Detection of Multiple Structural Breaks in Large Covariance Matrices

This article studies multiple structural breaks in large contemporaneous covariance matrices of high-dimensional time series satisfying an approximate factor model. The breaks in the second-order moment structure of the common components are due to sudden changes in either factor loadings or covariance of latent factors, requiring appropriate transformation of the factor models to facilitate estimation of the (transformed) common factors and factor loadings via the classical principal component analysis. With the estimated factors and idiosyncratic errors, an easy-to-implement CUSUM-based detection technique is introduced to consistently estimate the location and number of breaks and correctly identify whether they originate in the common or idiosyncratic error components. The algorithms of Wild Binary Segmentation for Covariance (WBS-Cov) and Wild Sparsified Binary Segmentation for Covariance (WSBS-Cov) are used to estimate breaks in the common and idiosyncratic error components, respectively. Under some technical conditions, the asymptotic properties of the proposed methodology are derived with near-optimal rates (up to a logarithmic factor) achieved for the estimated breaks. Monte Carlo simulation studies are conducted to examine the finite-sample performance of the developed method and its comparison with other existing approaches. We finally apply our method to study the contemporaneous covariance structure of daily returns of S&P 500 constituents and identify a few breaks including those occurring during the 2007–2008 financial crisis and the recent coronavirus (COVID-19) outbreak. An package "” is provided to implement the proposed algorithms.

A comparison of methods for forecasting value at risk and expected shortfall of cryptocurrencies

Several procedures to forecast daily risk measures in cryptocurrency markets have been recently implemented in the literature. Among them, long‐memory processes, procedures taking into account the presence of extreme observations, procedures that include more than a single regime, and quantile regression‐based models have performed substantially better than standard methods in terms of forecasting risk measures. Those procedures are revisited in this paper, and their value at risk and expected shortfall forecasting performance are evaluated using recent Bitcoin and Ethereum data that include periods of turbulence due to the COVID‐19 pandemic, the third halving of Bitcoin, and the Lexia class action. Additionally, in order to mitigate the influence of model misspecification and enhance the forecasting performance obtained by individual models, we evaluate the use of several forecast combining strategies. Our results, based on a comprehensive backtesting exercise, reveal that, for Bitcoin, there is no single procedure outperforming all other models, but for Ethereum, there is evidence showing that the GAS model is a suitable alternative for forecasting both risk measures. We found that the combining methods were not able to outperform the better of the individual models.

Cointegration between high base metals prices and backwardation: Getting ready for the metals super-cycle

This paper is devoted to test agents' behavior in the markets of hard commodities by trying to distinguish between managing future price structures to hedge their positions and speculating in on prices. We do a triple analysis: cointegration on the time series, structural breaks over the full time series and panel data. The analysis of the full series and the identification of structural breaks allows us to discover the connection between high prices and the negative futures price structure (backwardation) in rising prices scenarios of tin, copper, aluminium, and zinc. Moreover, we obtain that the base metals full matrix (price and futures price structure) is cointegrated in our analysis that uses panel data methods. We believe that these results are important for agents in the markets, as commodity traders or brokers, to maximize profits in their hedging positions.

U.S. House Prices by Census Division: Persistence, Trends and Structural Breaks

This paper uses fractional integration methods to examine persistence, trends and structural breaks in United States house prices, more specifically the monthly Federal Housing Finance Agency House Price Index for census divisions, and the United States as a whole over the period from January 1991 to August 2022. The full sample estimates imply that the order of integration of the series is above one in all cases, and is particularly high for the aggregate series, implying high levels of persistence. However, when the possibility of structural breaks is taken into account, segmented trends are detected. The subsample estimates of the fractional differencing parameter tend to be lower, with mean reversion occurring in a number of cases. This means that shocks in the series are expected to be transitory in these subsamples, disappearing in the long run by themselves. In addition, the time trend coefficient is at its highest in the last subsample, which in most cases starts around May 2020 coincident with the beginning of the coronavirus pandemic. The results provide clear evidence of differences between census divisions, which implies that appropriate housing policies should be designed at the local (rather than at the federal) level. © 2023, The Author(s).

