Statisticsfor

BusinessandEconomics(14e)

MetricVersionAnderson,Sweeney,Williams,Camm,Cochran,Fry,Ohlmann?2020CengageLearning1?2020Cengage.Maynotbescanned,copiedorduplicated,orpostedtoapubliclyaccessiblewebsite,inwholeorinpart,exceptforuseaspermittedinalicensedistributedwithacertainproductorserviceorotherwiseonapassword-protectedwebsiteorschool-approvedlearningmanagementsystemforclassroomuse.Chapter1-DataandStatistics1.1-ApplicationsinBusinessandEconomics1.2-Data1.3-DataSources1.4-DescriptiveStatistics1.5-StatisticalInference1.6-Analytics1.7-BigDataandDataMining1.8-ComputersandStatisticalAnalysis1.9-EthicalGuidelinesforStatisticalPractice2WhatIsStatistics?Thetermstatisticscanrefertonumericalfactssuchasaverages,medians,percentages,andmaximumsthathelpusunderstandavarietyofbusinessandeconomicsituations.Statisticscanalsorefertotheartandscienceofcollecting,analyzing,presenting,andinterpretingdata.3ApplicationsinBusinessandEconomics(1of2)AccountingPublicaccountingfirmsusestatisticalsamplingprocedureswhenconductingauditsfortheirclients.EconomicsEconomistsusestatisticalinformationinmakingforecastsaboutthefutureoftheeconomyorsomeaspectofit.FinanceFinancialadvisorsuseprice-earningsratiosanddividendyieldstoguidetheirinvestmentadvice.4ApplicationsinBusinessandEconomics(2of2)MarketingElectronicpoint-of-salescannersatretailcheckoutcountersareusedtocollectdataforavarietyofmarketingresearchapplications.ProductionAvarietyofstatisticalqualitycontrolchartsareusedtomonitortheoutputofaproductionprocess.InformationSystemsAvarietyofstatisticalinformationhelpsadministratorsassesstheperformanceofcomputernetworks.5DataandDataSetsDataarethefactsandfigurescollected,analyzed,andsummarizedforpresentationandinterpretation.Allthedatacollectedinaparticularstudyarereferredtoasthedatasetforthestudy.6Elements,Variables,andObservationsElementsaretheentitiesonwhichdataarecollected.Avariableisacharacteristicofinterestfortheelements.Thesetofmeasurementsobtainedforaparticularelementiscalledanobservation.Adatasetwithnelementscontainsnobservations.Thetotalnumberofdatavaluesinacompletedatasetisthenumberofelementsmultipliedbythenumberofvariables.7Data,DataSets,Elements,Variables,andObservationsCompanyStockExchangeAnnualSalesinmillionsofdollarsEarningspershareindollarsDataramNQ73.100.86EnergySouthN74.001.67KeystoneN365.700.86LandCareNQ111.400.33PsychemedicsN17.600.138ScalesofMeasurement(1of6)ScalesofmeasurementincludeNominalOrdinalIntervalRatioThescaledeterminestheamountofinformationcontainedinthedata.Thescaleindicatesthedatasummarizationandstatisticalanalysesthataremostappropriate.9ScalesofMeasurement(2of6)Nominalscale