Implemetasi Model Autoregressive (AR) Dan Autoregressive Conditional Heteroskedasticity (ARCH) Untuk Memprediksi Harga Emas

Ni Luh Ketut Dwi Murniati, Indwiarti Indwiarti, Aniq Atiqi Rohmawati


Gold is a one of  high selling value items in the market, and it  can be used as an investment item. The price of gold in the market tends to be stable and not undergoing too significant changes which makes gold be a very valuable item. The aim of this research is to predict gold price using AR (1) and ARCH (1) model which are the part of time series methods. The data of gold price is obtained from ANTAM's daily historical website from 2007 - 2017. Here, the basic information about data is given by using descriptive statistic and the estimation of parameters in each model is condacted by using Maximum Likelihood Estimation (MLE). To evaluate the model, Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used. In this research, the estimated model of AR (1) and ARCH (1) given as X_t = -0.012X_{t-1}+epsion_t and X_t = epsilon_t sqrt{0.000053+0.011958X^2_{t-1}} respectively. Moreover, the result of MAE and RMSE using AR (1) model are 0.0261 and 0.0342 respectively, meanwhile for ARCH (1) model  are 0.0170 and 0.0251 respectively.

Full Text:




  • There are currently no refbacks.

Copyright (c) 2018 Ni Luh Ketut Dwi Murniati, Indwiarti Indwiarti, Aniq Atiqi Rohmawati

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.