Effects of COVID-19 on the relationship between inflation and REITs returns in South Africa

PurposeThis research aims to ascertain the extent to which the coronavirus disease 2019 (COVID-19) epidemic affected the relationship between inflation and real estate investment trusts (REITs) returns in South Africa.Design/methodology/approachThis research used the Johansen cointegration test and effective test in establishing if there is a long-run cointegrating equation between the variables. To ascertain if COVID-19 resulted in a different relationship regime between inflation and REITs returns, the sequential Bai-Perron method was used.FindingsBetween December 2013 and July 2022, there was no evidence of a long-run relationship between inflation and REITs returns, and a restricted vector autoregressive (VAR) model with a period lag for each variable best describing the relationship. Using the sequential Bai-Perron method, for one break, the results show February 2020 as a structural break in the relationship. A cointegrating equation is also found for the period before the structural break and another after the break. Interestingly, the relationship is negative before the break and a new positive relationship (regime) is confirmed after the noted break.Practical implicationsThis research helps REITs stakeholders to position themselves in light of any changes to macroeconomic activity within South Africa.Originality/valueThis is one of the first studies to test inflation relationship with REITs returns in South Africa and the effects of COVID-19 thereof. This research helps REITs stakeholders to position themselves in light of any changes to macroeconomic activity within South Africa.

A comparison of methods for forecasting value at risk and expected shortfall of cryptocurrencies

Several procedures to forecast daily risk measures in cryptocurrency markets have been recently implemented in the literature. Among them, long-memory processes, procedures taking into account the presence of extreme observations, procedures that include more than a single regime, and quantile regression-based models have performed substantially better than standard methods in terms of forecasting risk measures. Those procedures are revisited in this paper, and their value at risk and expected shortfall forecasting performance are evaluated using recent Bitcoin and Ethereum data that include periods of turbulence due to the COVID-19 pandemic, the third halving of Bitcoin, and the Lexia class action. Additionally, in order to mitigate the influence of model misspecification and enhance the forecasting performance obtained by individual models, we evaluate the use of several forecast combining strategies. Our results, based on a comprehensive backtesting exercise, reveal that, for Bitcoin, there is no single procedure outperforming all other models, but for Ethereum, there is evidence showing that the GAS model is a suitable alternative for forecasting both risk measures. We found that the combining methods were not able to outperform the better of the individual models. © 2022 John Wiley & Sons Ltd.

Estimating the risk of SARS-CoV-2 deaths using a Markov switching-volatility model combined with heavy-tailed distributions for South Africa.

BACKGROUND: SARS-CoV-2 (Covid-19 virus) infection exposed the unpreparedness of African countries to health-related issues, South Africa included. Africa recorded more than 211 853 deaths as a consequence of Covid-19. When rare and deadly diseases require urgent hospitalisation strikes, governments and healthcare providers are usually caught unprepared, resulting in huge loss of lives. Usually, at the beginning of such pandemics, there is no rich data for health practitioners and academics to be able to forecast the number of patients or deaths related to the pandemic. This study aims to predict the number of deaths associated with Covid-19 infection. With the availability of the number of deaths on a daily basis, the results stemming from this study are important to inform and plan health policy. METHODS: This study uses the daily number of deaths due to Covid-19 infection. Exploratory data analysis reveals that the data exhibits non-normality, three structural breaks and volatility clustering characteristics. The Markov switching (MS)-generalized autoregressive conditional heteroscedasticity (GARCH)-type model combined with heavy-tailed distributions is fitted to the returns of the data. Using available daily reported Covid-19-related deaths up until 26 August 2021, we report 10-day ahead forecasts of deaths. All forecasts are compared to the actual observed values in the forecasting period. RESULTS: The Anderson-Darling Goodness of fit test confirms that the fitted models are adequate for the data. The Kupiec likelihood ratio test and the root mean square error (RMSE) were used to select the robust model at different risk levels. At 95% the MS(3)-GARCH(1,1) combined with Pearson's type IV distribution (PIVD) is the best model. This indicates that the proposed best-fitting model is reasonable and can be used for predicting the daily number of deaths due to Covid-19. CONCLUSION: The MS(3)-GARCH(1,1)-PIVD model provides a reliable and accurate method for predicting the minimum number of death due to Covid-19. The accuracy of the proposed model will assist policymakers, academics and health practitioners in forecasting the volatility of future health-related deaths in which the predictability of volatility plays an integral role in health risk management.

