nep-ets New Economics Papers
on Econometric Time Series
Issue of 2020‒01‒27
fifteen papers chosen by
Jaqueson K. Galimberti
Auckland University of Technology

  1. Capturing Macroeconomic Tail Risks with Bayesian Vector Autoregressions By Andrea Carriero; Todd E. Clark; Massimiliano Marcellino
  2. The use of BVARs in the analysis of emerging economies By Ángel Estrada; Luis Guirola; Iván Kataryniuk; Jaime Martínez-Martín
  3. A Higher-Order Correct Fast Moving-Average Bootstrap for Dependent Data By Davide La Vecchia; Alban Moor; Olivier Scaillet
  4. "The Squawk Bot": Joint Learning of Time Series and Text Data Modalities for Automated Financial Information Filtering By Xuan-Hong Dang; Syed Yousaf Shah; Petros Zerfos
  5. Modeling Azerbaijan’s Inflation and Output Using a Factor-Augmented Vector Autoregressive (FAVAR) Model By Vugar Rahimov; Nijat Guliyev; Vugar Ahmadov
  6. Shock and Volatility Spillovers between Crude Oil Price and Stock Returns: Evidence for Thailand By Theplib, Krit; Sethapramote, Yuthana; Jiranyakul, Komain
  7. The Financial Development-Environmental Degradation Nexus in the United Arab Emirates: The Importance of Growth, Globalization and Structural Breaks By Shahbaz, Muhammad; Haouas, Ilham; Sohag, Kazi; Ozturk, Ilhan
  8. "The Empirics of Canadian Government Securities Yields" By Tanweer Akram; Anupam Das
  9. Comovement and Instability in Cryptocurrency Markets By De Pace, Pierangelo; Rao, Jayant
  10. Trends and cycles under changing economic conditions By Cláudia Duarte; José R. Maria; Sharmin Sazedj
  11. Nowcasting East German GDP growth: A MIDAS approach By Claudio, João C.; Heinisch, Katja; Holtemöller, Oliver
  12. DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News By Xinyi Li; Yinchuan Li; Hongyang Yang; Liuqing Yang; Xiao-Yang Liu
  13. Stock Prices, Exchange Rates and Portfolio Equity Flows: A Toda-Yamamoto Panel Causality Test By Andriansyah, Andriansyah; Messinis, George
  14. The Relationship Between USD/EUR Official Exchange Rates And Implied Exchange Rates From The Bitcoin Market By Hélder Sebastião; Pedro Godinho
  15. Granger Predictability of Oil Prices after the Great Recession By Szilard Benk; Max Gillman

  1. By: Andrea Carriero; Todd E. Clark; Massimiliano Marcellino (European University Institute; Universität Commerciale Luigi Bocconi; National Bureau of Economic Research; Centre for Economic Policy Research (CEPR); Universität degli Studi di Firenze; Bocconi University)
    Abstract: A rapidly growing body of research has examined tail risks in macroeconomic outcomes. Most of this work has focused on the risks of significant declines in GDP, and has relied on quantile regression methods to estimate tail risks. In this paper we examine the ability of Bayesian VARs with stochastic volatility to capture tail risks in macroeconomic forecast distributions and outcomes. We consider both a conventional stochastic volatility specification and a specification featuring a common volatility factor that is a function of past financial conditions. Even though the conditional predictive distributions from the VAR models are symmetric, our estimated models featuring time-varying volatility yield more time variation in downside risk as compared to upside risk—a feature highlighted in other work that has advocated for quantile regression methods or focused on asymmetric conditional distributions. Overall, the BVAR models perform comparably to quantile regression for estimating tail risks, with, in addition, some gains in standard point and density forecasts.
    Keywords: forecasting; downside risk; asymmetries
    JEL: C53 E17 E37 F47
    Date: 2020–01–16
  2. By: Ángel Estrada (Banco de España); Luis Guirola (Banco de España); Iván Kataryniuk (Banco de España); Jaime Martínez-Martín (Banco de España)
    Abstract: The process of internationalisation that many Spanish banks have embarked upon in recent years has resulted in the need for much closer monitoring of the economies in which they are present, especially by a supervisory body such as the Banco de España. In this paper, we present a comprehensive theoretical and empirical modelling approach, developing a set of …five country-specific structural BVARs for Brazil, Mexico, Turkey, Chile and Peru, the economies representing the largest exposures of Spanish banks to the emerging markets. The results obtained show that our modelling strategy provides useful tools to: (i) analyse the structural shocks that underlie their recent macroeconomic behaviour; (ii) study the impact of certain decisions of policymakers on GDP, inflation and other variables; and (iii) carry out accurate conditional and unconditional projections two years ahead of the most policy-relevant variables. These projections, together with the “analyst’s judgement”, constitute the bulk of our assessment of the future behaviour of these economies.
