Klasifikasi Indeks Pembangunan Manusia Indonesia dengan Metode Classification and Regression Tress (CART)

Hardianti, Dewi (2018) Klasifikasi Indeks Pembangunan Manusia Indonesia dengan Metode Classification and Regression Tress (CART). S1 thesis, Universitas Mataram.

[img]
Preview
Text
JURNAL DEWI HARDIANTI (G1D014013).pdf

Download (608kB) | Preview

Abstract

The Human Development Index (HDI) is an indicator to measure success in an effort to build the quality of human life. HDI (Y) is measured by 3 basic dimensions, namely Longevity and Healthy Life as measured by Life Expectancy (X1); Education as measured by Number of School Length Expectations (X2) and Average School Duration (X3); Decent standard of living as measured by GDP per Capita (X4). HDI of Indonesia has increased from year to year. However, some districts/ cities in Indonesia still have low HDI. The step that can be taken by the local government is to identify the most influential variables. One way that can be done is by determining the classification tree for the classification of HDI. Classification and Regression Trees (CART) is a nonparametric method, developed to classify, both for category response variables, continuous, or a mixture of both. Therefore, in this study CART method was used to classify HDI into low, medium, high, and very high categories. Based on the results of the analysis, the most influential variable on the classification of Indonesian HDI is the Average School Duration. Furthermore, for the categories of HDI classification trees obtained, namely low, medium, and high.

Item Type: Thesis (S1)
Keywords (Kata Kunci): Gini Index, Goodness of Split, Optimal Tree, Sorter Selection, Terminal Knot.
Subjects: S Agriculture > S Agriculture (General)
Divisions: Fakultas Matematika dan ilmu Pengetahuan Alam
Depositing User: Saprudin Saprudin
Date Deposited: 05 Dec 2018 02:50
Last Modified: 05 Dec 2018 02:50
URI: http://eprints.unram.ac.id/id/eprint/11106

Actions (login required)

View Item View Item