Volatility Interdependence Between Cryptocurrencies, Equity, and Bond Markets.

This paper investigates (i) the return-volatility spillover between Bitcoin, Ethereum, Ripple, and Litecoin, (ii) the interdependence between cryptocurrencies' volatility and the US equity and bond markets' volatility, and (iii) the impact of the Covid-19 outbreak on the cryptocurrencies' return-volatility. A two-step estimation approach is considered where Univariate General Autoregressive Conditional Heteroskedastic models are estimated to model the volatility of the four cryptocurrencies then a Simultaneous Equation Model is estimated to model the interconnection between the cryptocurrency volatilities, the US equity and bond markets' volatility, and Covid-19 outbreak. We show that return-volatility spillovers exist among Bitcoin, Ethereum, and Litecoin while Ripple is the main transmitter of shocks. We find that the cryptocurrency market is detached from the US stock market but not from the US bond market. Finally, we show that a high economic and financial uncertainty in the US stock market due to pandemic outbreaks affects the price of Litecoin, Bitcoin, and Ethereum. However, shocks are short-lived. Our findings have practical implications; as the evidence of volatility spillovers among cryptocurrencies and their relative isolation from the majority of mainstream assets should be factored into the valuation and portfolio diversification strategies of investors. In crisis times such as those induced by Covid-19, investors who seek protection from downward movements in bond markets could benefit from taking a position in Ethereum. Policymakers can also rely on our findings to time their intervention to stabilize markets and control uncertainties inherent to stressful periods.

Nowcasting domestic demand using a dynamic factor model: the case of Ireland

The COVID-19 pandemic highlighted the need for timely information on the evolving economic impacts of such a crisis. During these periods, there is an increased need to understand the current state of the economy to guide the effective implementation of policy. This is made difficult by the fact that official estimates of economic indicators, such as those published by national statistical agencies, are released with a substantial lag. Using the case of Ireland, this article shows that the information contained in a panel of monthly economic indicators can be related to Quarterly National Accounts under the methodological framework of a dynamic factor model (DFM). The article also suggests that accounting for structural breaks improves the nowcasting performance of domestic demand. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

Detection of Multiple Structural Breaks in Large Covariance Matrices

This article studies multiple structural breaks in large contemporaneous covariance matrices of high-dimensional time series satisfying an approximate factor model. The breaks in the second-order moment structure of the common components are due to sudden changes in either factor loadings or covariance of latent factors, requiring appropriate transformation of the factor models to facilitate estimation of the (transformed) common factors and factor loadings via the classical principal component analysis. With the estimated factors and idiosyncratic errors, an easy-to-implement CUSUM-based detection technique is introduced to consistently estimate the location and number of breaks and correctly identify whether they originate in the common or idiosyncratic error components. The algorithms of Wild Binary Segmentation for Covariance (WBS-Cov) and Wild Sparsified Binary Segmentation for Covariance (WSBS-Cov) are used to estimate breaks in the common and idiosyncratic error components, respectively. Under some technical conditions, the asymptotic properties of the proposed methodology are derived with near-optimal rates (up to a logarithmic factor) achieved for the estimated breaks. Monte Carlo simulation studies are conducted to examine the finite-sample performance of the developed method and its comparison with other existing approaches. We finally apply our method to study the contemporaneous covariance structure of daily returns of S&P 500 constituents and identify a few breaks including those occurring during the 2007-2008 financial crisis and the recent coronavirus (COVID-19) outbreak. An R package "BSCOV" is provided to implement the proposed algorithms. for this article are available online.

