introduction to financial time series analysis-filtering and smoothing techniques

introduction to financial time series analysis-filtering and smoothing techniques

ID:7289651

大小:517.79 KB

页数:46页

时间:2018-02-10

introduction to financial time series analysis-filtering and smoothing techniques_第1页
introduction to financial time series analysis-filtering and smoothing techniques_第2页
introduction to financial time series analysis-filtering and smoothing techniques_第3页
introduction to financial time series analysis-filtering and smoothing techniques_第4页
introduction to financial time series analysis-filtering and smoothing techniques_第5页
资源描述:

《introduction to financial time series analysis-filtering and smoothing techniques》由会员上传分享,免费在线阅读,更多相关内容在工程资料-天天文库

1、Chapter3IntroductiontofinancialtimeseriesanalysisFordetailsseetextbooksbyMakridakisetal.[1989],Brockwelletal.[1991]andTsay[2002].3.1PrologueAtimeseriesisasetofmeasurementsrecordedonasingleunitovermultipletimeperiods.Moregenerally,atimeseiesisasetofstatistics,usuallycollectedatregularint

2、ervals,andoccurringnaturallyinmanyapplicationareassuchaseconomics,finance,environmental,medecine,etc.Inordertoanalyseandmodelpriceseriestodevelopefficientquantitativetrading,wedefinereturnsasthedifferencesofthelogarithmsoftheclosingpriceseries,andwefitmodelstothesereturns.Further,toconstru

3、ctefficientsecurityportfoliosmatchingtheriskprofileandneedsofindividualinvestorsweneedtoestimatethevariouspropertiesofthesecuritiesconsititutingsuchaportfolio.Hence,modellingandforecastingpricereturnandvolatilityisthemaintaskoffinancialresearch.Focusingonclosingpricesrecordedattheendofeac

4、htradingday,wearguethatitisthetradingdayratherthanthechronologicaldaywhichisrelevantsothatconstructingtheseriesfromavailabledata,weobtainaprocessequallyspacedintherelevanttimeunit.WesawinSection(2.1.5)thatafirststeptowardsforecastingfinancialtimeserieswastoconsidersometypeoftechnicalindi

5、catorsormathematicalstatisticswithpriceforecastingcapability,hopingthathistorytrendswouldrepeatitself.However,followingthisapproachwecannotassesstheuncertaintyinherentintheforecast,andassuch,wecannotmeasuretheerrorofforecast.Analternativeistoconsiderfinancialtimeseriesanalysiswhichiscon

6、cernedwiththeoryandpracticeofassetvaluationovertime.Whilethemethodsoftimeseriesanalysispre-datethoseforgeneralstochasticprocessesandMarkovChains,theiraimsaretodescribeandsummarisetimeseriesdata,fitlow-dimensionalmodels,andmakeforecasts.Eventhoughitisahighlyempiricaldiscipline,theoryform

7、sthefoundationformakinginference.However,bothfinancialtheoryanditsempiricaltimeseriescontainsomeelementsofuncertainty.Forinstance,therearevariousdefinitionsofassetvolatility,andinaddition,volatilityisnotdirectlyobservable.Consequently,statisticaltheoryandmethodsplayanimportantroleinfina

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。