 provinces in Indonesia in 2024, using Gross Regional Domestic Product (GRDP), Adjusted Per Capita Expenditure, Provincial Minimum Wage (UMP), Open Unemployment Rate (TPT), and Poverty Ratio as independent variables. Outlier detection using Leverage and DFFITS identified five provinces as outliers, reflecting genuine socio-economic disparities and thus retained in the analysis. Based on the highest Adjusted

Share this knowledge with your friends :

Actions (login required)

View Item