Hong Miao - Academia.edu (original) (raw)

Papers by Hong Miao

Energy Economics, 2021

We propose two ways to improve the forecasting accuracy of a focused time-delay neural network (F... more We propose two ways to improve the forecasting accuracy of a focused time-delay neural network (FTDNN) that forecasts the term structure of crude oil futures. Our results show that a convergence based FTDNN makes consistently more accurate predictions than the fixed-epoch FTDNN in Barunik and Malinska (2016). Further, we suggest using basis splines (B-splines), instead of Nelson-Siegel functions, to fit the term structure curves. The empirical results show that the B-spline expansions lead to consistently better 1 and 3 months ahead predictions compared to the convergence based FTDNN. We also explore conditions under which the B-spline based approach may be better for longer-term predictions.

Journal of Futures Markets, 2021

 Christoffersen et al. (2019): during the post financialization period (2004-2014), pairwise cor... more  Christoffersen et al. (2019): during the post financialization period (2004-2014), pairwise correlations between individual commodity futures volatility are much higher and much more integrated with significant common factors  commodity futures' returns appear much more segmented with almost no significant common factors.  The popular view on the financialization effect immediately implies that the concerned increases in commodity price volatility should be across the board and a long-lasting phenomenon by its nature.  Should be revealed by the network structure of commodity volatility spillovers. Methodology  Baruník and Křehlík (2018) is an extension of Diebold and Yilmaz's (2014) approach to measure the magnitude of spillover/connectedness effect in short-, medium-and longterm cycles.  Demirer et al. (2018) incorporate the least absolute shrinkage and selection operator (LASSO) technique to VAR models in high-dimensional environments.

Energy Economics, 2017

This paper identi…es factors that are in ‡uential in forecasting crude oil prices. We consider si... more This paper identi…es factors that are in ‡uential in forecasting crude oil prices. We consider six categories of factors (supply, demand, …nancial market, commodities market, speculative, and geopolitical) and test their signi…cance in the context of estimating various forecasting models. We …nd that the Least Absolute Shrinkage and Selection Operator (LASSO) regression method provides signi…cant improvements in the forecasting accuracy of prices compared to alternative benchmarks. Relative to the no-change and future-based models, LASSO forecasts at the 8-step ahead horizon yield signi…cant reductions in Mean Squared Prediction Error (MSPE), with MSPE ratios of 0.873 and 0.898, respectively. We also document substantial improvements in forecasting performance of the factor-based model that employs only a subset of variables chosen by LASSO. Finally, the time-varying nature of the relationship between factors and oil prices are used to explain recent movements in crude oil prices.

Journal of Futures Markets, 2017

Statistics of Crude Oil Inventory Announcements (6/16/03-12/30/11) This table reports the summary... more Statistics of Crude Oil Inventory Announcements (6/16/03-12/30/11) This table reports the summary statistics on EIA crude oil inventory changes.

Includes bibliographical references (pages 26-28).Published as: Does the price of crude oil respo... more Includes bibliographical references (pages 26-28).Published as: Does the price of crude oil respond to macroeconomic news?, Journal of Futures Markets, vol.32, no. 6, pp.536-559, June 2012, https://doi.org/10.1002/fut.20525.A recent study indicates that the daily price of crude oil is mostly unresponsive to macroeconomic news, at times exhibiting response-coefficients that carry the “wrong sign”. The study concludes that the price of crude oil is predetermined to macro aggregates, and hence determined in a flow demand and flow supply framework. We make the economic argument that inferences on commodity price determination should be drawn from news responses only after the standard tests are subject to inventory (or stock) controls. Using both daily and intraday data for crude oil, and using rudimentary tools to isolate perceived inventory levels, we test for the stock-flow hypothesis for crude oil. We find only weak evidence on the role of inventory levels for crude oil. We also ass...