    Keywords: structural analysis, vector autoregressions, bayesian estimation, sign restrictions
    JEL: E32 C22 E27
    Date: 2020–01
  3. By: Davide La Vecchia; Alban Moor; Olivier Scaillet
    Abstract: We develop and implement a novel fast bootstrap for dependent data. Our scheme is based on the i.i.d. resampling of the smoothed moment indicators. We characterize the class of parametric and semi-parametric estimation problems for which the method is valid. We show the asymptotic refinements of the proposed procedure, proving that it is higher-order correct under mild assumptions on the time series, the estimating functions, and the smoothing kernel. We illustrate the applicability and the advantages of our procedure for Generalized Empirical Likelihood estimation. As a by-product, our fast bootstrap provides higher-order correct asymptotic confidence distributions. Monte Carlo simulations on an autoregressive conditional duration model provide numerical evidence that the novel bootstrap yields higher-order accurate confidence intervals. A real-data application on dynamics of trading volume of stocks illustrates the advantage of our method over the routinely-applied first-order asymptotic theory, when the underlying distribution of the test statistic is skewed or fat-tailed.
    Date: 2020–01
  4. By: Xuan-Hong Dang; Syed Yousaf Shah; Petros Zerfos
    Abstract: Multimodal analysis that uses numerical time series and textual corpora as input data sources is becoming a promising approach, especially in the financial industry. However, the main focus of such analysis has been on achieving high prediction accuracy while little effort has been spent on the important task of understanding the association between the two data modalities. Performance on the time series hence receives little explanation though human-understandable textual information is available. In this work, we address the problem of given a numerical time series, and a general corpus of textual stories collected in the same period of the time series, the task is to timely discover a succinct set of textual stories associated with that time series. Towards this goal, we propose a novel multi-modal neural model called MSIN that jointly learns both numerical time series and categorical text articles in order to unearth the association between them. Through multiple steps of data interrelation between the two data modalities, MSIN learns to focus on a small subset of text articles that best align with the performance in the time series. This succinct set is timely discovered and presented as recommended documents, acting as automated information filtering, for the given time series. We empirically evaluate the performance of our model on discovering relevant news articles for two stock time series from Apple and Google companies, along with the daily news articles collected from the Thomson Reuters over a period of seven consecutive years. The experimental results demonstrate that MSIN achieves up to 84.9% and 87.2% in recalling the ground truth articles respectively to the two examined time series, far more superior to state-of-the-art algorithms that rely on conventional attention mechanism in deep learning.
    Date: 2019–12
  5. By: Vugar Rahimov (Central Bank of the Republic of Azerbaijan); Nijat Guliyev (Central Bank of the Republic of Azerbaijan); Vugar Ahmadov (Central Bank of the Republic of Azerbaijan)
    Abstract: In this study, we build and use a factor-augmented vector autoregressive (FAVAR) model to forecast inflation and output in Azerbaijan. The FAVAR model is particularly effective in data-rich environments, alleviating the curse of dimensionality of the standard VAR model and handling omitted variable bias. Using 77 variables for factor extraction and quarterly data for the period 2003 to 2018, we build several multivariate models, including a FAVAR model, and compare their performance with that of a benchmark univariate model. Our findings show that almost all of the multivariate models underperform in comparison with the univariate model. This result is in line with the literature, which finds that simple models are better forecasters of some macroeconomic variables, especially inflation. We acknowledge that the results might be affected by the relatively short length of the sample period and existence of irregularities in the data.
    Date: 2020–01–21
  6. By: Theplib, Krit; Sethapramote, Yuthana; Jiranyakul, Komain
    Abstract: This paper employs a bivariate BEKK-GARCH(1,1) model to examine shock and volatility spillovers between crude oil and stock markets by taking into account the impact of the 2008 global financial crisis. Daily data from crude oil market and the Thai stock market during February 6, 2004 and September 14, 2015 are used in the analyses. The whole sample is divided into the pre- and post- crisis periods. The results show that there are no spillover effects between oil price and stock returns in the pre-crisis period. In the post-crisis period, there are unilateral spillover effects from oil price to some equity sector returns. In the market level, there are unilateral spillovers of shock and volatility from oil price to stock market return. The findings in this paper are crucial for financial market participations to understand shock and volatility transmissions from oil to stock markets such that portfolio management should take into account the presence of oil price risk.
