Bayesian dynamic modeling of high-frequency integer price changes

István Barra, Agnieszka Borowska, Siem Jan Koopman

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

We investigate high-frequency volatility models for analyzing intradaily tick by tick stock price changes using Bayesian estimation procedures. Our key interest is the extraction of intradaily volatility patterns from high-frequency integer price changes. We account for the discrete nature of the data via two different approaches: ordered probit models and discrete distributions. We allow for stochastic volatility by modeling the variance as a stochastic function of time, with intraday periodic patterns. We consider distributions with heavy tails to address occurrences of jumps in tick by tick discrete prices changes. In particular, we introduce a dynamic version of the negative binomial difference model with stochastic volatility. For each model, we develop a Markov chain Monte Carlo estimation method that takes advantage of auxiliary mixture representations to facilitate the numerical implementation. This new modeling framework is illustrated by means of tick by tick data for two stocks from the NYSE and for different periods. Different models are compared with each other based on the predictive likelihoods. We find evidence in favor of our preferred dynamic negative binomial difference model.

Original languageEnglish
Pages (from-to)384-424
Number of pages41
JournalJournal of Financial Econometrics
Volume16
Issue number3
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

Price changes
Dynamic modeling
Ticks
Integer
Modeling
Stochastic volatility
Negative binomial
Discrete distributions
Bayesian estimation
Markov chain Monte Carlo
Stock prices
Jump
Ordered probit model
New York Stock Exchange
Volatility models
Heavy tails

Keywords

  • Bayesian inference
  • Discrete distributions
  • High-frequency dynamics
  • Markov chain monte carlo
  • Stochastic volatility

Cite this

Barra, István ; Borowska, Agnieszka ; Koopman, Siem Jan. / Bayesian dynamic modeling of high-frequency integer price changes. In: Journal of Financial Econometrics. 2018 ; Vol. 16, No. 3. pp. 384-424.
@article{12a2fa9498e34fea8d98282abdf580f5,
title = "Bayesian dynamic modeling of high-frequency integer price changes",
abstract = "We investigate high-frequency volatility models for analyzing intradaily tick by tick stock price changes using Bayesian estimation procedures. Our key interest is the extraction of intradaily volatility patterns from high-frequency integer price changes. We account for the discrete nature of the data via two different approaches: ordered probit models and discrete distributions. We allow for stochastic volatility by modeling the variance as a stochastic function of time, with intraday periodic patterns. We consider distributions with heavy tails to address occurrences of jumps in tick by tick discrete prices changes. In particular, we introduce a dynamic version of the negative binomial difference model with stochastic volatility. For each model, we develop a Markov chain Monte Carlo estimation method that takes advantage of auxiliary mixture representations to facilitate the numerical implementation. This new modeling framework is illustrated by means of tick by tick data for two stocks from the NYSE and for different periods. Different models are compared with each other based on the predictive likelihoods. We find evidence in favor of our preferred dynamic negative binomial difference model.",
keywords = "Bayesian inference, Discrete distributions, High-frequency dynamics, Markov chain monte carlo, Stochastic volatility",
author = "Istv{\'a}n Barra and Agnieszka Borowska and Koopman, {Siem Jan}",
year = "2018",
month = "6",
day = "1",
doi = "10.1093/jjfinec/nby010",
language = "English",
volume = "16",
pages = "384--424",
journal = "Journal of Financial Econometrics",
issn = "1479-8409",
publisher = "Oxford University Press",
number = "3",

}

Bayesian dynamic modeling of high-frequency integer price changes. / Barra, István; Borowska, Agnieszka; Koopman, Siem Jan.

In: Journal of Financial Econometrics, Vol. 16, No. 3, 01.06.2018, p. 384-424.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Bayesian dynamic modeling of high-frequency integer price changes

AU - Barra, István

AU - Borowska, Agnieszka

AU - Koopman, Siem Jan

PY - 2018/6/1

Y1 - 2018/6/1

N2 - We investigate high-frequency volatility models for analyzing intradaily tick by tick stock price changes using Bayesian estimation procedures. Our key interest is the extraction of intradaily volatility patterns from high-frequency integer price changes. We account for the discrete nature of the data via two different approaches: ordered probit models and discrete distributions. We allow for stochastic volatility by modeling the variance as a stochastic function of time, with intraday periodic patterns. We consider distributions with heavy tails to address occurrences of jumps in tick by tick discrete prices changes. In particular, we introduce a dynamic version of the negative binomial difference model with stochastic volatility. For each model, we develop a Markov chain Monte Carlo estimation method that takes advantage of auxiliary mixture representations to facilitate the numerical implementation. This new modeling framework is illustrated by means of tick by tick data for two stocks from the NYSE and for different periods. Different models are compared with each other based on the predictive likelihoods. We find evidence in favor of our preferred dynamic negative binomial difference model.

AB - We investigate high-frequency volatility models for analyzing intradaily tick by tick stock price changes using Bayesian estimation procedures. Our key interest is the extraction of intradaily volatility patterns from high-frequency integer price changes. We account for the discrete nature of the data via two different approaches: ordered probit models and discrete distributions. We allow for stochastic volatility by modeling the variance as a stochastic function of time, with intraday periodic patterns. We consider distributions with heavy tails to address occurrences of jumps in tick by tick discrete prices changes. In particular, we introduce a dynamic version of the negative binomial difference model with stochastic volatility. For each model, we develop a Markov chain Monte Carlo estimation method that takes advantage of auxiliary mixture representations to facilitate the numerical implementation. This new modeling framework is illustrated by means of tick by tick data for two stocks from the NYSE and for different periods. Different models are compared with each other based on the predictive likelihoods. We find evidence in favor of our preferred dynamic negative binomial difference model.

KW - Bayesian inference

KW - Discrete distributions

KW - High-frequency dynamics

KW - Markov chain monte carlo

KW - Stochastic volatility

UR - http://www.scopus.com/inward/record.url?scp=85051552102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051552102&partnerID=8YFLogxK

U2 - 10.1093/jjfinec/nby010

DO - 10.1093/jjfinec/nby010

M3 - Article

VL - 16

SP - 384

EP - 424

JO - Journal of Financial Econometrics

JF - Journal of Financial Econometrics

SN - 1479-8409

IS - 3

ER -