Indicator Saturation Research Articles

Cryptocurrency Returns Over a Decade: Breaks, Trend Breaks and Outliers

This study finds breaks, trend breaks, and outliers in the last decade returns of five cryptocurrencies Bitcoin, Ethereum, Litecoin, Tether USD, and Ripple that experienced frequent changes. The study uses the indicator saturation (IS) approach to simultaneously identify breaks, trend breaks, and outliers in these returns to gain a deeper understanding in their dynamics. The study found that monthly, weekly and daily breaks existed in these returns as well as trend breaks, and outliers mostly during the market peaks in 2017, 2018, 2020, and 2021 that can be attributed to a number of things, such as the global Covid-19 pandemic in 2020, the 2021 crypto crackdown in China, the 2020 price halving of Bitcoin, and the 2017–2018 initial coin offering (ICO) boom. These returns also have common break segments and outliers. The application of IS technique to cryptocurrencies and simultaneous detection of market breaks, trend breaks, and outliers makes this study unique. This study is limited to considering only returns of five digital coins. These results may help traders, investors, and financial analysts modify their tactics and risk-management techniques to deal with the complexity of the cryptocurrency market.

Modelling Australian electricity prices using indicator saturation

In our analysis of electricity price series from Australia's National Electricity Market (NEM), we employ the indicator saturation (IS) approach to simultaneously model the stylised facts of electricity prices, including extreme spikes, seasonality, level-shifts, and autocorrelation. The standard modelling methods described in the literature tend to use regime-switching models to cope with these characteristics, but these models cannot fully reflect the stylised facts of interest. Using a range of model-evaluation tools, our analysis finds that the IS method outperforms the regime-switching models in various settings. In addition to the statistical superiority of this approach, we detail the relevance of our findings to policymaking in the NEM and provide recommendations for the development of the electricity markets in Australia.

Does credit boost agricultural performance? Evidence from Vietnam

PurposeThis study investigates the short-run and long-run impacts of agricultural credit on Vietnam's agricultural GDP over the period 2004:Q4–2016:Q4, with the incorporation of agricultural labor, public investment and rainfall as important determinants of agricultural GDP.Design/methodology/approachThis study applies the indicator saturation (IS) break tests and the autoregressive distributed lag (ARDL) bounds test with structural breaks to examine the credit–agricultural performance nexus. The causal relationships among variables are explored through the Toda–Yamamoto Granger causality test.FindingsThe results indicate that agricultural credit positively influences agricultural GDP in both the short-run and long-run. A unidirectional causal relationship running from credit to agricultural GDP is confirmed. The results also discover the positive and significant effects of labor and rainfall on agricultural GDP in the long-run.Practical implicationsThe results imply that the government should focus on expanding agricultural credit as well as enhancing the efficiency of agricultural credit. Furthermore, formal credit institutions should be encouraged to work closely with farmers and agricultural enterprises to offer flexible lending periods and amounts to meet the real situation of agricultural production.Originality/valueThis study is the first to examine the credit–agricultural performance relationship at the macro-level in Vietnam. Based on the empirical results, the study provides crucial implications for policymakers to optimize the effectiveness of agricultural credit and enhance nationwide agricultural performance.

User-Specified General-to-Specific and Indicator Saturation Methods

General-to-Specific (GETS) modelling provides a comprehensive, systematic and cumulative approach to modelling that is ideally suited for conditional forecasting and counterfactual analysis, whereas Indicator Saturation (ISAT) is a powerful and flexible approach to the detection and estimation of structural breaks (e.g. changes in parameters), and to the detection of outliers. To these ends, multi-path backwards elimination, single and multiple hypothesis tests on the coefficients, diagnostics tests and goodness-of-fit measures are combined to produce a parsimonious final model. In many situations a specific model or estimator is needed, a specific set of diagnostics tests may be required, or a specific fit criterion is preferred. In these situations, if the combination of estimator/model, diagnostics tests and fit criterion is not offered by publicly available software, then the implementation of user-specified GETS and ISAT methods puts a large programming-burden on the user. Generic functions and procedures that facilitate the implementation of user-specified GETS and ISAT methods for specific problems can therefore be of great benefit. The R package gets, version 0.20 (September 2019), is the first software - both inside and outside the R universe - to provide a complete set of facilities for user-specified GETS and ISAT methods: User-specified model/estimator, user-specified diagnostics and user-specified goodness-of-fit criteria. The aim of this article is to illustrate how user-specified GETS and ISAT methods can be implemented. The aim of this article is to illustrate how user-specified GETS and ISAT methods can be implemented with the R package gets.

Automated General-to-Specific (GETS) Regression Modeling and Indicator Saturation for Outliers and Structural Breaks

This paper provides an overview of the R package gets, which contains facilities for automated general-to-specific (GETS) modeling of the mean and variance of a regression, and indicator saturation (IS) methods for the detection and modeling of outliers and structural breaks. The mean can be specified as an autoregressive model with covariates (an model), and the variance can be specified as an autoregressive log-variance model with covariates (a model). The covariates in the two specifications need not be the same, and the classical linear regression model is obtained as a special case when there is no dynamics, and when there are no covariates in the variance equation. The four main functions of the package are arx, getsm, getsv and isat. The first function estimates an AR-X model with log-ARCH-X errors. The second function undertakes GETS modeling of the mean specification of an 'arx' object. The third function undertakes GETS modeling of the log-variance specification of an 'arx' object. The fourth function undertakes GETS modeling of an indicator-saturated mean specification allowing for the detection of outliers and structural breaks. The usage of two convenience functions for export of results to EViews and Stata are illustrated, and LATEX code of the estimation output can readily be generated.