Loading…

Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates

•For out-of-sample VaR forecasts distribution effect is crucial for high level.•The WHS (the parametric approach) has the best (worst) VaR forecasting performance.•VaR (ES) models underrate (overrate) the risk and thus ES is more cautious than VaR.•Long memory (long memory and leverage effect) is ma...

Full description

Saved in:
Bibliographic Details
Published in:The North American journal of economics and finance 2014-11, Vol.30, p.1-39
Main Author: Su, Jung-Bin
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3
cites cdi_FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3
container_end_page 39
container_issue
container_start_page 1
container_title The North American journal of economics and finance
container_volume 30
creator Su, Jung-Bin
description •For out-of-sample VaR forecasts distribution effect is crucial for high level.•The WHS (the parametric approach) has the best (worst) VaR forecasting performance.•VaR (ES) models underrate (overrate) the risk and thus ES is more cautious than VaR.•Long memory (long memory and leverage effect) is major for ES (VaR) estimate.•Regarding in-sample VaR forecasts distribution effect is crucial for GFC period. In this study, eight generalized autoregressive conditional heteroskedasticity (GARCH) types of variance specifications and two return distribution settings, the normal and skewed generalized Student's t (SGT) of Theodossiou (1998), totaling nine GARCH-based models, are utilized to forecast the volatility of six stock indices, and then both the out-of-sample-period value-at-risk (VaR) and the expected shortfall (ES) are estimated following the rolling window approach. Moreover, the in-sample VaR is estimated for both the global financial crisis (GFC) period and the non-GFC period. Subsequently, through several accuracy measures, nine models are evaluated in order to explore the influence of long memory, leverage, and distribution effects on the performance of VaR and ES forecasts. As shown by the empirical results of the nine models, the long memory, leverage, and distribution effects subsist in the stock markets. Moreover, regarding the out-of-sample VaR forecasts, long memory is the most important effect, followed by the leverage effect for the low level, whereas the distribution effect is crucial for the high level. As for the three VaR approaches, weighted historical simulation achieves the best VaR forecasting performance, followed by filtered historical simulation, whereas the parametric approach has the worst VaR forecasting performance for all the levels. Furthermore, VaR models underestimate the true risk, whereas ES models overestimate the true risk, indicating that the ES risk measure is more conservative than the VaR risk measure. Additionally, based on back-testing, the VaR provides a better risk forecast than the ES since the ES highly overestimates the true risk. Notably, long memory is important for the ES estimate, whereas both the long memory and the leverage effect are crucial for the VaR estimate. Finally, via in-sample VaR forecasts in regard to the low level, it is found that long memory is important for the non-GFC period, whereas the distribution effect is crucial for the GFC period. On the other hand, with regard to the high level,
doi_str_mv 10.1016/j.najef.2014.07.003
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_1627728605</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S1062940814000771</els_id><sourcerecordid>3506660071</sourcerecordid><originalsourceid>FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3</originalsourceid><addsrcrecordid>eNp9kEtPwzAQhCMEEqXwC7hY4tqEtfNwcuCAqvKQKnGBs-XY68ppEhc7rdR_j0s5cxrLnvHufElyTyGjQKvHLhtlhyZjQIsMeAaQXyQzWvMmhbqCy3iGiqVNAfV1chNCBwBFxfkswdWws94q2RM5yv4YbCDOkN6NGzLg4PxxQXo8oJcbXESLJtqGydt2P1k3EjQG1RSIcZ6EyaktGaTf4kS8DVuCYbKDnDDcJldG9gHv_nSefL2sPpdv6frj9X35vE5V3pRTqnVLFaubRlLgbUOZYUUOhue0YPFFtrku2pMA47ppC1Sl0rGYzFlZ03g_Tx7O_-68-97H8aJzex97BUErxjmLMMroys8u5V0IHo3Y-binPwoK4sRTdOKXpzjxFMBF5BlTT-cUxgIHi14EZXFUqK2PDIR29t_8D6eEgIk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1627728605</pqid></control><display><type>article</type><title>Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates</title><source>ScienceDirect Freedom Collection</source><creator>Su, Jung-Bin</creator><creatorcontrib>Su, Jung-Bin</creatorcontrib><description>•For out-of-sample VaR forecasts distribution effect is crucial for high level.