Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution
This paper proposes a logarithmic version of the two-component ACD (LogCACD) model with no restrictions on the sign of the model parameters while allowing the expected durations to be decomposed into the long- and short-run components to capture the dynamics of these durations. The extended generali...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/10/1621 |
| _version_ | 1827668104876916736 |
|---|---|
| author | Yiing Fei Tan Kok Haur Ng You Beng Koh Shelton Peiris |
| author_facet | Yiing Fei Tan Kok Haur Ng You Beng Koh Shelton Peiris |
| author_sort | Yiing Fei Tan |
| collection | DOAJ |
| description | This paper proposes a logarithmic version of the two-component ACD (LogCACD) model with no restrictions on the sign of the model parameters while allowing the expected durations to be decomposed into the long- and short-run components to capture the dynamics of these durations. The extended generalised inverse Gaussian (EGIG) distribution is used for the error distribution as its hazard function consists of a roller-coaster shape for certain parameters’ values. An empirical application from the trade durations of International Business Machines stock index has been carried out to investigate this proposed model. Extensive comparisons are carried out to evaluate the modelling and forecasting performances of the proposed model with several benchmark models and different specifications of error distributions. The result reveals that the LogCACD<sub>EGIG</sub>(1,1) model gives the best in-sample fit based on the Akaike information criterion and other criteria. Furthermore, the estimated parameters obtained through the maximum likelihood estimation confirm the existence of the roller-coaster-shaped hazard function. The examination of LogCACD<sub>EGIG</sub>(1,1) model also provides the best out-of-sample forecasts evaluated based on the mean square forecast error using the Hansen’s model confidence set. Lastly, different levels of time-at-risk forecasts are provided and tested with Kupiec likelihood ratio test. |
| first_indexed | 2024-03-10T03:30:28Z |
| format | Article |
| id | doaj.art-fe0f1a6e84a64c9e995f02658ff406cb |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T03:30:28Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-fe0f1a6e84a64c9e995f02658ff406cb2023-11-23T11:59:59ZengMDPI AGMathematics2227-73902022-05-011010162110.3390/math10101621Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian DistributionYiing Fei Tan0Kok Haur Ng1You Beng Koh2Shelton Peiris3Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur 50603, MalaysiaInstitute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur 50603, MalaysiaInstitute of Mathematical Sciences, Faculty of Science, Universiti Malaya, Kuala Lumpur 50603, MalaysiaSchool of Mathematics and Statistics, Faculty of Science, The University of Sydney, Sydney, NSW 2006, AustraliaThis paper proposes a logarithmic version of the two-component ACD (LogCACD) model with no restrictions on the sign of the model parameters while allowing the expected durations to be decomposed into the long- and short-run components to capture the dynamics of these durations. The extended generalised inverse Gaussian (EGIG) distribution is used for the error distribution as its hazard function consists of a roller-coaster shape for certain parameters’ values. An empirical application from the trade durations of International Business Machines stock index has been carried out to investigate this proposed model. Extensive comparisons are carried out to evaluate the modelling and forecasting performances of the proposed model with several benchmark models and different specifications of error distributions. The result reveals that the LogCACD<sub>EGIG</sub>(1,1) model gives the best in-sample fit based on the Akaike information criterion and other criteria. Furthermore, the estimated parameters obtained through the maximum likelihood estimation confirm the existence of the roller-coaster-shaped hazard function. The examination of LogCACD<sub>EGIG</sub>(1,1) model also provides the best out-of-sample forecasts evaluated based on the mean square forecast error using the Hansen’s model confidence set. Lastly, different levels of time-at-risk forecasts are provided and tested with Kupiec likelihood ratio test.https://www.mdpi.com/2227-7390/10/10/1621autoregressive conditional durationtwo-component modelextended generalised inverse Gaussianhazard functiontime-at-risk |
| spellingShingle | Yiing Fei Tan Kok Haur Ng You Beng Koh Shelton Peiris Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution Mathematics autoregressive conditional duration two-component model extended generalised inverse Gaussian hazard function time-at-risk |
| title | Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution |
| title_full | Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution |
| title_fullStr | Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution |
| title_full_unstemmed | Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution |
| title_short | Modelling Trade Durations Using Dynamic Logarithmic Component ACD Model with Extended Generalised Inverse Gaussian Distribution |
| title_sort | modelling trade durations using dynamic logarithmic component acd model with extended generalised inverse gaussian distribution |
| topic | autoregressive conditional duration two-component model extended generalised inverse Gaussian hazard function time-at-risk |
| url | https://www.mdpi.com/2227-7390/10/10/1621 |
| work_keys_str_mv | AT yiingfeitan modellingtradedurationsusingdynamiclogarithmiccomponentacdmodelwithextendedgeneralisedinversegaussiandistribution AT kokhaurng modellingtradedurationsusingdynamiclogarithmiccomponentacdmodelwithextendedgeneralisedinversegaussiandistribution AT youbengkoh modellingtradedurationsusingdynamiclogarithmiccomponentacdmodelwithextendedgeneralisedinversegaussiandistribution AT sheltonpeiris modellingtradedurationsusingdynamiclogarithmiccomponentacdmodelwithextendedgeneralisedinversegaussiandistribution |