Faculty & Research

Dacheng Xiu

Associate Professor of Econometrics and Statistics and IBM Corporation Faculty Scholar

Phone :
Address :
5807 South Woodlawn Avenue
Chicago, IL 60637

Dacheng Xiu studies financial econometrics with emphases on statistical inference and the economic implication of high-frequency financial data. His current research also involves econometric modeling of derivatives and statistical methodologies for big financial data.

His work has appeared in the Econometrica, Journal of Econometrics, Journal of the American Statistical Association, and he has been invited to publish in the Journal of Business Statistics and Economic Statistics. Xiu has presented his work at various conferences and university seminars. He also serves as a referee for many journals in econometrics, statistics, and finance.

Xiu earned his PhD and MA in applied mathematics from Princeton University, where he studied at the Bendheim Center for Finance. Before that, he obtained a BS in mathematics from the University of Science and Technology of China in Hefei, China. Additionally, Xiu's professional experience includes work with TYKHE Capital LLC in New York and Citigroup in their capital markets and banking division.

Outside of academia, Xiu enjoys a variety of sports as well as photography.


2015 - 2016 Course Schedule

Number Name Quarter
41100 Applied Regression Analysis 2016 (Winter)
41902 Statistical Inference 2016 (Winter)

Other Interests

Skiing, swimming, diving, basketball, and photography


Research Activities

Financial Econometrics, Statistics, Empirical Asset Pricing, and Quantitative Finance

"Hermite Polynomial Based Expansion of European Option Prices." Dacheng Xiu; Journal of Econometrics, 2014, 179(2), pp. 158-77.

"Quasi-Maximum Likelihood Estimation of GARCH Models with Heavy-Tailed Likelihoods." Jianqing Fan, Lei Qi and Dacheng Xiu; Journal of Business & Economic Statistics, 2013, 32(2), pp. 178-91.

"Likelihood-Based Volatility Estimators in the Presence of Market Microstructure Noise," Yacine Aït-Sahalia and Dacheng Xiu, in L. Bauwens, C. Hafner and S. Laurent: Handbook of Volatility Models and Their Applications. Hoboken, New Jersey: John Wiley & Sons, Inc., 2012, pp. 347-61

"Quasi-Maximum Likelihood Estimation of Volatility with High Frequency Data." Dacheng Xiu; Journal of Econometrics, 2010, 159(1), pp. 235-50.

"High-Frequency Covariance Estimates with Noisy and Asynchronous Financial Data." Yacine Aït-Sahalia, Jianqing Fan and Dacheng Xiu; Journal of the American Statistical Association, 2010, 105(492), pp. 1504-17.

For a listing of research publications please visit ’s university library listing page.

REVISION: A Hausman Test for the Presence of Market Microstructure Noise in High Frequency Data
Date Posted: Apr  12, 2016
We develop tests that help assess whether a high frequency data sample can be treated as reasonably free of market microstructure noise at a given sampling frequency for the purpose of implementing high frequency volatility and other estimators. The tests are based on the Hausman principle of comparing two estimators, one that is efficient but not robust to the deviation being tested, and one that is robust but not as efficient. We investigate the asymptotic properties of the test statistic in a general nonparametric setting, and compare it with several alternatives that are also developed in the paper. Empirically, we find that improvements in stock market liquidity over the past decade have increased the frequency at which simple, uncorrected, volatility estimators can be safely employed.

REVISION: Using Principal Component Analysis to Estimate a High Dimensional Factor Model with High-Frequency Data
Date Posted: Apr  05, 2016
This paper constructs an estimator for the number of common factors in a setting where both the sampling frequency and the number of variables increase. Empirically, we document that the covariance matrix of a large portfolio of US equities is well represented by a low rank common structure with sparse residual matrix. When employed for out-of-sample portfolio allocation, the proposed estimator largely outperforms the sample covariance estimator.

REVISION: Econometric Analysis of Multivariate Realised QML: Estimation of the Covariation of Equity Prices under Asynchronous Trading
Date Posted: Mar  12, 2016
Estimating the covariance between assets using high frequency data is challenging due to market microstructure effects and asynchronous trading. In this paper we develop a multivariate realized quasi-likelihood (QML) approach, carrying out inference as if the observations arise from an asynchronously observed vector scaled Brownian model observed with error. Under stochastic volatility the resulting realised QML estimator is positive semi-definite, uses all available data, is consistent and asymptotically mixed normal. The quasi-likelihood is computed using a Kalman filter and optimized using a relatively simple EM algorithm which scales well with the number of assets. We derive the theoretical properties of the estimator and prove that it achieves the efficient rate of convergence. The estimator is also analysed using Monte Carlo methods and applied to equity data with varying levels of liquidity.