Prices for some real world tradable assets, for instance natural gas and oil, are correlated, and... more Prices for some real world tradable assets, for instance natural gas and oil, are correlated, and the price dynamics for those assets are di¤erent in di¤erent economic environments. In this paper we extend the mean reverting model to multi-assets and model correlation between prices. Our model also allows the means and the mean reverting factors to switch between di¤erent regimes by including a Hidden Markov chain which models the di¤erent economic environments, or "states of the world". We then obtain approximate estimates for the parameters by applying …lters and the EM algorithm. Approximate derivative prices are also given.

Journal of Banking & Finance, 2015

We compare clientele and information share in weekly-(Weeklys) and monthly-expiring options (Mont... more We compare clientele and information share in weekly-(Weeklys) and monthly-expiring options (Monthlys) on the S&P 500 index. Striking dissimilarities between the two instruments are found, most apparent being the much smaller trade size and substantially higher implied volatility in Weeklys, consistent with both speculation and event trading. Additionally, the price discovery contribution of Weeklys, albeit modest when compared to the underlying index itself, is substantially larger than that of Monthlys. The cumulative evidence points to an increasingly segmented options market. Thus, studies employing only standard options to investigate price discovery will likely underestimate the informational role of options.

To describe the complex behavior of energy prices, we propose a stochastic volatility model, wher... more To describe the complex behavior of energy prices, we propose a stochastic volatility model, where we allow the volatility to follow different dynamics in different states of the world. The dynamics of the “states of the world”, for example a “good ” or “bad ” economic environment, or an “on-peak ” or “off-peak ” time for electricity, are represented by a Markov Chain. We obtain closed form estimates for all the parameters by using Filtering and the EM algorithm. In addition, we discuss the pricing of derivative contracts on assets whose dynamics follow this stochastic process, and possible extensions of our model. 1

Pacific-Basin Finance Journal, 2017

The introduction of stock index futures in China in 2010 marked an important development in the c... more The introduction of stock index futures in China in 2010 marked an important development in the country's financial markets. It was however not without controversy as regulators blamed the futures market for its role in the stock market crash in 2015. This paper examines the intraday price discovery and volatility spillover relationship between the CSI 300 equity index and index futures in China. Results from the study, covering the period 2010-2015, reveal that index futures plays a dominant role in contributing towards price discovery, with an average yearly information share of about 67%. The price leadership of the futures market, although found to be strong, is diminished in the presence of stringent regulatory trading curbs that were put in place as a response to the crisis. Furthermore, investigation into volatility spillover documents significant return and volatility shocks transmitted from the stock market to the futures market. The evidence, which contradicts regulatory claims, is explained in the context of the unique institutional trading structure in China.

Statistics & Risk Modeling, 2017

We introduce a functional factor model to investigate the dependence of cumulative return curves ... more We introduce a functional factor model to investigate the dependence of cumulative return curves of individual assets on the market and other factors. We propose a new statistical test to determine whether the dependence in two sample periods are equal. The statistical properties of the test are established by asymptotic theory and simulations. We apply this test to study the impact of the recent financial crisis and trends in oil price on individual stock and sector ETFs. Our analysis reveals the significance of the daily oil futures curves and their different impact on individual stocks and sector ETFs. It also shows that the functional approach has an information content different from that obtained from scalar factor models for point-to-point returns.

Journal of Financial Econometrics, 2017

Motivated by testing the significance of risk factors for a cross-section of returns, we develop ... more Motivated by testing the significance of risk factors for a cross-section of returns, we develop an inferential framework which involves function-on-scalar regression. Asymptotic theory is developed assuming the factors form a weakly dependent vector-valued time series, and the regression errors are weakly dependent functions. To accommodate the empirical behavior of the cross-section of returns and of the factors, we allow both the factors and the error functions can exhibit mild departures from stationarity. This requires new asymptotic theory which leads to several tests for the significance of function-valued regression coefficients. The new approach to the study of the significance of risk factors for a cross-section of returns complements the established Fama-French approach based on portfolio construction. It is more suitable if the statistical significance of the risk factors is to be rigorously controlled.