    Keywords: Stock returns, oil price shock, volatility spillover, bivariate GARCH
    JEL: G1 G12 Q43
    Date: 2020–01
  7. By: Shahbaz, Muhammad; Haouas, Ilham; Sohag, Kazi; Ozturk, Ilhan
    Abstract: This article revisits the nexus between financial development and environmental degradation by incorporating economic growth, electricity consumption and economic globalization in the CO2 emissions function for the period 1975QI-2014QIV in the United Arab Emirates. We apply structural break and cointegration tests to examine unit root and cointegration between the variables. Further, the article also uses the Toda-Yamamoto causality test to investigate the causal relationship between the variables and tests the linkages of the robustness of causality by following the innovative accounting approach. Our empirical analysis shows cointegration between the series. Financial development increases CO2 emissions. Economic growth is positively linked with environmental degradation. Electricity consumption improves environmental quality. Economic globalization affects CO2 emissions negatively. The relationship between financial development and CO2 emissions is U-shaped and inverted N-shaped. Further, financial development leads to environmental degradation and environmental degradation in turn leads to financial development in the Granger sense.
    Keywords: Financial development, environment, growth, electricity, globalization
    JEL: Q5
    Date: 2020–01–01
  8. By: Tanweer Akram; Anupam Das
    Abstract: Keynes argued that the short-term interest rate is the main driver of the long-term interest rate. This paper empirically models the relationship between short-term interest rates and long-term government securities yields in Canada, after controlling for other important financial variables. The statistical analysis uses high-frequency daily data from 1990 to 2018. It applies both the cointegration technique and Granger causality within the vector error correction (VEC) framework. The empirical results suggest that the action of the monetary authority is an important determinant of Canadian government securities yields, which supports the Keynesian perspective. These findings have important implications for investors, financial analysts, and policymakers.
    Keywords: : Canadian Government Bond Yields; Long-Term Interest Rate; Short-Term Interest Rate; Monetary Policy; Cointegration; Granger Causality
    JEL: E43 E50 E60 G10 G12
  9. By: De Pace, Pierangelo (Pomona College); Rao, Jayant (Claremont Graduate University)
    Abstract: We analyze the correlations of daily price returns for nine major cryptocurrencies between April 2013 and November 2018 and estimate their evolution using bivariate and multivariate modelling approaches. We detect pronounced time variation and fid these correlations to be generally increasing between early 2017 and late 2018. We then adopt a right-tail variation of the Augmented Dickey-Fuller unit root test to identify and date-stamp periods of mildly explosive behavior (statistical instability) in the time series of the Network Value to Transactions (NVT) ratio (a measure of the dollar value of cryptocurrency transaction activity relative to its network value) of six cryptocurrencies. We show statistically significant evidence of mild explosiveness in all of them. At the end of 2017 and in 2018, several major cryptocurrencies experience significant (often simultaneous) instability associated with rising NVT ratios. Instability is a steady feature of cryptocurrency markets.
    Keywords: Asset Pricing, Cryptocurrencies, Comovement, Bubbles, Mild Explosiveness
    Date: 2020–01–13
  10. By: Cláudia Duarte; José R. Maria; Sharmin Sazedj
    Abstract: The identification of trends and cycles is often a challenging task under sizeable changes in economic conditions. We solve this problem with a flexible unobserved components model, featuring an (unobserved) evolving trend inflation drift to cope with distinct inflationary periods and data-driven low frequency movements to partly influence ex ante key trend components. In the long run the model displays a balanced growth path, in addition to other standard restrictions (e.g. nil output and labour market slacks). We estimate the model with Bayesian techniques using two datasets, one for the euro area and another for Portugal, two economies displaying distinct macroeconomic environments over the last four decades, and conclude that Portugal witnessed (i) a steeper deceleration of potential output, since the 1990s; (ii) a pervasively higher volatility in labour and product markets; and (iii) a long-lived interruption in convergence trends after the 2000s. Results are robust to sensitivity analyses. Parameter uncertainty is, nevertheless, significant.
    JEL: C11 C30 E32
    Date: 2019
  11. By: Claudio, João C.; Heinisch, Katja; Holtemöller, Oliver
    Abstract: Economic forecasts are an important element of rational economic policy both on the federal and on the local or regional level. Solid budgetary plans for government expenditures and revenues rely on efficient macroeconomic projections. However, official data on quarterly regional GDP in Germany are not available, and hence, regional GDP forecasts do not play an important role in public budget planning. We provide a new quarterly time series for East German GDP and develop a forecasting approach for East German GDP that takes data availability in real time and regional economic indicators into account. Overall, we find that mixed-data sampling model forecasts for East German GDP in combination with model averaging outperform regional forecast models that only rely on aggregate national information.
