|
on Econometric Time Series |
| By: | Dan Li; Adam Clements; Christopher Drovandi |
| Abstract: | This paper exploits the advantages of sequential Monte Carlo (SMC) to develop parameter estimation and model selection methods for GARCH (Generalized AutoRegressive Conditional Heteroskedasticity) style models. This approach provides an alternative method for quantifying estimation uncertainty relative to classical inference. We demonstrate that even with long time series, the posterior distribution of model parameters are non-normal, highlighting the need for a Bayesian approach and an efficient posterior sampling method. Efficient approaches for both constructing the sequence of distributions in SMC, and leave-one-out cross-validation, for long time series data are also proposed. Finally, we develop an unbiased estimator of the likelihood for the Bad Environment-Good Environment model, a complex GARCH-type model, which permits exact Bayesian inference not previously available in the literature. |
| Date: | 2019–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1906.03828&r=all |
| By: | Feiyu Jiang; Dong Li; Ke Zhu |
| Abstract: | This paper considers a semiparametric generalized autoregressive conditional heteroscedastic (S-GARCH) model, which has a smooth long run component with unknown form to depict time-varying parameters, and a GARCH-type short run component to capture the temporal dependence. For this S-GARCH model, we first estimate the time-varying long run component by the kernel estimator, and then estimate the non-time-varying parameters in short run component by the quasi maximum likelihood estimator (QMLE). We show that the QMLE is asymptotically normal with the usual parametric convergence rate. Next, we provide a consistent Bayesian information criterion for order selection. Furthermore, we construct a Lagrange multiplier (LM) test for linear parameter constraint and a portmanteau test for model diagnostic checking, and prove that both tests have the standard chi-squared limiting null distributions. Our entire statistical inference procedure not only works for the non-stationary data, but also has three novel features: first, our QMLE and two tests are adaptive to the unknown form of the long run component; second, our QMLE and two tests are easy-to-implement due to their related simple asymptotic variance expressions; third, our QMLE and two tests share the same efficiency and testing power as those in variance target method when the S-GARCH model is stationary. |
| Date: | 2019–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1907.04147&r=all |
| By: | Xinyu Song |
| Abstract: | We provide a novel method for large volatility matrix prediction with high-frequency data by applying eigen-decomposition to daily realized volatility matrix estimators and capturing eigenvalue dynamics with ARMA models. Given a sequence of daily volatility matrix estimators, we compute the aggregated eigenvectors and obtain the corresponding eigenvalues. Eigenvalues in the same relative magnitude form a time series and the ARMA models are further employed to model the dynamics within each eigenvalue time series to produce a predictor. We predict future large volatility matrix based on the predicted eigenvalues and the aggregated eigenvectors, and demonstrate the advantages of the proposed method in volatility prediction and portfolio allocation problems. |
| Date: | 2019–07 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1907.01196&r=all |
| By: | Nghia Nguyen; Minh-Ngoc Tran; David Gunawan; R. Kohn |
| Abstract: | Stochastic Volatility (SV) models are widely used in the financial sector while Long Short-Term Memory (LSTM) models have been successfully used in many large-scale industrial applications of Deep Learning. Our article combines these two methods non trivially and proposes a model for capturing the dynamics of financial volatility process, which we call the LSTM-SV model. The proposed model overcomes the short-term memory problem in conventional SV models, is able to capture non-linear dependence in the latent volatility process, and often has a better out-of-sample forecast performance than SV models. The conclusions are illustrated through simulation studies and applications to three financial time series datasets: US stock market weekly index SP500, Australian stock weekly index ASX200 and Australian-US dollar daily exchange rates. We argue that there are significant differences in the underlying dynamics between the volatility process of SP500 and ASX200 datasets and that of the exchange rate dataset. For the stock index data, there is strong evidence of long-term memory and non-linear dependence in the volatility process, while this is not the case for the exchange rates. An user-friendly software package together with the examples reported in the paper are available at https://github.com/vbayeslab. |
| Date: | 2019–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1906.02884&r=all |
| By: | Gilles de Truchis; Elena Ivona Dumitrescu; Florent Dubois |
| Abstract: | In this paper we propose a local Whittle estimator of stationary bivariate unbalanced fractional cointegration systems. Unbalanced cointegration refers to the situation where the observables have different integration orders, but their filtered versions have equal integration orders and are cointegrated in the usual sense. Based on the frequency domain representation of the unbalanced version of Phillips’ triangular system, we develop a semiparametric approach to jointly estimate the unbalance parameter, the long run coefficient, and the integration orders of the regressand and cointegrating errors. The paper establishes the consistency and asymptotic normality of this estimator. We find a peculiar rate of convergence for the unbalance estimator (possibly faster than root-n) and a singular joint limiting distribution of the unbalance and long-run coefficients. Its good finite-sample properties are emphasized through Monte Carlo experiments. We illustrate the relevance of the developed estimator for financial data in an empirical application to the information flowing between the crude oil spot and CME-NYMEX markets. |
| Keywords: | Unbalanced cointegration, Long memory, Stationarity, Local Whittle likelihood |
| JEL: | C22 G10 |
| Date: | 2019 |
| URL: | http://d.repec.org/n?u=RePEc:drm:wpaper:2019-15&r=all |
| By: | Gilles de Truchis; Elena Ivona Dumitrescu |
| Abstract: | We discuss cointegration relationships when covariance stationary observables exhibit unbalanced integration orders. Least squares type estimates of the long run coefficient are expected to converge either to 0 or to infinity if one does not account for the true unknown unbalance parameter. We propose a class of narrow-band weighted non-linear least squares estimators of these two parameters and analyze its asymptotic properties. The limit distribution is shown to be Gaussian, albeit singular, and it covers the entire stationary region in the particular case of the generalized non-linear least squares estimator, thereby allowing for straightforward statistical inference. A Monte Carlo study documents the good finite sample properties of our class of estimators. They are further used to provide new perspectives on the risk-return relationship on financial stock markets. In particular, we find that the variance risk premium estimated in an appropriately rebalanced cointegration system is a better return predictor than existing risk premia measures. |
| Keywords: | Unbalanced cointegration, Long memory, Stationarity, Generalized Least Squares, Nonlinear Least Squares |
| JEL: | C22 G10 |
| Date: | 2019 |
| URL: | http://d.repec.org/n?u=RePEc:drm:wpaper:2019-14&r=all |
| By: | Z. Keskin; T. Aste |
| Abstract: | Information transfer between time series is calculated by using the asymmetric information-theoretic measure known as transfer entropy. Geweke's autoregressive formulation of Granger causality is used to find linear transfer entropy, and Schreiber's general, non-parametric, information-theoretic formulation is used to detect non-linear transfer entropy. We first validate these measures against synthetic data. Then we apply these measures to detect causality between social sentiment and cryptocurrency prices. We perform significance tests by comparing the information transfer against a null hypothesis, determined via shuffled time series, and calculate the Z-score. We also investigate different approaches for partitioning in nonparametric density estimation which can improve the significance of results. Using these techniques on sentiment and price data over a 48-month period to August 2018, for four major cryptocurrencies, namely bitcoin (BTC), ripple (XRP), litecoin (LTC) and ethereum (ETH), we detect significant information transfer, on hourly timescales, in directions of both sentiment to price and of price to sentiment. We report the scale of non-linear causality to be an order of magnitude greater than linear causality. |
| Date: | 2019–06 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1906.05740&r=all |