Dataarelabelsornamesusedtoidentifyanattributeoftheelement.Anonnumericlabelornumericcodemaybeused.ExampleStudentsofauniversityareclassifiedbytheschoolinwhichtheyareenrolledusinganonnumericlabelsuchasBusiness,Humanities,Education,andsoon.Alternatively,anumericcodecouldbeusedfortheschoolvariable(e.g.,1denotesBusiness,2denotesHumanities,3denotesEducation,andsoon).10ScalesofMeasurement(3of6)OrdinalscaleThedatahavethepropertiesofnominaldataandtheorderorrankofthedataismeaningful.Anonnumericlabelornumericcodemaybeused.ExampleStudentsofauniversityareclassifiedbytheirclassstandingusinganonnumericlabelsuchasFreshman,Sophomore,Junior,orSenior.Alternatively,anumericcodecouldbeusedfortheclassstandingvariable(e.g.,1denotesFreshman,2denotesSophomore,andsoon).11ScalesofMeasurement(4of6)IntervalscaleThedatahavethepropertiesofordinaldata,andtheintervalbetweenobservationsisexpressedintermsofafixedunitofmeasure.Intervaldataarealwaysnumeric.ExampleMelissahasanSATscoreof1985,whileKevinhasanSATscoreof1880.Melissascored105pointsmorethanKevin.12ScalesofMeasurement(5of6)RatioscaleDatahaveallthepropertiesofintervaldataandtheratiooftwovaluesismeaningful.Ratiodataarealwaysnumerical.Zerovalueisincludedinthescale.Example:Priceofabookataretailstoreis$200,whilethepriceofthesamebooksoldonlineis$100.Theratiopropertyshowsthatretailstoreschargetwicetheonlineprice.13CategoricalandQuantitativeDataDatacanbefurtherclassifiedasbeingcategoricalorquantitative.Thestatisticalanalysisthatisappropriatedependsonwhetherthedataforthevariablearecategoricalorquantitative.Ingeneral,therearemorealternativesforstatisticalanalysiswhenthedataarequantitative.14CategoricalDataLabelsornamesareusedtoidentifyanattributeofeachelementOftenreferredtoasqualitativedataUseeitherthenominalorordinalscaleofmeasurementCanbeeithernumericornonnumericAppropriatestatisticalanalysesareratherlimited15QuantitativeDataQuantitativedataindicatehowmanyorhowmuch.Quantitativedataarealwaysnumeric.Ordinaryarithmeticoperationsaremeaningfulforquantitativedata.16ScalesofMeasurement(6of6)17Cross-SectionalDataCross-sectionaldataarecollectedatthesameorapproximatelythesamepointintime.ExampleDatadetailingthenumberofbuildingpermitsissuedinNovember2013ineachofthecountiesofOhio.18TimeSeriesData(1of2)Timeseriesdataarecollectedoverseveraltimeperiods.ExampleDatadetailingthenumberofbuildingpermitsissuedinLucasCounty,Ohioineachofthelast36months.Graphsoftimeseriesdatahelpanalystsunderstandwhathappenedinthepastidentifyanytrendsovertime,andprojectfuturelevelsforthetimeseries19TimeSeriesData(2of2)GraphofTimeSeriesData20DataSources(1of5)ExistingSourcesInternalcompanyrecords–almostanydepartmentBusinessdatabaseservices–DowJones&Co.Governmentagencies–U.S.DepartmentofLaborIndustryassociations–TravelIndustryAssociationofAmericaSpecial-interestorganizations–GraduateManagementAdmissionCouncil(GMAT)Internet–moreandmorefirms21DataSources(2of5)DataAvailableFromInternalCompanyRecordsRecordSomeoftheDataAvailableEmployeerecordsName,address,socialsecuritynumberProductionrecordsPartnumber,quantityproduced,directlaborcost,materialcostInventoryrecordsPartnumber,quantityinstock,

