5/14/2017 EViewsHelp:PanelUnitRootTesting
UsersGuide:AdvancedUnivariateAnalysis:UnivariateTimeSeriesAnalysis:PanelUnitRootTesting
PanelUnitRootTesting
PerformingPanelUnitRootTestsinEViews
PanelUnitRootDetails
TestswithCommonUnitRootProcess
Levin,Lin,andChu
Breitung
Hadri
TestswithIndividualUnitRootProcesses
Im,Pesaran,andShin
FisherADFandFisherPP
SummaryofAvailablePanelUnitRootTests
Recentliteraturesuggeststhatpanelbasedunitroottestshavehigherpowerthanunitroottests
[Link]
roottests:Levin,LinandChu(2002),Breitung(2000),Im,PesaranandShin(2003),Fishertype
testsusingADFandPPtests(MaddalaandWu(1999)andChoi(2001)),andHadri(2000).
Whilethesetestsarecommonlytermedpanelunitroottests,theoretically,theyaresimply
multipleseriesunitrootteststhathavebeenappliedtopaneldatastructures(wherethepresenceof
crosssectionsgeneratesmultipleseriesoutofasingleseries).Accordingly,EViewssupportsthese
testsinsettingsinvolvingmultipleseries:asaseriesview(iftheworkfileispanelstructured),asa
groupview,orasapoolview.
PerformingPanelUnitRootTestsInEViews
Thefollowingdiscussionassumesthatyouarefamiliarwiththebasicsofbothunitroottestsand
panelunitroottests.
Tobegin,selectView/UnitRootTestfromthemenuofanEViewsgrouporpoolobject,orfrom
[Link]
unitroottesttheotherdialogsdifferslightly(fortestingusingapoolobject,thereisanadditional
fieldintheupperlefthandportionofthedialogwhereyoumustindicatethenameofthepoolseries
onwhichyouwishtoconductyourtestfortheseriesobjectinapanelworkfile,theUsebalanced
sampleoptionisnotpresent).
[Link] 1/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
Ifyouwishtoacceptthedefaultsettings,[Link]
setting,andwillcomputeafullsuiteofunitroottestsonthelevelsoftheseries,alongwitha
summaryoftheresults.
Tocustomizetheunitrootcalculations,[Link]
lefthandsideofthedialogdeterminethebasicstructureofthetestortests,whiletheoptionson
therighthandsideofthedialogcontroladvancedcomputationaldetailssuchasbandwidthorlag
selectionmethods,orkernelmethods.
Thedropdownmenuatthetopofthedialogiswhereyouwillchoosethetypeoftesttoperform.
Therearesixsettings:Summary,CommonrootLevin,Lin,Chu,CommonrootBreitung,
IndividualrootIm,Pesaran,Shin,IndividualrootFisherADF,IndividualrootFisher
PP,andHadri,[Link]
[Link]
rootindicatesthatthetestsareestimatedassumingacommonARstructureforalloftheseries
IndividualrootisusedfortestswhichallowfordifferentARcoefficientsineachseries.
WehavealreadypointedoutthattheSummarydefaultinstructsEViewstoestimatethefirstfiveof
thetests,whereapplicable,[Link]
testtypeallowsyoubettercontroloverthecomputationalmethodandprovidesadditionaldetailon
thetestresults.
[Link],
youmaychoosetoconducttheunitrootontheLevel,1stdifference,or2nddifferenceofyour
[Link],[Link]
Individualinterceptifyouwishtoincludeindividualfixedeffects,Individualinterceptsand
individualtrendstoincludebothfixedeffectsandtrends,orNonefornoregressors.
TheUsebalancedsampleoptionispresentonlyifyouareestimatingaPooloraGroupunitroot
[Link],EViewswilladjustyoursamplesothatonlyobservationswhereall
seriesvaluesarenotmissingwillbeincludedinthetestequations.
Dependingontheformofthetestorteststobecomputed,youwillbepresentedwithvarious
[Link]
differenceterms(Levin,Lin,andChu,Breitung,Im,Pesaran,andShin,FisherADF)theseoptions
[Link]
(Levin,Lin,andChu,FisherPP,Hadri),theoptionsrelatetothechoiceofbandwidthandkernel
type.