REVISION: Nonparametric Estimation of the Leverage Effect: A Trade-off between Robustness and Efficiency
Date Posted: Nov  24, 2015
We consider two new approaches to nonparametric estimation of the leverage effect. The first approach uses stock prices alone. The second approach uses the data on stock prices as well as a certain volatility instrument, such as the CBOE volatility index (VIX) or the Black-Scholes implied volatility. The theoretical justification for the instrument-based estimator relies on a certain invariance property, which can be exploited when high frequency data is available. The price-only estimator is more robust since it is valid under weaker assumptions. However, in the presence of a valid volatility instrument, the price-only estimator is inefficient as the instrument-based estimator has a faster rate of convergence. We consider two empirical applications, in which we study the relationship between the leverage effect and the debt-to-equity ratio, credit risk, and illiquidity.

REVISION: Principal Component Analysis of High Frequency Data
Date Posted: Oct  11, 2015
We develop the necessary methodology to conduct principal component analysis at high frequency. We construct estimators of realized eigenvalues, eigenvectors, and principal components and provide the asymptotic distribution of these estimators. Empirically, we study the high frequency covariance structure of the constituents of the S&P 100 Index using as little as one week of high frequency data at a time. The explanatory power of the high frequency principal components varies over time. During the recent financial crisis, the first principal component becomes increasingly dominant, explaining up to 60% of the variation on its own, while the second principal component drives the common variation of financial sector stocks.

REVISION: Incorporating Global Industrial Classification Standard into Portfolio Allocation: A Simple Factor-Based Large Covariance Matrix Estimator with High Frequency Data
Date Posted: Apr  22, 2015
We document a striking block-diagonal pattern in the factor model residual covariances of the S&P 500 Equity Index constituents, after sorting the assets by their assigned Global Industry Classification Standard (GICS) codes. Cognizant of this structure, we propose combining a location-based thresholding approach based on sector inclusion with the Fama-French and SDPR sector Exchange Traded Funds (ETF’s). We investigate the performance of our estimators in an out-of-sample portfolio allocation study. We find that our simple and positive-definite covariance matrix estimator yields strong empirical results under a variety of factor models and thresholding schemes. Conversely, we find that the Fama-French factor model is only suitable for covariance estimation when used in conjunction with our proposed thresholding technique. Theoretically, we provide justification for the empirical results by jointly analyzing the in-fill and diverging dimension asymptotics.

REVISION: A Tale of Two Option Markets: Pricing Kernels and Volatility Risk
Date Posted: Apr  15, 2015
Using both S&P 500 option and recently introduced VIX option prices, we study pricing kernels and their dependence on multiple volatility factors. We first propose nonparametric estimates of marginal pricing kernels, conditional on the VIX and the slope of the variance swap term structure. Our estimates highlight the state-dependence nature of the pricing kernels. In particular, conditioning on volatility factors, the pricing kernel of market returns exhibit a downward sloping shape up to the extreme end of the right tail. Moreover, the volatility pricing kernel features a striking U-shape, implying that investors have high marginal utility in both high and low volatility states. This finding on the volatility pricing kernel presents a new empirical challenge to both existing equilibrium and reduced-form asset pricing models of volatility risk. Finally, using a full-fledged parametric model, we recover the joint pricing kernel, which is not otherwise identifiable.

New: Generalized Method of Integrated Moments for High-Frequency Data
Date Posted: Feb  06, 2015
We propose a semiparametric two-step inference procedure for a finite-dimensional parameter based on moment conditions constructed from high-frequency data. The population moment conditions take the form of temporally integrated functionals of state-variable processes that include the latent stochastic volatility process of an asset. In the first step, we nonparametrically recover the volatility path from high-frequency asset returns. The nonparametric volatility estimator is then used to form sample moment functions in the second-step GMM estimation, which requires the correction of a high-order nonlinearity bias from the first step. We show that the proposed estimator is consistent and asymptotically mixed Gaussian and propose a consistent estimator for the conditional asymptotic variance. We also construct a Bierens-type consistent specification test. These infill asymptotic results are based on a novel empirical-process-type theory for general integrated functionals of noisy ...

