时间序列分析(r语言实现)

时间序列分析(r语言实现)

ID:30481265

大小:2.74 MB

页数:335页

时间:2018-12-30

时间序列分析(r语言实现)_第1页
时间序列分析(r语言实现)_第2页
时间序列分析(r语言实现)_第3页
时间序列分析(r语言实现)_第4页
时间序列分析(r语言实现)_第5页
资源描述:

《时间序列分析(r语言实现)》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、TimeseriesIntroductionSimpletimeseriesmodelsARIMAValidatingamodelSpectralAnalysisWaveletsDigitalSignalProcessing(DSP)Modelingvolatility:GARCHmodels(GeneralizedAutoRegressiveConditionnalHeteroscedasticity)MultivariatetimeseriesState-SpaceModelsandKalmanFilteringNon-lineart

2、imeseriesandchaosOthertimesDiscrete-valuedtimeseries:MarkovchainsandbeyondVariantsofMarkovchainsUntackledsubjectsTOSORTThischaptercontrastswiththetopicswehaveseenuptonow:wewereinterestedinthestudyofseveralindependantrealizationsofasimplestatisticalprocess(e.g.,agaussianra

3、ndomvariable,oramixtureofgaussians,oralinearmodel);weshallnowfocusonasinglerealizationofamorecomplexprocess.Hereisthestructureofthischapter.Afteranintroduction,motivatingthenotionofatimeseriesandgivingseveralexamples,simulatedorreal,weshallpresenttheclassicalmodelsoftimes

4、eries(AR,MA,ARMA,ARIMA,SARIMA),thatproviderecipestobuildtimeserieswithdesiredproperties.Weshallthenpresentspectralmethods,thatfocusonthediscoveryofperiodicelementsintimeseries.Thesimplicityofthosemodelsmakesthemamenable,buttheycannotdescribethepropertiesofsomereal-worldti

5、meseries:non-linearmethods,builtupontheclassicalmodels(GARCH)arecalledfor.State-SpaceModelsandtheKalmanfilterfollowthesamevein:theyassumethatthedataisbuildfromlinearalgebra,butthatwedonotobserveeverything--thereare"hidden"(unobserved,latent)variables.Someofthosemethodsrea

6、dilygeneralizetohigherdimensions,i.e.,tothestudyofvector-valuedtime-series,i.e.,tothestudyofseveralrelatedtimeseriesatthesametime--butsomenewphenomenaappear(e.g.,cointegration).Furthermore,ifthenumberoftimeseriestostudybecomestoolarge,thevectormodelshavetoomanyparameterst

7、obeuseful:weentertherealmofpaneldata.Weshallthenpresentsomelessmainstreamideas:insteadoflinearalgebra,timeseriescanbeproducedbyanalytical(read:differentialequations)orprocedural(read:chaos,fractals)means.Wefinallypresentgeneralizationsoftimeseries:stochasticprocesses,inwh

8、ichtimeiscontinuous;irregulartimeseries,inwhichtimeisdiscretebutirregular;anddiscrete-valuedtime

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。