Foragrouporpoolunitroottest,theEViewsdefaultistouseautomaticselectionmethods:
informationmatrixcriterionbasedforthenumberoflagdifferenceterms(withautomaticselection
ofthemaximumlagtoevaluate),andtheAndrewsorNeweyWestmethodforbandwidthselection.
Forunitroottestsonaseriesinapanelworkfile,thedefaultbehaviorusesuserspecifiedoptions.
Ifyouwishtooverridethesesettings,[Link],for
example,selectafixed,userspecifiednumberoflagsbyenteringanumberintheUserspecified
[Link],[Link]
[Link] 2/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
criteriaforevaluatingtheoptimallaglengthmaybeselectedviathedropdownmenu(Akaike,
Schwarz,HannanQuinn,ModifiedAkaike,ModifiedSchwarz,ModifiedHannanQuinn),andyoumay
limitthenumberoflagstotryinautomaticselectionbyenteringanumberintheMaximumlags
[Link],youmayselectakerneltypefromthedropdownmenu
(Bartlett,Parzen,Quadraticspectral),andyoumayspecifyeitheranautomaticbandwidth
selectionmethod(Andrews,NeweyWest)oruserspecifiedfixedbandwidth.
Asanillustration,weperformapanelunitroottestsonrealgrossinvestmentdata(I)intheoft
citedGrunfelddatacontainingdataonR&Dexpenditureandothereconomicmeasuresfor10firms
fortheyears1935to1954foundinGrunfeld_Baltagi.[Link]
roottest,usingindividualfixedeffectsasregressors,andautomaticlagdifferencetermand
bandwidthselection(usingtheSchwarzcriterionforthelagdifferences,andtheNeweyWestmethod
andtheBartlettkernelforthebandwidth).Theresultsforthepanelunitroottestarepresented
below:
Thetopoftheoutputindicatesthetypeoftest,[Link]
wereinsteadestimatingaPoolorGrouptest,alistoftheseriesusedinthetestwouldalsobe
[Link],organizedbothbynull
hypothesisaswellasthemaintainedhypothesisconcerningthetypeofunitrootprocess.
Alloftheresultsindicatethepresenceofaunitroot,astheLLC,IPS,andbothFishertestsfailto
rejectthenullofaunitroot.
Ifyouonlywishtocomputeasingleunitroottesttype,orifyouwishtoexaminethetestsresultsin
greaterdetail,youmaysimplyrepeattheunitroottestafterselectingthedesiredtestinTesttype
[Link],weshowthebottomportionoftheLLCtestspecificoutputforthesamedata:
[Link] 3/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
Foreachcrosssection,theautoregressioncoefficient,varianceoftheregression,HACofthe
dependentvariable,theselectedlagorder,maximumlag,bandwidthtruncationparameter,andthe
numberofobservationsusedaredisplayed.
PanelUnitRootDetails
Panelunitroottestsaresimilar,butnotidentical,tounitroottestscarriedoutonasingleseries.
Here,webrieflydescribethefivepanelunitroottestscurrentlysupportedinEViewsforadditional
detail,[Link]
basicknowledgeofunitroottheory.
Webeginbyclassifyingourunitroottestsonthebasisofwhethertherearerestrictionsonthe
[Link](1)processforpanel
data:
(37.45)
where crosssectionunitsorseries,thatareobservedoverperiods
The representtheexogenousvariablesinthemodel,includinganyfixedeffectsorindividual
trends, aretheautoregressivecoefficients,andtheerrors areassumedtobemutually
[Link] , issaidtobeweakly(trend)[Link]
otherhand,if then containsaunitroot.
Forpurposesoftesting,therearetwonaturalassumptionsthatwecanmakeaboutthe .First,one
canassumethatthepersistenceparametersarecommonacrosscrosssectionssothat for
all .TheLevin,Lin,andChu(LLC),Breitung,andHadritestsallemploythisassumption.
Alternatively,onecanallow [Link],Pesaran,andShin
(IPS),andFisherADFandFisherPPtestsareofthisform.
TestsWithCommonUnitRootProcess
Levin,Lin,andChu(LLC),Breitung,andHadritestsallassumethatthereisacommonunitroot
processsothat [Link]
aunitrootwhiletheHadritestusesanullofnounitroot.