•The WHS (the parametric approach) has the best (worst) VaR forecasting performance.•VaR (ES) models underrate (overrate) the risk and thus ES is more cautious than VaR.•Long memory (long memory and leverage effect) is major for ES (VaR) estimate.•Regarding in-sample VaR forecasts distribution effect is crucial for GFC period. In this study, eight generalized autoregressive conditional heteroskedasticity (GARCH) types of variance specifications and two return distribution settings, the normal and skewed generalized Student's t (SGT) of Theodossiou (1998), totaling nine GARCH-based models, are utilized to forecast the volatility of six stock indices, and then both the out-of-sample-period value-at-risk (VaR) and the expected shortfall (ES) are estimated following the rolling window approach. Moreover, the in-sample VaR is estimated for both the global financial crisis (GFC) period and the non-GFC period. Subsequently, through several accuracy measures, nine models are evaluated in order to explore the influence of long memory, leverage, and distribution effects on the performance of VaR and ES forecasts. As shown by the empirical results of the nine models, the long memory, leverage, and distribution effects subsist in the stock markets. Moreover, regarding the out-of-sample VaR forecasts, long memory is the most important effect, followed by the leverage effect for the low level, whereas the distribution effect is crucial for the high level. As for the three VaR approaches, weighted historical simulation achieves the best VaR forecasting performance, followed by filtered historical simulation, whereas the parametric approach has the worst VaR forecasting performance for all the levels. Furthermore, VaR models underestimate the true risk, whereas ES models overestimate the true risk, indicating that the ES risk measure is more conservative than the VaR risk measure. Additionally, based on back-testing, the VaR provides a better risk forecast than the ES since the ES highly overestimates the true risk. Notably, long memory is important for the ES estimate, whereas both the long memory and the leverage effect are crucial for the VaR estimate. Finally, via in-sample VaR forecasts in regard to the low level, it is found that long memory is important for the non-GFC period, whereas the distribution effect is crucial for the GFC period. On the other hand, with regard to the high level, the distribution effect is crucial for both the non-GFC and the GFC period. These results seem to be consistent with those found in the out-of-sample VaR forecasts. In accordance with these results, several important policy implications are proposed in this study.</description><identifier>ISSN: 1062-9408</identifier><identifier>EISSN: 1879-0860</identifier><identifier>DOI: 10.1016/j.najef.2014.07.003</identifier><language>eng</language><publisher>Greenwich: Elsevier Inc</publisher><subject>Distribution effects ; Economic crisis ; Economic models ; Expected shortfall ; Global financial crisis ; Indexes ; Leverage effect ; Long memory ; Rates of return ; Risk assessment ; Stock exchanges ; Studies ; Value-at-risk ; Volatility</subject><ispartof>The North American journal of economics and finance, 2014-11, Vol.30, p.1-39</ispartof><rights>2014 Elsevier Inc.</rights><rights>Copyright Elsevier Science Ltd. Nov 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3</citedby><cites>FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>Su, Jung-Bin</creatorcontrib><title>Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates</title><title>The North American journal of economics and finance</title><description>•For out-of-sample VaR forecasts distribution effect is crucial for high level.•The WHS (the parametric approach) has the best (worst) VaR forecasting performance.•VaR (ES) models underrate (overrate) the risk and thus ES is more cautious than VaR.•Long memory (long memory and leverage effect) is major for ES (VaR) estimate.