Impact of Monetary Aggregates on Consumer Behavior: A Study on the Policy Response of the Federal Reserve against COVID-19

Consumers have tended to sharply decrease their spending during the COVID-19 pandemic due to pessimistic expectations related to the economic outlook, concerns about their jobs, and a decline in incomes. The Federal Reserve has taken several measures in response to the pandemic, resulting in increases in the money supply and asset sizes. This study aims to analyze the impact of monetary aggregates on consumer behavior before and after the pandemic by employing the bootstrap autoregressive distributed lag (ARDL) cointegration test with an exogenous structural break. The US money supply (M3) and total assets are used as dependent variables and consumer expenditure, consumer credit, and consumer sentiment are the independent variables. The data employed cover the period from January 2003 to August 2020. The results show cointegration relationships among consumer expenditure, the US money supply (M3), and total assets. The effect of the FED???s policy response on consumer behavior has strengthened after the pandemic.

Time-varying herding spillover for emerging countries: evidence from BRIC countries and Turkey

Purpose This study aims to investigate herding spillover in BRIC (Brazil, Russia, India and China) countries and Turkey under different regimes by using a time-varying approach. Design/methodology/approach The authors used the structural change model of Bai and Perron (1998). Findings The results indicate that there is an evidence of herding behaviour in the Chinese stock market in two different regimes. These regimes cover the recent global financial crisis and the period of Hong Kong protests. We also report the evidence of herding behaviour in the Turkish stock market in the regime covering the COVID-19 period. Findings of herding spillover show that there is a two-way herding among Russia and China during crises and high volatile regimes. Similarly, there exists a cross-country herding among Brazil and India during crisis regimes. Also, there is herding spillover from Turkey to Russia, China and Brazil during the global financial crisis, post-European debt crisis and COVID-19 periods respectively. Furthermore, it is also evident that there is a herding spillover from Russia and China to India during the period covering COVID-19. Originality/value To the best of the authors' knowledge, this is the first study that uses structural change approach to identify herding behaviour spillovers from the US stock market to BRIC countries and Turkey and to investigate the cross-country herding behaviour among BRIC countries and Turkey.

Integration of stock markets using autoregressive distributed lag bounds test approach

Financial integration plays a decisive role to the institutional investors for diversification of their investment portfolio(s). This research investigates the integration of selected stock markets (India, Australia, China, Spain, UK, and the USA) from different continents that are highly affected by COVID-19, employing the autoregressive distributed lag approach using daily data from 2 January 2011 to 7 May 2020. The outcomes show evidence of long and short-run integration among the markets. The rest of the markets are co-integrated with the markets of India, China, and UK. India has a long-run equilibrium with the USA and Spain, whereas China has a long-run association with Spain, and the UK has a long-run association with the USA. In short-run, India is positively influenced by the returns of rest of the markets, whereas all the markets under the study except USA influence China. Further, the UK's market is significantly inclined negatively by its own past innovations. © 2022 Inderscience Enterprises Ltd.. All rights reserved.

The impact of COVID-19 containment measures on changes in electricity demand

Emergency measures imposed by governments around the world have had massive impacts on the energy sector, resulting in dramatic reductions in total energy demand The New Zealand government introduced strict containment measures in response to the Covid-19 virus. We use an augmented auto-regressive-moving-average model to assess the impact of containment measures on wholesale electricity demand. The study spans the period 27 February 2020 to 23 February 2021. Results show that the Alert Level-4 lockdown had the largest, significant, and negative effect on electricity demand compared to other containment level measures. Specifically, Alert Level 4 resulted in a 12 % reduction in wholesale electricity demand. Structural breaks in the data are evident as containment progressed to Alert Level 1. This unprecedented experiment provides insights into underlying patterns of electricity demand, therefore, projection of economic activity. Furthermore, the analysis offers insights into the performance of the electricity market when both aggregate demand and the pattern of demand change in response to exogenous constraints. Finally, the outcomes of this analysis also provide a robust reference for other countries on how the New Zealand market performed.

Detecting time-changes in $ PM_{10} $ during Covid pandemic by means of an Ornstein Uhlenbeck type process.

