简介:Inthispaper,theso-calledlocallikelihoodmethodissuggestedforsolvingthechangepointproblemswhenthedataaredistributedasmultivariatenormal.Thedetectionproceduresproposednotonlyprovidestronglyeonsistentestimatesforthenumberandlocationsofthechangepoints,butalsosimplifysignificantlythecomputation.
简介:Inthispaper,twokindsofKullback-Leiblercriteriawithappropriateconstraintsareproposedtoconstructempiricallikelihoodconfidenceintervalsforthemeanofrightcensoreddata.ItisshownthatoneofthecriteriaisequivalenttoAdimari's(1997)procedure,andtheothersharesthesameasymptoticbehavior.
简介:Inthispaperweconsidersomerelatednegativehypergeometricdistributionsarisingfromtheproblemofsamplingwithoutreplacementfromanurncontainingballsofdifferentcoloursandindifferentproportionsbutstoppingonlyaftersomespecificnumberofballsofdifferentcolourshavebeenobtained.Withtheaidofsomesimplerecurrencerelationsandidentitiesweobtaininthecaseoftwocoloursthemomentsforthemaximumnegativehypergeometricdistribution,theminimumnegativehypergeometricdistribution,thelikelihoodrationegativehypergeometricdistributionandconsequentlythelikelihoodproportionalnegativehypergeometricdistributiuon.TotheextentthatthesamplingschemeisapplicabletomodellingdataasillustratedwithabiologicalexampleandinfactmanysituationsofestimatingBernoulliparametersforbinarytraitswithinafinitepopulation,theseareimportantfirst-stepresults.
简介:1.IntroductionThemethodoflikelihoodintroducedbyFisheriscertainlyoneofthemostcommonlyusedtechniquesforparametricmodels.Recentlythelikelihoodhasalsobeenshowntobeveryusefulinnonparametriccontexts.O...II--31hasintroducedempiricallikelihoodratiostatistics...
简介:
简介:Inthispaperanewtext-independentspeakerverificationmethodGSMSVisproposedbasedonlikelihoodscorenormalization.Inthisnovelmethodaglobalspeakermodelisestablishedtorepresenttheuniversalfeaturesofspeechandnormalizethelikelihoodscore.Statisticalanalysisdemonstratesthatthisnormalizationmethodcanremovecommonfactorsofspeechandbringthedifferencesbetweenspeakersintoprominence.Asaresulttheequalerrorrateisdecreasedsignificantly,verificationprocedureisacceleratedandsystemadaptabilitytospeakingspeedisimproved.
简介:
简介:Blindidentification-blindequalizationforFiniteImpulseResponse(FIR)MultipleInput-MultipleOutput(MIMO)channelscanbereformulatedastheproblemofblindsourcesseparation.Ithasbeenshownthatblindidentificationviadecorrelatingsub-channelsmethodcouldrecovertheinputsources.TheBlindIdentificationviaDecorrelatingSub-channels(BIDS)algorithmfirstconstructsasetofdecorrelators,whichdecorrelatetheoutputsignalsofsubchannels,andthenestimatesthechannelmatrixusingthetransferfunctionsofthedecorrelatorsandfinallyrecoverstheinputsignalusingtheestimatedchannelmatrix.Inthispaper,anewapproximationoftheinputsourceforFIR-MIMOchannelsbasedonthemaximumlikelihoodsourceseparationmethodisproposed.TheproposedmethodoutperformsBIDSinthepresenceofadditivewhiteGaussiannoise.