PENERAPAN METODE EMPIRICAL BEST LINEAR UNBIASED PREDICTION (EBLUP) PADA MODEL PENDUGAAN AREA KECIL (Studi Kasus: Estimasi Tingkat Kemiskinan di Provinsi Papua Tahun 2019)

EMSA CITRA SAPUTRI, NIM. 16610028 (2021) PENERAPAN METODE EMPIRICAL BEST LINEAR UNBIASED PREDICTION (EBLUP) PADA MODEL PENDUGAAN AREA KECIL (Studi Kasus: Estimasi Tingkat Kemiskinan di Provinsi Papua Tahun 2019). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PENERAPAN METODE EMPIRICAL BEST LINEAR UNBIASED PREDICTION (EBLUP) PADA MODEL PENDUGAAN AREA KECIL (Studi Kasus: Estimasi Tingkat Kemiskinan di Provinsi Papua Tahun 2019)) 16610028_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (3MB) | Preview
	Text (PENERAPAN METODE EMPIRICAL BEST LINEAR UNBIASED PREDICTION (EBLUP) PADA MODEL PENDUGAAN AREA KECIL (Studi Kasus: Estimasi Tingkat Kemiskinan di Provinsi Papua Tahun 2019)) 16610028_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (6MB)

Abstract

The methods used to obtain data include census and surveys. In Indonesia, the agency entrusted with conducting censuses and surveys is the Central Statistics Agency (BPS). The objects that are observed in the census are all elements in the population. While the survey is only part of the elements that exist in the population. The data generated in this survey is designed for a large area. Problems will arise if you want to get information in a small area such as a village, sub-district or district. One of the efforts is to estimate up to a small area without adding the number of samples, namely estimating a small area. The purpose of the concept of small area estimation is to increase the accuracy of estimation of parameters by indirect estimation method. Indirect estimation works by borrowing information from other areas that have almost the same characteristics, commonly referred to as accompanying variables. One of the indirect estimates is Empirical Best Linear Unbiased Prediction (EBLUP). In this study, the method used is EBLUP based on area level where to estimate the influence parameter, we use Maximum Likelihood (ML) and the variance component with Restricted Maximum Likelihood (REML). Next, to see how accurate the results are using the Relative Root Mean Square Error (RRMSE). The case is then applied to estimate the poverty rate in Papua Province. It was found that the RRMSE value from the direct estimate was greater than the estimate with EBLUP although there were some districts whose results were smaller. This is because the selection of the accompanying variables is not right.

Share this knowledge with your friends :

Actions (login required)

View Item