Wirawati, Ika (2017) Pemodelan Pengeluaran Per Kapita Rumah Tangga Di Maluku Utara Menggunakan Struktur Hirarki Dua Tingkat Dengan Pendekatan Bayesian. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
1315201712-Master-Theses.pdf - Published Version Download (2MB) | Preview |
Abstract
Pengeluaran merupakan salah satu ukuran yang merepresentasikan kondisi ekonomi suatu rumah tangga, sehingga sering digunakan untuk mengukur tingkat kesejahteraan ataupun kemiskinan di suatu daerah. Data pengeluaran yang dihasilkan dari Survei Sosial Ekonomi Nasional (Susenas) merupakan data berstruktur hirarki. Analisis statistik yang sesuai untuk memodelkan tipe data ini adalah model linier hirarki. Pemodelan dilakukan menggunakan model linear hirarki dua tingkat dengan sembilan karakteristik rumah tangga di tingkat pertama (model mikro) dan tujuh karakteristik wilayah kabupaten/kota di tingkat kedua (model makro). Selain struktur data, pada penelitian ini juga mempertimbangkan pola distribusi pengeluaran per kapita yang terbukti mengikuti distribusi Gamma Tiga Parameter. Pola distibusi data dapat merepresentasikan karakteristik pola pengeluaran yang unik antar kabupaten/kota, sehingga diharapkan akan menghasilkan model yang khas. Estimasi parameter model hirarki dua tingkat dilakukan dengan pendekatan Bayesian menggunakan Markov Chain Monte Carlo (MCMC) dan algoritma Gibbs Sampling. Model hirarki yang terbentuk terbukti dapat menjelaskan variasi data sebesar 55,03%. Hasil menunjukkan bahwa variasi koefisien regresi model mikro antar kabupaten/kota terbukti secara signifikan dipengaruhi oleh karakteristik rumah tangga dan karakteristik kabupaten/kota. Dengan demikian, model hirarki dua tingkat dengan pendekatan Bayesian terbukti dapat menggambarkan pengaruh prediktor pada tingkatan berbeda terhadap pengeluaran per kapita rumah tangga di Maluku Utara.
=================================================================
Expenditure is one of the measurements that represents the economic condition of a household, so it is often used to measure the welfare or the poverty in a region. Expenditure data which is obtained from the National Socioeconomic Survey (Susenas) is a data with hierarchical structure. The appropriate statistical analysis in modeling this type of data is the hierarchical linear model. Modeling was performed using a two-level hierarchical linear model with nine characteristics of household in the first level (micro model) and seven characteristics of districts/cities in the second level (macro model). In addition to considering the structure of the data, this research would also like to consider the distribution pattern of per capita expenditure. The data were captured by the three parameters Gamma distribution. It could represent a unique characteristic of expenditure pattern among districts/cities, so it is expected to give results in a distinctive model. The estimation method that used in this research is the Bayesian method using Markov Chain Monte Carlo (MCMC) algorithm and Gibbs Sampling. Hierarchical model were proven to explain the variation data at 55.03%. The results showed that the variation of micro mode coefficients were significantly affected by the household and the districts/cities characteristics. Thus, the two-level hierarchical model with Bayesian approach was proven to demonstrate the effect of the predictor at different levels in per capita household expenditure in Maluku Utara.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Pengeluaran per Kapita Rumah Tangga; Bayesian; Struktur Hirarki; MCMC; Gibbs Sampling; Per Capita Household Expenditure; Bayesian; Hierarchical Structure |
| Subjects: | H Social Sciences > HA Statistics |
| Divisions: | Faculty of Mathematics and Science > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | IKA WIRAWATI - |
| Date Deposited: | 06 Mar 2017 08:53 |
| Last Modified: | 06 Mar 2019 03:07 |
| URI: | http://repository.its.ac.id/id/eprint/2246 |
Actions (login required)
 |
View Item |