LLCandBreitungbothconsiderthefollowingbasicADFspecification:
[Link] 4/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
(37.46)
whereweassumeacommon ,butallowthelagorderforthedifferenceterms, ,to
[Link]:
(37.47)
(37.48)
Underthenullhypothesis,thereisaunitroot,whileunderthealternative,thereisnounitroot.
Levin,Lin,AndChu
ThemethoddescribedinLLCderivesestimatesof fromproxiesfor and thatare
standardizedandfreeofautocorrelationsanddeterministiccomponents.
Foragivensetoflagorders,webeginbyestimatingtwoadditionalsetsofequations,regressing
both ,and onthelagterms (for )andtheexogenousvariables
.Theestimatedcoefficientsfromthesetworegressionswillbedenoted and ,
respectively.
Wedefine bytaking andremovingtheautocorrelationsanddeterministiccomponents
usingthefirstsetofauxiliaryestimates:
(37.49)
Likewise,wemaydefinetheanalogous usingthesecondsetofcoefficients:
(37.50)
Next,weobtainourproxiesbystandardizingboth and ,dividingbytheregression
standarderror:
(37.51)
where aretheestimatedstandarderrorsfromestimatingeachADFinEquation(37.46).
Lastly,anestimateofthecoefficient maybeobtainedfromthepooledproxyequation:
(37.52)
[Link] 5/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
LLCshowthatunderthenull,amodifiedtstatisticfortheresulting isasymptoticallynormally
distributed
(37.53)
where isthestandardtstatisticfor , istheestimatedvarianceoftheerrorterm ,
isthestandarderrorof ,and:
(37.54)
Theremainingterms,whichinvolvecomplicatedmomentcalculations,aredescribedingreaterdetail
[Link], ,isdefinedasthemeanoftheratiosofthelong
[Link]
[Link], and areadjustment
termsforthemeanandstandarddeviation.
TheLLCmethodrequiresaspecificationofthenumberoflagsusedineachcrosssectionADF
regression, ,aswellaskernelchoicesusedinthecomputationof .Inaddition,youmust
[Link]
regressors,ortoincludeindividualconstantterms(fixedeffects),ortoemployindividualconstants
andtrends.
Breitung
[Link],onlytheautoregressiveportion
(andnottheexogenouscomponents)isremovedwhenconstructingthestandardizedproxies:
(37.55)
where , ,and areasdefinedforLLC.
Second,theproxiesaretransformedanddetrended,
(37.56)
Thepersistenceparameter isestimatedfromthepooledproxyequation:
[Link] 6/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
(37.57)
Breitungshowsthatunderthenull,theresultingestimator isasymptoticallydistributedasa
standardnormal.
TheBreitungmethodrequiresonlyaspecificationofthenumberoflagsusedineachcrosssection
ADFregression, ,[Link],nokernel
computationsarerequired.
Hadri
TheHadripanelunitroottestissimilartotheKPSSunitroottest,andhasanullhypothesisofno
[Link],theHadritestisbasedontheresiduals
fromtheindividualOLSregressionsof onaconstant,[Link],
ifweincludeboththeconstantandatrend,wederiveestimatesfrom:
(37.58)
Giventheresiduals fromtheindividualregressions,weformtheLMstatistic:
(37.59)
where arethecumulativesumsoftheresiduals,
(37.60)
and istheaverageoftheindividualestimatorsoftheresidualspectrumatfrequencyzero:
(37.61)
EViewsprovidesseveralmethodsforestimatingthe .SeeUnitRootTestingforadditional
details.
AnalternativeformoftheLMstatisticallowsforheteroskedasticityacross :
(37.62)
Hadrishowsthatundermildassumptions,
(37.63)
[Link] 7/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
where and ,ifthemodelonlyincludesconstants( issetto0forall ),and
and ,otherwise.
TheHadripanelunitroottestsrequireonlythespecificationoftheformoftheOLSregressions:
whethertoincludeonlyindividualspecificconstantterms,orwhethertoincludebothconstantand
[Link] statisticvalues,onebasedon withtheassociated
homoskedasticityassumption,andtheotherusing thatisheteroskedasticityconsistent.
