嚴(yán)平穩(wěn)過程條件密度非參數(shù)估計(jì)及其在風(fēng)險(xiǎn)分析中的應(yīng)用.pdf

1、上海大學(xué)碩士學(xué)位論文嚴(yán)平穩(wěn)過程條件密度非參數(shù)估計(jì)及其在風(fēng)險(xiǎn)分析中的應(yīng)用姓名：謝瀟衡申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：系統(tǒng)分析與集成指導(dǎo)教師：何幼樺20080401AbstractThispaperfocusesonnonparametricestimationforconditionaldensityofstrictlystationaryprocessesUndertheassumptionofa—mixingprocess，analyzest

2、heerrorproblemsforakernelestimatoroftheconditionalprobabilitydensityfunctiontheoreticallyexplorestheoptimalbandwidthforestimatekernelfunction，andappliesitinrealrisktimeseriesInchapter2，thebiasandmeansquareerrorforakernel

3、estimatoroftheconditionalprobabilitydensityfunctionarestudiedundertheassumptionofamixingstrictlystationaryprocessAnasymptoticallyoptimalbandwidthisgivenandtheresultsareillustratedwithS&P500indexTllispartwillbepublishedin

4、OperationsResearchTransactionsBasedonthistheorychapter3and4useittodealwithdifferentpracticeoffinancialtimeseriesrespectivelyChapter3proposesanonparametricmethodtotestthekurtosisandconditionalkurtosisforrisktimeseriesWeap

5、plythismethodtoS&P500indexShanghaiCompositeindexdailyreturnsandsimulatedGARCHdatatoverifytheefficiencyItispartlypromisedby乃讓m口f巧ShanghaiUniversity(EnglishEdition)Undertheassumptionofthattheyieldseriesisastrictlystationar

6、yprocess，anequationwhichtheVaRattimetgivenhistoricaldatashouldbesatisfiedisprovidedinchapter4Atthesametime，ananalyticformulaforCVaRisalsobroughtforwardWetakeS&P5002usanexampletodiscusshowthelengthofhistoricaldatabeforetw

7、illaffecttheestimateofVaRandCVaRattimet，thencomparetheVaRbyourmethodandthatbyGARCHmodelAtlast，usingdifferentlengthofsampletoestimateCVaRshowsthatourmethodisrobustTheresultsinthischapterwerepublishedin如Ⅱm越∥ShanghaiUnivers