Ezha Easyfa Wieldyanisa, Ferissa Maulida Ismi, Refa Berliana Putri, Shabrina Nareswari Dwitya, Elly Pusporani, Dita Amelia

ANALISIS BIPLOT PADA BERBAGAI FAKTOR KEMISKINAN DI INDONESIA BERDASARKAN PROVINSI

Introduction

Analisis biplot pada berbagai faktor kemiskinan di indonesia berdasarkan provinsi. Analisis biplot mengungkap faktor kemiskinan di provinsi Indonesia. Teliti hubungan pendidikan, kesehatan, infrastruktur & PDRB per kapita, serta korelasi antar variabel untuk kebijakan pembangunan tepat sasaran.

Abstract

Kemiskinan merupakan permasalahan kompleks yang dipengaruhi oleh berbagai faktor sosial dan ekonomi. Berdasarkan hal tersebut, penelitian ini bertujuan untuk melihat hubungan antara provinsi di Indonesia dan berbagai faktor yang berpengaruh terhadap kemiskinan seperti pendidikan, kesehatan, dan infrastruktur dasar menggunakan analisis biplot. Data sekunder tahun 2024 dari BPS digunakan dengan delapan variabel utama, meliputi usia harapan hidup, produk domestik regional bruto (PDRB) per kapita, angka melek huruf, rumah tangga dengan sanitasi layak, akses air layak, akses listrik, angka partisipasi sekolah, dan rata-rata lama sekolah. Hasil analisis menunjukkan bahwa 81,772% keragaman data dapat dijelaskan oleh dua komponen utama dalam grafik biplot. Provinsi-provinsi dikelompokkan ke dalam empat kuadran berdasarkan kesamaan karakteristik kemiskinan. Faktor dengan keragaman tertinggi adalah rumah tangga dengan sanitasi layak, sedangkan faktor dengan keragaman terendah adalah PDRB per kapitaKorelasi antar variabel menunjukkan bahwa angka melek huruf dan akses listrik memiliki hubungan paling kuat, yang berarti semakin tinggi tingkat melek huruf suatu daerah, semakin besar pula kemungkinan masyarakatnya memiliki akses terhadap listrik. Sebaliknya, hubungan terlemah terdapat antara PDRB dan akses listrik. Penelitian ini menunjukkan bahwa memahami kemiskinan memerlukan pendekatan terhadap berbagai faktor yang saling berkaitan serta perlunya kebijakan pembangunan yang disesuaikan dengan karakteristik daerah masing-masing.

Review

This paper presents a timely and crucial analysis of poverty factors across Indonesian provinces, employing biplot analysis to unravel complex socio-economic relationships. The research clearly articulates its objective: to identify connections between various provinces and key determinants of poverty, including education, health, and basic infrastructure. The use of secondary data from BPS, encompassing eight pertinent variables such as life expectancy, PDRB per capita, literacy rate, and access to sanitation, demonstrates a robust foundation for the study. The methodological choice of biplot analysis is well-suited for visualizing multivariate data, offering a comprehensive overview of how provinces cluster and how different factors interrelate, providing valuable insights into the multifaceted nature of poverty. The findings reveal significant insights, with two principal components explaining an impressive 81.772% of the data's variability, underscoring the effectiveness of the biplot in capturing the underlying structure. The clustering of provinces into four distinct quadrants based on shared poverty characteristics is a key contribution, offering a practical framework for targeted interventions. Notably, the analysis identifies household sanitation as the factor with the highest variability, while PDRB per capita shows the lowest. Furthermore, the correlation analysis provides compelling insights, highlighting a strong positive relationship between literacy rates and access to electricity, suggesting a reinforcing cycle of development. Conversely, the weak correlation between PDRB and electricity access prompts further inquiry into the pathways of economic development and infrastructure provision. While the study offers valuable contributions, a few points warrant further consideration. The abstract mentions the use of "data sekunder tahun 2024," which, if the paper is being reviewed prior to this year, requires clarification. This could be a typo, or it implies the use of projected or estimated data, which would need explicit justification regarding its reliability for analyzing current poverty characteristics. Additionally, while the paper concludes on the necessity of tailored development policies, the abstract could benefit from briefly hinting at the *nature* of these policies, perhaps by outlining how the identified provincial clusters directly inform distinct strategic approaches. Future work could also explore the temporal dynamics of these factors, possibly through a longitudinal analysis, to understand the evolution of poverty and the effectiveness of interventions over time.

Full Text

Comments

You need to be logged in to post a comment.