Department of Economics and Business Economics

Dynamic Discrete Mixtures for High Frequency Prices

Research output: Working paperResearch

Standard

Dynamic Discrete Mixtures for High Frequency Prices. / Catania, Leopoldo; Di Mari, Roberto; Santucci de Magistris, Paolo.

Social Science Research Network (SSRN), 2019.

Research output: Working paperResearch

Harvard

APA

CBE

Catania L, Di Mari R, Santucci de Magistris P. 2019. Dynamic Discrete Mixtures for High Frequency Prices. Social Science Research Network (SSRN).

MLA

Catania, Leopoldo, Roberto Di Mari, and Paolo Santucci de Magistris Dynamic Discrete Mixtures for High Frequency Prices. Social Science Research Network (SSRN). 2019.,

Vancouver

Catania L, Di Mari R, Santucci de Magistris P. Dynamic Discrete Mixtures for High Frequency Prices. Social Science Research Network (SSRN). 2019.

Author

Catania, Leopoldo ; Di Mari, Roberto ; Santucci de Magistris, Paolo. / Dynamic Discrete Mixtures for High Frequency Prices. Social Science Research Network (SSRN), 2019.

Bibtex

@techreport{e7ca8cfc16914eec8bc955f6f1a0280b,
title = "Dynamic Discrete Mixtures for High Frequency Prices",
abstract = "The tick structure of the financial markets entails that price changes observed at very high frequency are discrete. Departing from this empirical evidence we develop a new model to describe the dynamic properties of multivariate time-series of high frequency price changes, including the high probability of observing no variations (price staleness). We assume the existence of two independent latent/hidden Markov processes determining the dynamic properties of the price changes and the excess probability of the occurrence of zeros. We study the probabilistic properties of the model that generates a zero-inflated mixture of Skellam distributions and we develop an EM estimation procedure with closed-form M step. In the empirical application, we study the joint distribution of the price changes of four assets traded on NYSE. Particular focus is dedicated to the precision of the univariate and multivariate density forecasts, to the quality of the predictions of quantities like the volatility and correlations across assets, and to the possibility of disentangling the different sources of zero price variation as generated by absence of news, microstructural frictions or by the offsetting positions taken by the traders.",
author = "Leopoldo Catania and {Di Mari}, Roberto and {Santucci de Magistris}, Paolo",
year = "2019",
language = "English",
publisher = "Social Science Research Network (SSRN)",
type = "WorkingPaper",
institution = "Social Science Research Network (SSRN)",

}

RIS

TY - UNPB

T1 - Dynamic Discrete Mixtures for High Frequency Prices

AU - Catania, Leopoldo

AU - Di Mari, Roberto

AU - Santucci de Magistris, Paolo

PY - 2019

Y1 - 2019

N2 - The tick structure of the financial markets entails that price changes observed at very high frequency are discrete. Departing from this empirical evidence we develop a new model to describe the dynamic properties of multivariate time-series of high frequency price changes, including the high probability of observing no variations (price staleness). We assume the existence of two independent latent/hidden Markov processes determining the dynamic properties of the price changes and the excess probability of the occurrence of zeros. We study the probabilistic properties of the model that generates a zero-inflated mixture of Skellam distributions and we develop an EM estimation procedure with closed-form M step. In the empirical application, we study the joint distribution of the price changes of four assets traded on NYSE. Particular focus is dedicated to the precision of the univariate and multivariate density forecasts, to the quality of the predictions of quantities like the volatility and correlations across assets, and to the possibility of disentangling the different sources of zero price variation as generated by absence of news, microstructural frictions or by the offsetting positions taken by the traders.

AB - The tick structure of the financial markets entails that price changes observed at very high frequency are discrete. Departing from this empirical evidence we develop a new model to describe the dynamic properties of multivariate time-series of high frequency price changes, including the high probability of observing no variations (price staleness). We assume the existence of two independent latent/hidden Markov processes determining the dynamic properties of the price changes and the excess probability of the occurrence of zeros. We study the probabilistic properties of the model that generates a zero-inflated mixture of Skellam distributions and we develop an EM estimation procedure with closed-form M step. In the empirical application, we study the joint distribution of the price changes of four assets traded on NYSE. Particular focus is dedicated to the precision of the univariate and multivariate density forecasts, to the quality of the predictions of quantities like the volatility and correlations across assets, and to the possibility of disentangling the different sources of zero price variation as generated by absence of news, microstructural frictions or by the offsetting positions taken by the traders.

M3 - Working paper

BT - Dynamic Discrete Mixtures for High Frequency Prices

PB - Social Science Research Network (SSRN)

ER -