Journal of Business & Financial Affairs, 2013

High-Frequency and intraday financial data in general, have been an important focus of research i... more High-Frequency and intraday financial data in general, have been an important focus of research in finance, econometrics and statistics for over two decades. There are mainly two streams of studies in this area: 1) time series properties at tick by tick or fixed high frequency resolution, 2) inference based on diffusion processes. The distinction is not sharp. The focus of the statistical analysis has been on building of time series models at fine resolution, possibly at non-evenly spaced times, or on estimating quantities, i.e. the noise covariance’s, implied by the continuous time financial theory.

Energy Economics, 2016

This paper examines the information content of risk-neutral moments to explain crude oil futures ... more This paper examines the information content of risk-neutral moments to explain crude oil futures returns. Implied volatility and higher moments are extracted from observed crude oil option prices using a model-free implied volatility framework and the Black-Scholes model. We …nd a tenuous and time-varying association between returns and implied volatility and its innovations. Speci…cally, changes in implied volatility are found to be meaningfully associated with crude returns only over the period spanning the recent …nancial crisis. The results lead us to conclude that crude oil prices are determined primarily in a ‡ow demand/supply environment. Finally, we document that oil risk is priced into the cross-section of stock returns in the oil and transportation sectors.

SSRN Electronic Journal, 2015

Higher default probabilities are associated with lower future stock returns. The anomaly cannot b... more Higher default probabilities are associated with lower future stock returns. The anomaly cannot be explained by strategic shareholder actions, traditional risk factors, characteristics, or mispricing, but, instead, is consistent with a risk-shifting hypothesis. Consistent with the risk-shifting hypothesis, we find that distressed firms tend to overinvest, destroy value, and exhaust their cash flows. Effects are concentrated in firms with wide credit spreads, firms with no convertible debt, and in cases where CEOs receive above-average equity-based compensation. As default risk rises, credit spreads rise, equity betas fall, and equity returns fall.

Quantitative Finance, 2009

We have developed a regime switching framework to compute the Value at Risk and Expected Shortfal... more We have developed a regime switching framework to compute the Value at Risk and Expected Shortfall measures. Although Value at Risk as a risk measure has been criticized by some researchers for lack of subadditivity, it is still a central tool in banking regulations and internal risk management in the …nance industry. In contrast, Expected Shortfall (ES) is coherent and convex, so it is a better measure of risk than Value at Risk. Expected Shortfall is widely used in the insurance industry and has the potential to replace Value at Risk as a standard risk measure in the near future. We have proposed regime switching models to measure value at risk and expected shortfall for a single …nancial asset as well as …nancial portfolios. Our models capture the volatility clustering phenomenon and variance independent variation in the higher moments by assuming the returns follow Student's t-distributions.

Journal of Futures Markets, 2013

ABSTRACT This study examines the influence of macroeconomic news on price discontinuities in the ... more ABSTRACT This study examines the influence of macroeconomic news on price discontinuities in the S&P 500 index futures. Results document a strong association between macro news and price jumps. Over three-fourths of the price jumps between 8:30 am and 8:35 am and over three-fifths of the jumps between 10:00 am and 10:05 am are related to news released at 8:30 am and 10:30 am, respectively. Notably, among several types of news releases considered, Non-farm Payroll and Consumer Confidence are found to be significantly related to price jumps. Our findings also provide insights into the speed of news absorption and the influence of alternative trading platforms on the jump return behavior.

SSRN Electronic Journal, 2007

a b s t r a c t JEL classification: G15 O13 Q43 Keywords: Crude oil futures WTI Brent Information... more a b s t r a c t JEL classification: G15 O13 Q43 Keywords: Crude oil futures WTI Brent Information sharing Inventory level Spread