REVISION: Resolution of Policy Uncertainty and Sudden Declines in Volatility
Date Posted: Aug  06, 2014
We introduce downward volatility jumps into a general non-affine modeling framework of the term structure of variance. With variance swaps and S&P 500 returns, we find that downward volatility jumps are associated with a resolution of policy uncertainty, in particular through statements from Federal Open Market Committee meetings and speeches of the Federal Reserve chairman. We also find that such jumps are priced with positive risk premia, which reflect the price of the "put protection" offered by the Federal Reserve. Ignoring downward volatility jumps may lead to an exaggeration of the negative total variance risk premia, hence a biased-interpretation of the price of tail events. We also find variance risk premia tend to be insignificant or even positive at the inception of crises. On the modeling side, we explore the structural differences and relative goodness-of-fits of factor specifications, and find that the log-volatility model with two Ornstein-Uhlenbeck factors and ...

New: Increased Correlation Among Asset Classes: Are Volatility or Jumps to Blame, or Both?
Date Posted: Apr  16, 2014
We develop estimators and asymptotic theory to decompose the quadratic covariation between two assets into its continuous and jump components, in a manner that is robust to the presence of market microstructure noise. Using high frequency data on different assets classes, we find that the recent financial crisis led to an increase in both the quadratic variations of the assets and their correlations. However, we find little evidence to suggest a change between the relative contributions of the Brownian and jump components, as both comove. Co-jumps stem from surprising news announcements that occur primarily before the opening of the U.S. market, and are also accompanied by an increase in Brownian-driven correlations.

REVISION: Hermite Polynomial Based Expansion of European Option Prices
Date Posted: Dec  20, 2013
We seek a closed-form series approximation of European option prices under a variety of diffusion models. The proposed convergent series are derived using the Hermite polynomial approach. Departing from the usual option pricing routine in the literature, our model assumptions have no requirements for affine dynamics or explicit characteristic functions. Moreover, convergent expansions provide a distinct insight into how and on which order the model parameters affect option prices, in contrast with small-time asymptotic expansions in the literature. With closed-form expansions, we explicitly translate model features into option prices, such as mean-reverting drift and self-exciting or skewed jumps. Numerical examples illustrate the accuracy of this approach and its advantage over alternative expansion methods.

New: Spot Variance Regressions
Date Posted: Feb  12, 2013
We study a nonlinear vector regression model for discretely sampled high-frequency data with the latent spot variance of an asset as a covariate. We propose a two-stage inference procedure by first nonparametrically recovering the volatility path from asset returns and then conducting inference based on the generalized method of moments (GMM). The GMM estimator is nonstandard in that the second-order asymptotics is dominated by a bias term, rendering the standard inference implausible. We propos

REVISION: Quasi Maximum Likelihood Estimation of GARCH Models with Heavy-Tailed Likelihoods
Date Posted: Aug  06, 2012
The non-Gaussian maximum likelihood estimator is frequently used in GARCH models with the intention of capturing the heavy-tailed returns. However, unless the parametric likelihood family contains the true likelihood, the estimator is inconsistent due to density misspecification. To correct this bias, we identify an unknown scale parameter that is critical to the identification, and propose a two-step quasi maximum likelihood procedure with non-Gaussian likelihood functions. This novel approach

New: High Frequency Covariance Estimates with Noisy and Asynchronous Financial Data
Date Posted: Jun  28, 2010
This paper proposes a consistent and efficient estimator of the high frequency covariance (quadratic covariation) of two arbitrary assets, observed asynchronously with market microstructure noise. This estimator is built upon the marriage of the quasi-maximum likelihood estimator of the quadratic variation and the proposed Generalized Synchronization scheme. It is therefore not influenced by the Epps effect. Moreover, the estimation procedure is free of tuning parameters or bandwidths and readil

REVISION: Quasi-Maximum Likelihood Estimation of Volatility with High Frequency Data
Date Posted: Jun  28, 2010
This paper investigates the properties of the well-known maximum likelihood estimator in the presence of stochastic volatility and market microstructure noise, by extending the classic asymptotic results of quasi-maximum likelihood estimation. When trying to estimate the integrated volatility and the variance of noise, this parametric approach remains consistent, efficient and robust as a quasi-estimator under misspecified assumptions. Moreover, it shares the model-free feature with nonparametri