{"title":"Modelling time-varying volatility in the Indian stock returns: Some empirical evidence","authors":"Trilochan Tripathy , Luis A. Gil-Alana","doi":"10.1016/j.rdf.2015.04.002","DOIUrl":null,"url":null,"abstract":"<div><p>This paper models time-varying volatility in one of the Indian main stock markets, namely, the National Stock Exchange (NSE) located in Mumbai, investigating whether it has been affected by the recent global financial crisis. A Chow test indicates the presence of a structural break. Both symmetric and asymmetric GARCH models suggest that the volatility of NSE returns is persistent and asymmetric and has increased as a result of the crisis. The model under the Generalized Error Distribution appears to be the most suitable one. However, its out-of-sample forecasting performance is relatively poor.</p></div>","PeriodicalId":39052,"journal":{"name":"Review of Development Finance","volume":"5 2","pages":"Pages 91-97"},"PeriodicalIF":0.7000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/j.rdf.2015.04.002","citationCount":"15","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Review of Development Finance","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1879933715000032","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
引用次数: 15
Abstract
This paper models time-varying volatility in one of the Indian main stock markets, namely, the National Stock Exchange (NSE) located in Mumbai, investigating whether it has been affected by the recent global financial crisis. A Chow test indicates the presence of a structural break. Both symmetric and asymmetric GARCH models suggest that the volatility of NSE returns is persistent and asymmetric and has increased as a result of the crisis. The model under the Generalized Error Distribution appears to be the most suitable one. However, its out-of-sample forecasting performance is relatively poor.