Forecasting exchange rate across countries with gold price as exogenous variable using transfer function and VARI-X model

Sesay, Alhassan (2018) Forecasting exchange rate across countries with gold price as exogenous variable using transfer function and VARI-X model. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 06211650017015_Master-Thesis.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

Investor dan kolektor menyimpan emas sebagai tabungan dan kekayaan mereka dalam jumlah yang banyak. Emas tidak dikenai bunga layaknya obligasi harta atau tabungan, tetapi harga emas sering mengalami kenaikan dan penurunan. Penelitian ini bertujuan untuk membuat model statistik untuk memahami hubungan antara nilai tukar dan harga emas di beberapa negara yang merupakan anggota utama dalam pengekspor emas di dunia. Selain itu, penelitian ini juga bertujuan untuk mendapatkan model terbaik untuk peramalan nilai tukar dan harga emas sebagai variabel eksogen lintas negara dengan membandingkan akurasi prediksi antara Fungsi Transfer dan VARI-X. Nilai tukar tiga negara digunakan sebagai studi kasus terhadap harga emas yaitu Australia, Brasil, dan Afrika Selatan. Dalam penelitian ini, model ARIMA digunakan untuk meramalkan data harga emas sebagai input untuk Fungsi Transfer dan VARI-X. Model Fungsi Transfer hanya mempertimbangkan hubungan antara harga emas sebagai input dengan nilai tukar di masing-masing negara, sedangkan model VARI-X mem-pertimbangkan juga keterkaitan antara nilai tukar di ketiga negara tersebut. Data yang digunakan adalah data harian periode 1 Juni 2010 hingga 28 Februari 2018. The Root Mean Square Error (RMSE) dan Mean Absolute Percentage Error (MAPE) adalah kriteria yang dipakai untuk memilih model terbaik. Hasil kajian menunjukkan bahwa VARI-X adalah model terbaik untuk meramalkan nilai tukar di Australia, sedangkan Fungsi Transfer adalah model terbaik untuk meramalkan nilai tukar di Afrika Selatan dan Brasil. ========== Investors and collectors hold gold as protection for their savings and wealth at large. Gold does not pay interest like treasure bonds or savings account but current gold prices often reflect increases and decreases. This research aims to provide a model for understanding the relationship between exchange rate and gold price across countries as key members in the export of gold in the world. Also, it finds the best method to exchange rate and exogenous gold price data across countries by comparing the forecast accuracy between transfer function and VARI-X. Three countries exchange rates are used as a case study against the gold price i.e. Australia, Brazil, and South Africa. In this research, the ARIMA model is used for forecasting gold price data as an input for Transfer Function and VARI-X models. Transfer function model only considers the relationship between the gold price as input with the exchange rate in each country, whereas VARI-X model also considers the interrelationship between exchange rates in these three countries. Daily data is used for the period 1st June 2010 to the 28th February 2018. The Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) is used as criteria for selecting the best model. The results show that VARI-X is the best model for forecasting the Australian exchange rate, whereas Transfer Function is the best model for forecasting South African and Brazilian exchange rates.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	transfer function, vari-x, exchange rate, gold price, RMSE MAPE
Subjects:	H Social Sciences > HG Finance > HG3881 Foreign exchange. H Social Sciences > HG Finance > HG4012 Mathematical models
Divisions:	Faculty of Mathematics and Science > Statistics > 49101-(S2) Master Thesis
Depositing User:	- Davi Wah
Date Deposited:	02 May 2019 09:17
Last Modified:	02 May 2019 09:17
URI:	http://repository.its.ac.id/id/eprint/62911

Actions (login required)

View Item