•Regarding in-sample VaR forecasts distribution effect is crucial for GFC period. In this study, eight generalized autoregressive conditional heteroskedasticity (GARCH) types of variance specifications and two return distribution settings, the normal and skewed generalized Student's t (SGT) of Theodossiou (1998), totaling nine GARCH-based models, are utilized to forecast the volatility of six stock indices, and then both the out-of-sample-period value-at-risk (VaR) and the expected shortfall (ES) are estimated following the rolling window approach. Moreover, the in-sample VaR is estimated for both the global financial crisis (GFC) period and the non-GFC period. Subsequently, through several accuracy measures, nine models are evaluated in order to explore the influence of long memory, leverage, and distribution effects on the performance of VaR and ES forecasts. As shown by the empirical results of the nine models, the long memory, leverage, and distribution effects subsist in the stock markets. Moreover, regarding the out-of-sample VaR forecasts, long memory is the most important effect, followed by the leverage effect for the low level, whereas the distribution effect is crucial for the high level. As for the three VaR approaches, weighted historical simulation achieves the best VaR forecasting performance, followed by filtered historical simulation, whereas the parametric approach has the worst VaR forecasting performance for all the levels. Furthermore, VaR models underestimate the true risk, whereas ES models overestimate the true risk, indicating that the ES risk measure is more conservative than the VaR risk measure. Additionally, based on back-testing, the VaR provides a better risk forecast than the ES since the ES highly overestimates the true risk. Notably, long memory is important for the ES estimate, whereas both the long memory and the leverage effect are crucial for the VaR estimate. Finally, via in-sample VaR forecasts in regard to the low level, it is found that long memory is important for the non-GFC period, whereas the distribution effect is crucial for the GFC period. On the other hand, with regard to the high level, the distribution effect is crucial for both the non-GFC and the GFC period. These results seem to be consistent with those found in the out-of-sample VaR forecasts. In accordance with these results, several important policy implications are proposed in this study.</description><subject>Distribution effects</subject><subject>Economic crisis</subject><subject>Economic models</subject><subject>Expected shortfall</subject><subject>Global financial crisis</subject><subject>Indexes</subject><subject>Leverage effect</subject><subject>Long memory</subject><subject>Rates of return</subject><subject>Risk assessment</subject><subject>Stock exchanges</subject><subject>Studies</subject><subject>Value-at-risk</subject><subject>Volatility</subject><issn>1062-9408</issn><issn>1879-0860</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNp9kEtPwzAQhCMEEqXwC7hY4tqEtfNwcuCAqvKQKnGBs-XY68ppEhc7rdR_j0s5cxrLnvHufElyTyGjQKvHLhtlhyZjQIsMeAaQXyQzWvMmhbqCy3iGiqVNAfV1chNCBwBFxfkswdWws94q2RM5yv4YbCDOkN6NGzLg4PxxQXo8oJcbXESLJtqGydt2P1k3EjQG1RSIcZ6EyaktGaTf4kS8DVuCYbKDnDDcJldG9gHv_nSefL2sPpdv6frj9X35vE5V3pRTqnVLFaubRlLgbUOZYUUOhue0YPFFtrku2pMA47ppC1Sl0rGYzFlZ03g_Tx7O_-68-97H8aJzex97BUErxjmLMMroys8u5V0IHo3Y-binPwoK4sRTdOKXpzjxFMBF5BlTT-cUxgIHi14EZXFUqK2PDIR29t_8D6eEgIk</recordid><startdate>20141101</startdate><enddate>20141101</enddate><creator>Su, Jung-Bin</creator><general>Elsevier Inc</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20141101</creationdate><title>Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates</title><author>Su, Jung-Bin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Distribution effects</topic><topic>Economic crisis</topic><topic>Economic models</topic><topic>Expected shortfall</topic><topic>Global financial crisis</topic><topic>Indexes</topic><topic>Leverage effect</topic><topic>Long memory</topic><topic>Rates of return</topic><topic>Risk assessment</topic><topic>Stock exchanges</topic><topic>Studies</topic><topic>Value-at-risk</topic><topic>Volatility</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Su, Jung-Bin</creatorcontrib><collection>CrossRef</collection><jtitle>The North American journal of economics and finance</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Su, Jung-Bin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates</atitle><jtitle>The North American journal of economics and finance</jtitle><date>2014-11-01</date><risdate>2014</risdate><volume>30</volume><spage>1</spage><epage>39</epage><pages>1-39</pages><issn>1062-9408</issn><eissn>1879-0860</eissn><abstract>•For out-of-sample VaR forecasts distribution effect is crucial for high level.