Guest editors' introduction

摘要

This special issue, entitled "Recent Development in Financial Econometrics", is a collection of some research results presented in the First Symposium on Econometric Theory and Applications (SETA) Conference held in Academia Sinica, Taipei, Taiwan, from May 18 through May 20, 2005. Among 35 papers presented in the meeting, 27 were submitted to the special issue, and 16 were accepted for publication, including three by the invited speakers (C. Gourieroux, B. Lehmann, and G. Tauchen) and their coauthors. The volatility of financial time series has been a leading research area in financial econometrics. A majority of the accepted articles in this special issue are related to the modeling and estimation of volatility. In the first article, "Predictive Density Estimators for Daily Volatility Based on the Use of Realized Measures", V. Corradi, W. Distaso, and N.R. Swanson construct a non-parametric estimator of the predictive density of integrated volatility based on a given realized measure. This estimator is quite flexible because several well known measures, such as realized volatility, bipower variation, and subsampled realized volatility, can be employed to compute the proposed estimator. The second paper by P.C.B. Phillips and J. Yu, "A Two-StageRealized Volatility Approach to Estimation of Diffusion Processes with Discrete Data", proposes a two-step estimation method for diffusion processes, such that the parameters in the diffusion function and the drift function are estimated separately. In the third paper, "A Discrete-Time Model for Daily S&P500 Returns and Realized Variations: Jumps and Leverage Effects", T. Bollerslev, U. Kretschmer, C. Pigorsch, and G. Tauchen introduce a multivariate system that jointly model return and two volatility components -realized continuous and jump variations.