Particulate matter with 10 micrometers or less in diameter ($ PM_{10} $) from several italian cities is modeled by means of a non homogeneous Ornstein Uhlenbeck process. Such model includes two deterministic time dependent functions in the infinitesimal moments to describe the presence of exogeneous terms in the typical dynamics of the phenomenon. An iterative estimating procedure combining the maximum likelihood estimation and a generalized method of moments is provided. A Quandt Likelihood Ratio test for detecting structural breaks in $ PM_{10} $ data, in the period from 1st January 2020 to 8th July 2020 which includes the first lockdown due to Covid pandemic, confirms the presence of time-changes. These results show that the lockdown made the air once again cleaner. It is then shown that our model and the associated estimation procedure, while not explicitly contemplating the presence of structural breaks in the time series, implicitly incorporates them in the time dependence of the functions in the infinitesimal moments of the underlying process.

COVID-19 and instability of stock market performance: evidence from the U.S.

The effect of COVID-19 on stock market performance has important implications for both financial theory and practice. This paper examines the relationship between COVID-19 and the instability of both stock return predictability and price volatility in the U.S over the period January 1st, 2019 to June 30th, 2020 by using the methodologies of Bai and Perron (Econometrica 66:47-78, 1998. 10.2307/2998540; J Appl Econo 18:1-22, 2003. 10.1002/jae.659), Elliot and Muller (Optimal testing general breaking processes in linear time series models. University of California at San Diego Economic Working Paper, 2004), and Xu (J Econ 173:126-142, 2013. 10.1016/j.jeconom.2012.11.001). The results highlight a single break in return predictability and price volatility of both S&P 500 and DJIA. The timing of the break is consistent with the COVID-19 outbreak, or more specifically the stock selling-offs by the U.S. senate committee members before COVID-19 crashed the market. Furthermore, return predictability and price volatility significantly increased following the derived break. The findings suggest that the pandemic crisis was associated with market inefficiency, creating profitable opportunities for traders and speculators. Furthermore, it also induced income and wealth inequality between market participants with plenty of liquidity at hand and those short of funds.

The only certainty is uncertainty: An analysis of the impact of COVID-19 uncertainty on regional stock markets.

Uncertainty surrounding COVID-19 is widespread. We investigate the timing and quantify the impact of COVID-19 related uncertainty on returns and volatility for regional market aggregates using ARCH/GARCH models. Drawing upon economic psychology, COVID-19 related uncertainty is measured by searches for information as reflected by Google search trends. Asian markets are more resilient than others. Latin American markets are most impacted in terms of returns and volatility. For most regions, there is evidence of an increasing impact of COVID-19 related uncertainty which dissipates as the crisis evolves. We confirm that Google search trends capture uncertainty by comparing this measure against alternative uncertainty measures.

Nowcasting unemployment insurance claims in the time of COVID-19.

Near-term forecasts, also called nowcasts, are most challenging but also most important when the economy experiences an abrupt change. In this paper, we explore the performance of models with different information sets and data structures in order to best nowcast US initial unemployment claims in spring of 2020 in the midst of the COVID-19 pandemic. We show that the best model, particularly near the structural break in claims, is a state-level panel model that includes dummy variables to capture the variation in timing of state-of-emergency declarations. Autoregressive models perform poorly at first but catch up relatively quickly. The state-level panel model, exploiting the variation in timing of state-of-emergency declarations, also performs better than models including Google Trends. Our results suggest that in times of structural change there is a bias-variance tradeoff. Early on, simple approaches to exploit relevant information in the cross sectional dimension improve forecasts, but in later periods the efficiency of autoregressive models dominates.

Have COVID-19-Related Economic Shocks Affected the Health Levels of Individuals in the United States and the United Kingdom?

This paper introduces a health index for measuring the health level of societies during the lockdown era, i. e., for the period from March 21, 2020 to April 7, 2020. For this purpose, individual-level survey data from the Global Behaviors and Perceptions in the COVID-19 Pandemic dataset are considered. We focus on cases in the United States and the United Kingdom, and the data come from 11,270 and 11,459 respondents, respectively. We then use unit root tests with structural breaks to examine whether COVID-19-related economic shocks significantly affect the health levels of the United States and the United Kingdom. The empirical results indicate that the health levels in the United States and the United Kingdom are not significantly affected by the COVID-19-related economic shocks. The evidence shows that government directives (such as lockdowns) did not significantly change the health levels of these societies.