Comparison of Estimate Method of Moment and Least Trimmed Squares in Models Robust Regression

Authors

  • Tri Wahyuni Nurmulyati Universitas Negeri Padang
  • Dony Permana
  • Nonong Amalita
  • Zamahsary Martha

DOI:

https://doi.org/10.24036/ujsds/vol2-iss2/176

Abstract

The poverty line is the minimum income that a person must earn to be considered to have a decent standard of living in a particular area. In 2022, the poverty line in West Sumatra Province was higher than the poverty line in Indonesia as a whole. An analysis was conducted to identify the factors influencing the poverty line in West Sumatra Province. However, the observational data on the poverty line and its influencing factors contained outlier. Therefore, robust regression analysis was performed to address the data containing outlier, comparing two estimates: MM estimation and LTS estimation. By examining the  value, the best estimate was found to be MM estimation, with significant factors being average net wages/salaries, TPT, APM, and AMH. If the average net wages/salaries, TPT, APM, and AMH increase, the poverty line in West Sumatra will rise. With an  of 0.9582, the model can explain 95.82% of the variation in the poverty line, while the remaining variation is explained by other factors not included in the model.

Published

2024-05-31

How to Cite

Tri Wahyuni Nurmulyati, Dony Permana, Nonong Amalita, & Martha, Z. (2024). Comparison of Estimate Method of Moment and Least Trimmed Squares in Models Robust Regression. UNP Journal of Statistics and Data Science, 2(2), 240–248. https://doi.org/10.24036/ujsds/vol2-iss2/176

Most read articles by the same author(s)

1 2 3 4 5 6 7 > >>