reorderlevel,economicorderquantitySalesrecordsProductnumber,salesvolume,sales

volumebyregionCreditrecordsCustomername,creditlimit,accounts

receivablebalanceCustomerprofileAge,gender,income,householdsize22DataSources(3of5)DataAvailableFromSelectedGovernmentAgenciesU.S.GovernmentAgencyWebaddressSomeoftheDataAvailableCensusBureauPopulationdata,numberof

households,householdincomeFederalReserveBoardDataonmoneysupply,exchange

rates,discountratesOfficeofMgmt.&

Budget/ombDataonrevenue,expenditures,debt

offederalgovernmentDepartmentof

CommerceDataonbusinessactivity,valueof

shipments,profitbyindustryBureauofLaborStatisticsCustomerspending,unemployment

rate,hourlyearnings,safetyrecord23DataSources(4of5)StatisticalStudies–ObservationalInobservational(nonexperimental)studiesnoattemptismadetocontrolorinfluencethevariablesofinterest. Example-SurveyStudiesofsmokersandnonsmokersareobservationalstudiesbecauseresearchersdonotdetermineorcontrolwhowillsmokeandwhowillnotsmoke.24DataSources(5of5)StatisticalStudies–ExperimentalInexperimentalstudiesthevariableofinterestisfirstidentified.Thenoneormoreothervariablesareidentifiedandcontrolledsothatdatacanbeobtainedabouthowtheyinfluencethevariableofinterest.Thelargestexperimentalstudyeverconductedisbelievedtobethe1954PublicHealthServiceexperimentfortheSalkpoliovaccine.NearlytwomillionU.S.children(grades1-3)wereselected.25DataAcquisitionConsiderationsTimeRequirementSearchingforinformationcanbetimeconsuming.Informationmaynolongerbeusefulbythetimeitisavailable.CostofAcquisitionOrganizationsoftenchargeforinformationevenwhenitisnottheirprimarybusinessactivity.DataErrorsUsinganydatathathappentobeavailableorwereacquiredwithlittlecarecanleadtomisleadinginformation.26DescriptiveStatisticsMostofthestatisticalinformationinnewspapers,magazines,companyreports,andotherpublicationsconsistsofdatathataresummarizedandpresentedinaformthatiseasytounderstand.Suchsummariesofdata,whichmaybetabular,graphical,ornumerical,arereferredtoasdescriptivestatistics.ExampleThemanagerofHudsonAutowouldliketohaveabetterunderstandingofthecostofpartsusedintheenginetune-upsperformedinhershop.Sheexamines50customerinvoicesfortune-ups.Thecostsofparts,roundedtothenearestdollar,arelistedonthenextslide.27Example:HudsonAutoRepairSampleofPartsCost($)for50Tune-ups91,78,93,57,75,52,99,80,97,6271,69,72,89,66,75,79,75,72,76104,74,62,68,97,105,77,65,80,10985,97,88,68,83,68,71,69,67,7462,82,98,101,79,105,79,69,62,7328TabularSummary:FrequencyandPercentFrequencyPartsCost($)FrequencyPercentFrequency50-5924%60-691326%70-791632%80-89714%90-99714%100-109510%TOTAL50100%29GraphicalSummary:HistogramExample:HudsonAuto30NumericalDescriptiveStatisticsThemostcommonnumericaldescriptivestatisticisthemean(oraverage).Themeandemonstratesameasureofthecentraltendency,orcentrallocationofthedataforavariable.Hudson’smeancostofparts,basedonthe50tune-upsstudiedis$79(foundbysummingupthe50costvaluesandthendividingby50).31StatisticalInferencePopulation:Thesetofallelementsofinterestinaparticularstudy.Sample:Asubsetofthepopulation.Statisticalinference:Theprocessofusingdataobtainedfromasampletomakeestimatesandtesthypothesesaboutthecharacteristicsofapopulation.Census:Collectingdatafortheentirepopulation.Samplesurvey:Collectingdataforasample.32ProcessofStatisticalInferenceExample:HudsonAuto33Analytics

Analyticsisthescientificprocessoftransformingdataintoinsightformakingbetterdecisions.Techniques:Descriptiveanalytics:Thisdescribeswhathashappenedinthepast.Predictiveanalytics:Usemodelsconstructedfrompastdatatopredictthefutureortoassesstheimpactofonevariableonanother.Prescriptiveanalytics:Thesetofanalyticaltechniquesthatyieldabestcourseofaction.34BigDataandDataMiningBigdata:Largeandcomplexdataset.ThreeV’sofBigdata:Volume:AmountofavailabledataVelocity:SpeedatwhichdataiscollectedandprocessedVariety:Differentdatatypes35DataWarehousingDatawarehousingistheprocessofcapturing,storing,andmaintainingthedata.Organizationsobtainlargeamountsofdataonadailybasisbymeansofmagneticcardreaders,barcodescanners,pointofsaleterminals,andtouchscreenmonitors.Wal-Martcapturesdataon20-30milliontransactionsperday.Visaprocesses6,800paymenttransactionspersecond.36DataMiningMethodsfordevelopingusefuldecision-makinginformationfromlargedatabases.Usingacombinationofproceduresfromstatistics,mathematics,andcomputerscience,analysts“minethedata”toconvertitintousefulinformation.Themosteffectivedataminingsystemsuseautomatedprocedurestodiscoverrelationshipsinthedataandpredictfutureoutcomespromptedbygeneralandevenvaguequeriesbytheuser.37DataMiningApplicationsThemajorapplicationsofdatamininghavebeenmadebycompanieswithastrongconsumerfocussuchasretail,financial,andcommunicationfirms.Dataminingisusedtoidentifyrelatedproductsthatcustomerswhohavealreadypurchasedaspecificproductarealsolikelytopurchase(andthenpop-upsareusedtodrawattentiontothoserelatedproducts).Dataminingisalsousedtoidentifycustomerswhoshouldreceivespecialdiscountoffersbasedontheirpastpurchasingvolumes.38DataMiningRequirementsStatisticalmethodologysuchasmultipleregression,logisticregression,andcorrelationareheavilyused.Alsoneededarecomputersciencetechnologiesinvolvingartificialintelligenceandmachinelearning.Asignificantinvestmentintimeandmoneyisrequiredaswell.39DataMiningModelReliabilityFindingastatisticalmodelthatworkswellforaparticularsampleofdatadoesnotnecessarilymeanthatitcanbereliablyappliedtootherdata.Withtheenormousamountofdat