EcoSta 2021: Start Registration
View Submission - EcoSta2021
A0310
Title: Bayesian analysis of price discovery on time-varying partial adjustment model Authors:  Kenji Hatakenaka - Osaka University (Japan) [presenting]
Kosuke Oya - Osaka University (Japan)
Abstract: Price discovery is an important built-in function of financial markets and the central issue in microstructure research. Market participants need to know whether the price discovery has been achieved or how much progress has been made to trade at an appropriate price they consider. Since various economic events such as earning announcement affect price discovery, the intraday transition of price discovery varies date-by-date. We propose a statistical method to see when, how fast, and how accurate the intraday price discovery works using only the high-frequency price series in a single day. The method consists of estimating candidate models and selecting the most appropriate model based on a Bayesian approach. We conduct simulation studies to examine the performance of the proposed method and confirm the most reliable selection criteria. We will report how the selection criteria work and result from an empirical study using actual financial data.