Statistical-hypothesis-testing统计假设检验毕业论文外文文献翻译及原文

-1-毕业设计（论文）外文文献翻译文献、资料中文题目：统计假设检验文献、资料英文题目：Statisticalhypothesistesting文献、资料来源：文献、资料发表（出版）日期：院（部）：专业：班级：姓名：学号：指导教师：翻译日期：2017.02.14-2-StatisticalhypothesistestingAdrianaAlbu，LoredanaUngureanuPolitehnicaUniversityTimisoara,[e-mail]imisoara,[e-mail],wepresentaBayesianstatisticalhypothesistestinginspection,testingtheoryandtheprocessMentionedhypothesistestingintherealworldandtheimportanceof,andsuccessfultestoftheNotes.KeywordsBayesianhypothesistesting;Bayesianinference;TestofsignificanceIntroductionAstatisticalhypothesistestisamethodofmakingdecisionsusingdata,whetherfromacontrolledexperimentoranobservationalstudy(notcontrolled).Instatistics,aresultiscalledstatisticallysignificantifitisunlikelytohaveoccurredbychancealone,accordingtoapre-determinedthresholdprobability,thesignificancelevel.ThephrasetestofsignificancewascoinedbyRonaldFisher:Criticaltestsofthiskindmaybecalledtestsofsignificance,andwhensuchtestsareavailablewemaydiscoverwhetherasecondsampleisorisnotsignificantlydifferentfromthefirst.[1]Hypothesistestingissometimescalledconfirmatorydataanalysis,incontrasttoexploratorydataanalysis.Infrequencyprobability,thesedecisionsarealmostalwaysmadeusingnull-hypothesistests.TheseareteststhatanswerthequestionAssumingthatthenullhypothesisistrue,whatistheprobabilityofobservingavaluefortheteststatisticthatisatleastasextremeasthevaluethatwasactuallyobserved?)2[]Moreformally,theyrepresentanswerstothequestion,posedbeforeundertakinganexperiment,ofwhatoutcomesoftheexperimentwouldleadtorejectionofthenullhypothesisforapre-specifiedprobabilityofanincorrectrejection.Oneuseofhypothesistestingisdecidingwhetherexperimentalresultscontainenoughinformationtocastdoubtonconventionalwisdom.Statisticalhypothesistestingisakeytechniqueoffrequentiststatisticalinference.TheBayesianapproachtohypothesistestingistobaserejectionofthehypothesisontheposteriorprobability.[3][4]Otherapproachestoreachingadecisionbasedondataareavailableviadecisiontheoryandoptimaldecisions.Thecriticalregionofahypothesistestisthesetofalloutcomeswhichcausethenullhypothesistoberejectedinfavorofthealternativehypothesis.ThecriticalregionisusuallydenotedbytheletterC.One-sampletestsareappropriatewhenasampleisbeingcomparedtothepopulationfromahypothesis.Thepopulationcharacteristicsareknownfromtheoryorarecalculatedfromthepopulation.Two-sampletestsareappropriateforcomparingtwosamples,typicallyexperimentalandcontrolsamplesfromascientificallycontrolledexperiment.Pairedtestsareappropriateforcomparingtwosampleswhereitisimpossibletocontrolimportantvariables.Ratherthancomparingtwosets,membersarepairedbetweensamples-3-sothedifferencebetweenthemembersbecomesthesample.Typicallythemeanofthedifferencesisthencomparedtozero.Z-testsareappropriateforcomparingmeansunderstringentconditionsregardingnormalityandaknownstandarddeviation.T-testsareappropriateforcomparingmeansunderrelaxedconditions(lessisassumed).Testsofproportionsareanalogoustotestsofmeans(the50%proportion).Chi-squaredtestsusethesamecalculationsandthesameprobabilitydistributionfordifferentapplications:Chi-squaredtestsforvarianceareusedtodeterminewhetheranormalpopulationhasaspecifiedvariance.Thenullhypothesisisthatitdoes.Chi-squaredtestsofindependenceareusedfordecidingwhethertwovariablesareassociatedorareindependent.Thevariablesarecategoricalratherthannumeric.Itcanbeusedtodecidewhetherleft-handednessiscorrelatedwithlibertarianpolitics(ornot).Thenullhypothesisisthatthevariablesareindependent.Thenumbersusedinthecalculationaretheobservedandexpectedfrequenciesofoccurrence(fromcontingencytables).Chi-squaredgoodnessoffittestsareusedtodeterminetheadequacyofcurvesfittodata.Thenullhypothesisisthatthecurvefitisadequate.Itiscommontodeterminecurveshapestominimizethemeansquareerror,soitisappropriatethatthegoodness-of-fitcalculationsumsthesquarederrors.F-tests(analysisofvariance,ANOVA)arecommonlyusedwhendecidingwhethergroupingsofdatabycategoryaremeaningful.Ifthevarianceoftestscoresoftheleft-handedinaclassismuchsmallerthanthevarianceofthewholeclass,thenitmaybeusefultostudyleftiesasagroup.Thenullhypothesisisthattwovariancesarethesame-sotheproposedgroupingisnotmeaningful.ThetestingprocessInthestatisticalliterature,statisticalhypothesistestingplaysafundamentalrole.Theusuallineofreasoningisasfollows:1.Thereisaninitialresearchhypothesisofwhichthetruthisunknown.2.Thefirststepistostatetherelevantnullandalternativehypotheses.Thisisimportantasmis-statingthehypotheseswillmuddytherestoftheprocess.Specifically,thenullhypothesisallowsattachinganattribute:itshouldbechoseninsuchawaythatitallowsustoconcludewhetherthealternativehypothesiscaneitherbeacceptedorstaysundecidedasitwasbeforethetest.[9]3.Thesecondstepistoconsiderthestatisticalassumptionsbeingmadeaboutthesampleindoingthetest;forexample,assumptionsaboutthestatisticalindependenceorabouttheformofthedistributionsoftheobservations.Thisisequallyimportantasinvalidassumptionswillmeanthattheresultsofthetestareinvalid.4.Decidewhichtestisappropriate,and