Markov-switching and noise-to-signal ratio approach for early detection of currency crises

Sugiyanto Sugiyanto, Muhammad Bayu Nirwana, Isnandar Slamet, Etik Zukhronah, Syifa’ Salsabila Gita Parahita

Abstract


Economic instability can easily lead to a currency crisis. Therefore, observing a number of crisis indicators is crucial for building an early warning system (EWS). However, selecting the indicators most responsive to the crisis is the best choice. For this purpose, the noise-to-signal ratio (NSR) method was used. Monthly data from 1990-1925 were used in the autoregressive moving average (ARMA), generalized autoregressive moving average with generalized autoregressive conditional heteroscedasticity (GARMACH), and Markov-switching (MS)-GARMACH hybrid models to explain the crisis. Model interpretation indicates that there will be no crisis from May 2025-April 2026.

Full Text:

PDF


DOI: http://doi.org/10.11591/ijaas.v15.i1.pp42-54

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Sugiyanto, Muhammad Bayu Nirwana, Isnandar Slamet, Etik Zukhronah, Syifa’ Salsabila Gita Parahita

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

View the IJAAS Visitor Statistics

International Journal of Advances in Applied Sciences (IJAAS)
p-ISSN 2252-8814, e-ISSN 2722-2594
This journal is published by Intelektual Pustaka Media Utama (IPMU) in collaboration with the Institute of Advanced Engineering and Science (IAES).