A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data

A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data

In this paper, we propose a general family of Birnbaum−Saunders autoregressive conditional duration (BS-ACD) models based on generalized Birnbaum−Saunders (GBS) distributions, denoted by GBS-ACD. We further generalize these GBS-ACD models by using a Box-Cox transformation with a...

Full description

Bibliographic Details
Main Authors: Danúbia R. Cunha, Roberto Vila, Helton Saulo, Rodrigo N. Fernandez
Format: Article
Language:English
Published: MDPI AG 2020-03-01
Series:Journal of Risk and Financial Management
Subjects:
generalized birnbaum–saunders distributions
acd models
box-cox transformation
high-frequency financial data
goodness-of-fit
Online Access:https://www.mdpi.com/1911-8074/13/3/45
id doaj-26e4585229c94000b9a7899204c737fe
record_format Article
spelling doaj-26e4585229c94000b9a7899204c737fe2020-11-25T02:56:03ZengMDPI AGJournal of Risk and Financial Management1911-80742020-03-011334510.3390/jrfm13030045jrfm13030045A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial DataDanúbia R. Cunha0Roberto Vila1Helton Saulo2Rodrigo N. Fernandez3Department of Economics, Catholic University of Brasilia, 71966-700 Brasilia, BrazilDepartment of Statistics, University of Brasilia, 70910-900 Brasilia, BrazilDepartment of Statistics, University of Brasilia, 70910-900 Brasilia, BrazilDepartment of Economics, Federal University of Pelotas, 96010-610 Pelotas, BrazilIn this paper, we propose a general family of Birnbaum&#8722;Saunders autoregressive conditional duration (BS-ACD) models based on generalized Birnbaum&#8722;Saunders (GBS) distributions, denoted by GBS-ACD. We further generalize these GBS-ACD models by using a Box-Cox transformation with a shape parameter <inline-formula> <math display="inline"> <semantics> <mi>&#955;</mi> </semantics> </math> </inline-formula> to the conditional median dynamics and an asymmetric response to shocks; this is denoted by GBS-AACD. We then carry out a Monte Carlo simulation study to evaluate the performance of the GBS-ACD models. Finally, an illustration of the proposed models is made by using New York stock exchange (NYSE) transaction data.https://www.mdpi.com/1911-8074/13/3/45generalized birnbaum–saunders distributionsacd modelsbox-cox transformationhigh-frequency financial datagoodness-of-fit
collection DOAJ
language English
format Article
sources DOAJ
author Danúbia R. Cunha
Roberto Vila
Helton Saulo
Rodrigo N. Fernandez
spellingShingle Danúbia R. Cunha
Roberto Vila
Helton Saulo
Rodrigo N. Fernandez
A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
Journal of Risk and Financial Management
generalized birnbaum–saunders distributions
acd models
box-cox transformation
high-frequency financial data
goodness-of-fit
author_facet Danúbia R. Cunha
Roberto Vila
Helton Saulo
Rodrigo N. Fernandez
author_sort Danúbia R. Cunha
title A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
title_short A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
title_full A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
title_fullStr A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
title_full_unstemmed A General Family of Autoregressive Conditional Duration Models Applied to High-Frequency Financial Data
title_sort general family of autoregressive conditional duration models applied to high-frequency financial data
publisher MDPI AG
series Journal of Risk and Financial Management
issn 1911-8074
publishDate 2020-03-01
description In this paper, we propose a general family of Birnbaum&#8722;Saunders autoregressive conditional duration (BS-ACD) models based on generalized Birnbaum&#8722;Saunders (GBS) distributions, denoted by GBS-ACD. We further generalize these GBS-ACD models by using a Box-Cox transformation with a shape parameter <inline-formula> <math display="inline"> <semantics> <mi>&#955;</mi> </semantics> </math> </inline-formula> to the conditional median dynamics and an asymmetric response to shocks; this is denoted by GBS-AACD. We then carry out a Monte Carlo simulation study to evaluate the performance of the GBS-ACD models. Finally, an illustration of the proposed models is made by using New York stock exchange (NYSE) transaction data.
topic generalized birnbaum–saunders distributions
acd models
box-cox transformation
high-frequency financial data
goodness-of-fit
url https://www.mdpi.com/1911-8074/13/3/45
work_keys_str_mv AT danubiarcunha ageneralfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT robertovila ageneralfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT heltonsaulo ageneralfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT rodrigonfernandez ageneralfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT danubiarcunha generalfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT robertovila generalfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT heltonsaulo generalfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
AT rodrigonfernandez generalfamilyofautoregressiveconditionaldurationmodelsappliedtohighfrequencyfinancialdata
_version_ 1724714415315484672

Similar Items