Matriks bobot lokasi pada tahap identifikasi model Generalized Space-Time Autoregressive (GSTAR): Studi kasus nilai tukar petani di 32 Provinsi di Indonesia

Azizah, Annisa (2016) Matriks bobot lokasi pada tahap identifikasi model Generalized Space-Time Autoregressive (GSTAR): Studi kasus nilai tukar petani di 32 Provinsi di Indonesia. Diploma thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_COVER.pdf Download (203kB) | Preview
Preview	Text (ABSTRAK) 2_ABSTRAK.pdf Download (201kB) | Preview
Preview	Text (DAFTAR ISI) 3_DAFTAR ISI.pdf Download (416kB) | Preview
Preview	Text (BAB I) 4_BAB I.pdf Download (542kB) | Preview
	Text (BAB II) 5_BAB II.pdf Restricted to Registered users only Download (857kB)
	Text (BAB III) 6_BAB III.pdf Restricted to Registered users only Download (561kB)
	Text (BAB IV) 7_BAB IV.pdf Restricted to Registered users only Download (1MB)
	Text (BAB V) 8_BAB V.pdf Restricted to Registered users only Download (326kB)
	Text (DAFTAR PUSTAKA) 9_ DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (317kB)

Abstract

INDONESIA: Model Generalized Space Time Autoregressive (GSTAR) digunakan untuk memodelkan data deret waktu yang juga mempunyai keterkaitan antar lokasi (space time). Pada tahap identifikasi model, bobot lokasi pada model GSTAR menunjukkan hubungan antar lokasi, diantaranya adalah bobot normalisasi korelasi silang, biner, seragam dan berdasarkan invers jarak. Tujuan penelitian ini yaitu 1) memahami peranan matriks bobot lokasi pada tahap identifikasi model 2) mengetahui jenis-jenis matriks bobot lokasi pada tahap identifikasi model 3) menerapkan matriks bobot lokasi pada studi kasus data dengan hasil akhir berupa model. Data yang digunakan adalah data sekunder Nilai Tukar Petani di 32 Provinsi selama 71 bulan dari tahun 2005-2013 yang diperoleh dari buku Indikator Ekonomi yang diterbitkan oleh BPS setiap bulannya. Kandidat model yang diperoleh untuk data tersebut adalah model GSTAR(1;1) untuk 4 lokasi dan 14 lokasi berdasarkan keempat matriks bobot lokasi, GSTAR(2;1;1) untuk 4 lokasi berdasarkan matriks bobot normalisasi korelasi silang dan invers jarak, dan untuk 14 lokasi berdasarkan matriks bobot normalisasi korelasi silang dan biner, GSTAR(2;1,2) untuk 4 lokasi berdasarkan matriks bobot seragam, dan GSTAR(2;1,3) untuk 4 lokasi berdasarkan matriks bobot biner. ENGLISH: Generalized Space Time Autoregressive (GSTAR) model was used to model the time series data that had correlation inter-location (space time). In the stage of model identification, spatial weight on GSTAR model shown relations of inter-location, which were weight normalized cross-correlation, binary, uniform, and inverse of distance. The main purpose of this research is to 1) comprehend the role of weight matrix location on the model identification stage 2) knowing the types of weight matrix on the identification model 3) apply the weight matrix location on case study with the results of the final form of the model. The data used was secondary data of Farmer Exchange Rate in 32 provinces for 71 months from year 2005 to 2013, which has been obtained from the Economic Indicators published by BPS every month. Model candidates that have been obtained of the data were GSTAR(1;1) for 4 locations and 14 locations built upon four spatial weight matrices, GSTAR(2;1;1) for 4 locations and 14 locations reposed on weight normalized cross-correlation matrix and inverse of distance, and for 14 locations based on weight normalized cross-correlation matrix and binary, GSTAR(2;1,2) for 4 locations by uniform weighting matrix, and then GSTAR(2;1,3) for 4 locations by binary weighting matrix.

Actions (login required)

View Item