    Keywords: business surveys,East Germany,MIDAS model,nowcasting
    JEL: C22 C52 C53 E37 R11
    Date: 2019
  12. By: Xinyi Li; Yinchuan Li; Hongyang Yang; Liuqing Yang; Xiao-Yang Liu
    Abstract: Stock price prediction is important for value investments in the stock market. In particular, short-term prediction that exploits financial news articles is promising in recent years. In this paper, we propose a novel deep neural network DP-LSTM for stock price prediction, which incorporates the news articles as hidden information and integrates difference news sources through the differential privacy mechanism. First, based on the autoregressive moving average model (ARMA), a sentiment-ARMA is formulated by taking into consideration the information of financial news articles in the model. Then, an LSTM-based deep neural network is designed, which consists of three components: LSTM, VADER model and differential privacy (DP) mechanism. The proposed DP-LSTM scheme can reduce prediction errors and increase the robustness. Extensive experiments on S&P 500 stocks show that (i) the proposed DP-LSTM achieves 0.32% improvement in mean MPA of prediction result, and (ii) for the prediction of the market index S&P 500, we achieve up to 65.79% improvement in MSE.
    Date: 2019–12
  13. By: Andriansyah, Andriansyah; Messinis, George
    Abstract: Purpose – The purpose of this paper is to develop a new framework to test the hypothesis that portfolio model predicts a negative correlation between stock prices and exchange rates in a trivariate transmission channel for foreign portfolio equity investment. Design/methodology/approach – This paper utilizes panel data for eight economies to extend the Dumitrescu and Hurlin (2012) Granger non-causality test of heterogeneous panels to a trivariate model by integrating the Toda and Yamamoto (1995) approach to Granger causality. Findings – The evidence suggests that stock prices Granger-cause exchange rates and portfolio equity flows Granger-cause exchange rates. However, the overall panel evidence casts doubt on the explicit trivariate model of portfolio balance model. The study shows that Indonesia may be the only case where stock prices affect exchange rates through portfolio equity flows. Research limitations/implications – The proposed test does not account for potential asymmetries or structural shifts associated with the crisis period. To isolate the impact of the Asian Financial crisis, this paper rather splits the sample period into two sub-periods: pre- and post-crises. The sample period and countries are also limited due to the use of the balance of payment statistics. Practical implications – The study casts doubt on the maintained hypothesis of a trivariate transmission channel, as posited by the portfolio model. Policy makers of an economy may integrate capital market and fiscal policies in order to maintain stable exchange rate. Originality/value – This paper integrates a portfolio equity inflow variable into a single framework with stock price and exchange rate variables. It extends the Dumitrescu and Hurlin’s (2012) bivariate stationary Granger non-causality test in heterogeneous panels to a trivariate setting in the framework of Toda and Yamamoto (1995).
    Keywords: Granger causality, Exchange rates, Stock prices, Heterogeneous panels, Portfolio equity
    JEL: F31 G14 G15
    Date: 2019–02–22
  14. By: Hélder Sebastião (Centre for Business and Economics CeBER and Faculty of Economics, University of Coimbra); Pedro Godinho (Centre for Business and Economics CeBER and Faculty of Economics, University of Coimbra)
    Abstract: We examine the long- and short-run relationships between USD/EUR official rates and implicit exchange rates, through Bitcoin as a currency vehicle, over the period from March 07, 2016 to November 22, 2019. The results show that the two exchange rates are cointegrated and that the cointegrating vector is not statistically different from the theoretical one that results from the law of one price. In the short-run, the implied rate Granger-causes the official reference rate. Our main conclusion is that Bitcoin USD and EUR prices incorporate fundamental information from the USD/EUR official exchange rate.
    Keywords: Bitcoin, USD/EUR, Exchange rates, Cointegration, Forecasting.
    JEL: G14 G15 G23
    Date: 2020–02
  15. By: Szilard Benk; Max Gillman
    Abstract: Real oil prices surged from 2009 through 2014, comparable to the 1970's oil shock period. Standard explanations based on monopoly markup fall short since inflation remained low after 2009. This paper contributes strong evidence of Granger (1969) predictability of nominal factors to oil prices, using one adjustment to monetary aggregates. This adjustment is the subtraction from the monetary aggregates of the 2008-2009 Federal Reserve borrowing of reserves from other Central Banks (Swaps), made after US reserves turned negative. This adjustment is key in that Granger predictability from standard monetary aggregates is found only with the Swaps subtracted.
    Keywords: oil price shocks; Granger predictability; monetary base; M1 Divisia; Swaps; inflation;
    JEL: Q43 E51 E52
    Date: 2019–12

This nep-ets issue is ©2020 by Jaqueson K. Galimberti. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.