•The WHS (the parametric approach) has the best (worst) VaR forecasting performance.•VaR (ES) models underrate (overrate) the risk and thus ES is more cautious than VaR.•Long memory (long memory and leverage effect) is major for ES (VaR) estimate.•Regarding in-sample VaR forecasts distribution effect is crucial for GFC period. In this study, eight generalized autoregressive conditional heteroskedasticity (GARCH) types of variance specifications and two return distribution settings, the normal and skewed generalized Student's t (SGT) of Theodossiou (1998), totaling nine GARCH-based models, are utilized to forecast the volatility of six stock indices, and then both the out-of-sample-period value-at-risk (VaR) and the expected shortfall (ES) are estimated following the rolling window approach. Moreover, the in-sample VaR is estimated for both the global financial crisis (GFC) period and the non-GFC period. Subsequently, through several accuracy measures, nine models are evaluated in order to explore the influence of long memory, leverage, and distribution effects on the performance of VaR and ES forecasts. As shown by the empirical results of the nine models, the long memory, leverage, and distribution effects subsist in the stock markets. Moreover, regarding the out-of-sample VaR forecasts, long memory is the most important effect, followed by the leverage effect for the low level, whereas the distribution effect is crucial for the high level. As for the three VaR approaches, weighted historical simulation achieves the best VaR forecasting performance, followed by filtered historical simulation, whereas the parametric approach has the worst VaR forecasting performance for all the levels. Furthermore, VaR models underestimate the true risk, whereas ES models overestimate the true risk, indicating that the ES risk measure is more conservative than the VaR risk measure. Additionally, based on back-testing, the VaR provides a better risk forecast than the ES since the ES highly overestimates the true risk. Notably, long memory is important for the ES estimate, whereas both the long memory and the leverage effect are crucial for the VaR estimate. Finally, via in-sample VaR forecasts in regard to the low level, it is found that long memory is important for the non-GFC period, whereas the distribution effect is crucial for the GFC period. On the other hand, with regard to the high level, the distribution effect is crucial for both the non-GFC and the GFC period. These results seem to be consistent with those found in the out-of-sample VaR forecasts. In accordance with these results, several important policy implications are proposed in this study.</abstract><cop>Greenwich</cop><pub>Elsevier Inc</pub><doi>10.1016/j.najef.2014.07.003</doi><tpages>39</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1062-9408
ispartof The North American journal of economics and finance, 2014-11, Vol.30, p.1-39
issn 1062-9408
1879-0860
language eng
recordid cdi_proquest_journals_1627728605
source ScienceDirect Freedom Collection
subjects Distribution effects
Economic crisis
Economic models
Expected shortfall
Global financial crisis
Indexes
Leverage effect
Long memory
Rates of return
Risk assessment
Stock exchanges
Studies
Value-at-risk
Volatility
title Empirical analysis of long memory, leverage, and distribution effects for stock market risk estimates
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-21T09%3A49%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Empirical%20analysis%20of%20long%20memory,%20leverage,%20and%20distribution%20effects%20for%20stock%20market%20risk%20estimates&rft.jtitle=The%20North%20American%20journal%20of%20economics%20and%20finance&rft.au=Su,%20Jung-Bin&rft.date=2014-11-01&rft.volume=30&rft.spage=1&rft.epage=39&rft.pages=1-39&rft.issn=1062-9408&rft.eissn=1879-0860&rft_id=info:doi/10.1016/j.najef.2014.07.003&rft_dat=%3Cproquest_cross%3E3506660071%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c395t-ddb1c2899a107b912f2430f73142b1cab3d4bcab3027d9b4ec5cd062a32581ab3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1627728605&rft_id=info:pmid/&rfr_iscdi=true