Itisworthnotingthatsimulationevidencesuggeststhatinvarioussettings(forexample,small ),
Hadri'spanelunitroottestexperiencessignificantsizedistortioninthepresenceofautocorrelation
[Link],theHadritestappearstooverrejectthenullofstationarity,
andmayyieldresultsthatdirectlycontradictthoseobtainedusingalternativeteststatistics(see
HlouskovaandWagner(2006)fordiscussionanddetails).
TestsWithIndividualUnitRootProcesses
TheIm,Pesaran,andShin,andtheFisherADFandPPtestsallallowforindividualunitroot
processessothat [Link]
combiningofindividualunitrootteststoderiveapanelspecificresult.
Im,Pesaran,AndShin
Im,Pesaran,andShinbeginbyspecifyingaseparateADFregressionforeachcrosssection:
(37.64)
Thenullhypothesismaybewrittenas,
(37.65)
whilethealternativehypothesisisgivenby:
(37.66)
(wherethe maybereorderedasnecessary)whichmaybeinterpretedasanonzerofractionof
theindividualprocessesisstationary.
AfterestimatingtheseparateADFregressions,theaverageofthetstatisticsfor fromthe
individualADFregressions, :
(37.67)
isthenadjustedtoarriveatthedesiredteststatistics.
[Link] 8/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
Inthecasewherethelagorderisalwayszero( forall ),simulatedcriticalvaluesfor
areprovidedintheIPSpaperfordifferentnumbersofcrosssections ,serieslengths ,andfor
testequationscontainingeitherintercepts,[Link],
orlinearlyinterpolatedvalues,inevaluatingthesignificanceoftheteststatistics.
InthegeneralcasewherethelagorderinEquation(37.64)maybenonzeroforsomecross
sections,IPSshowthataproperlystandardized hasanasymptoticstandardnormaldistribution:
(37.68)
TheexpressionsfortheexpectedmeanandvarianceoftheADFregressiontstatistics,
and ,areprovidedbyIPSforvariousvaluesof and anddifferingtestequation
assumptions,andarenotprovidedhere.
TheIPSteststatisticrequiresspecificationofthenumberoflagsandthespecificationofthe
[Link]
constants,ortoincludeindividualconstantandtrendterms.
FisherADFAndFisherPP
AnalternativeapproachtopanelunitroottestsusesFishers(1932)resultstoderiveteststhat
[Link]
Wu,andbyChoi.
Ifwedefine asthepvaluefromanyindividualunitroottestforcrosssection ,thenunderthe
nullofunitrootforall crosssections,wehavetheasymptoticresultthat
(37.69)
Inaddition,Choidemonstratesthat:
(37.70)
where istheinverseofthestandardnormalcumulativedistributionfunction.
EViewsreportsboththeasymptotic andstandardnormalstatisticsusingADFandPhillipsPerron
[Link].
ForbothFishertests,[Link]
toincludenoexogenousregressors,toincludeindividualconstants(effects),orincludeindividual
[Link] 9/10
5/14/2017 EViewsHelp:PanelUnitRootTesting
constantandtrendterms.
Additionally,whentheFishertestsarebasedonADFteststatistics,youmustspecifythenumberof
[Link],youmustinsteadspecify
amethodforestimating .EViewssupportsestimatorsfor basedonkernelbasedsumof
[Link].
SummaryOfAvailablePanelUnitRootTests
Thefollowingtablesummarizesthebasiccharacteristicsofthepanelunitroottestsavailablein
EViews:
Test Null Alternative Possible Autocorrela
Deterministi tion
c Correction
Component Method
Levin,Lin Unitroot NoUnitRoot None,F,T Lags
andChu
Breitung Unitroot NoUnitRoot None,F,T Lags
IPS UnitRoot Somecross F,T Lags
sections
withoutUR
FisherADF UnitRoot Somecross None,F,T Lags
sections
withoutUR
FisherPP UnitRoot Somecross None,F,T Kernel
sections
withoutUR
Hadri NoUnit UnitRoot F,T Kernel
Root
NonenoexogenousvariablesFfixedeffectandTindividualeffectandindividualtrend.
Lastupdated:Mon,27Feb20[Link]PST
Backtotop
[Link] 10/10
