Crime Geography Under Administrative Changes

Paulo Joo1, Jorge Ferreira2, Jos Martins2

1

DEIO Statistics and Operational Research Department- FCUL Campo Grande 1649-004-Lisbon, Portugal 2 e-GEO, Research Centre for Geography and Regional Planning, FCSH UNL Av. Berna 26 C 1069-061 Lisboa

Crime Geography Under Administrative Changes

Paulo Joo, Jorge Ferreira, Jos Martins

e-Working Papers OSN, N 2 | Novembro de 2011

Classificao: Segurana Nacional; Estatsticas do Crime

OSN | Observatrio de Segurana Nacional | 2

 AcercadoOSN
Enfrentamosumanovaeradedesafioseoportunidadesnaresoluodequestesoutrora emergentes,masque,frutodeumacrescentedesestruturaosocialecriseeconmica mundial,adquiriramumadimensoqueexigecircunscrioetratamentoimediatoe prospectivo.Assim,noOSNacreditamosqueoestudodasmatriasdasegurananacional, sustentadoporinformaoadequadaedevidamentetratada,permiteofereceralternativas polticas(pblicaseprivadas)queprevejamofuturo,antecipandoamudanae,por conseguinte,permitindoumgraudepreparaosuperiordonossoPasedosnossosAmigose Aliados. OObservatriodeSeguranaNacionalOSNumaOrganizaoNoGovernamentalONG, dedicadaaoestudo,anliseecomentriodaspolticasnareadasegurananacional. OOSNpretendenosfornecerumavisoanalticaeestruturadasobreasquestesda seguranaecriminalidade,mastambmodiscernimentoestratgiconecessrionoapoio decisodeinstituiesgovernamentaiseprivadas,nacionaiseinternacionais,assimcomo sociedadecivil.

AboutOSN:
Wefaceaneweraofchallengesandopportunitiesinaddressingemergingissuesonce,butthat theresultofanincreasingsocialdisruptionandeconomiccrisis,haveacquiredadimensionthat requiresimmediatetreatmentdivisionandprospective.Thus,theOSNbelievethatthestudyof mattersofnationalsecurity,supportedbyappropriateinformationandproperlytreated,can offeralternativepolicies(publicandprivate)providingforthefuture,anticipatingchangeand thereforeallowingahigherdegreeofpreparationofourcountryandourfriendsandallies. TheObservatoryofNationalSecurityOSNisanongovernmentalorganizationNGO dedicatedtothestudy,analysisandreviewofpoliciesintheareaofnationalsecurity. OSNintendsnotonlytoprovideastructuredandanalyticalviewontheissuesofsecurityand crime,butalsothestrategicinsightneededfordecisionsupportofgovernmentalandprivate, nationalandinternational,aswellascivilsociety.

OSN|www.observatoriosegurancanacional.org

OSN | Observatrio de Segurana Nacional | 3

ConselhoEditorial/EditorialBoardOSN:

ProfessorDoutorAntnioSilvaRibeiro ProfessoraDoutoraCristinaSoeiro ProfessorDoutorHeitorBarrasRomana ProfessoraDoutoraIsabelSoares ProfessorDoutorLusFiesFernandes ProfessoraDoutoraMariadoCuPinto ProfessorMestreNunodeBarrosPoiares ProfessorMestrePauloMacedo ProfessorDoutorPauloMachado ProfessorMestrePauloSaragoadaMatta ProfessorDoutorPauloPereiradeAlmeida ProfessorMestrePauloAbeldeAlmeidaJoo ProfessorDoutorPedroClemente ProfessorDoutorPedroSimes GeneralDoutorRodolfoBegonha GeneralDoutorVizelaCardoso MestreFranciscoNobre MestreJaneteBento MestrePedroSarmento

NotaEditorial
AsvisesexpressasnopresentedocumentonoreflectemasposiesoficiaisdoOSN,sendoda exclusivaresponsabilidadedo(s)autor(es).

Citao:
JOO, Paulo et al. (2011), Crime Geography Under Administrative Changes, OSN eWorking Paper n. 2 [www. www.observatoriosegurancanacional.org]

OSN | Observatrio de Segurana Nacional | 4

Abstract
Overthelastfewyearsanewworldwidesocioeconomicalorderleadtoanincreasingnumber oncrimeratesandraisedtheneedtofindnewwaystohandleinformationaboutcriminality. Tobetterunderstanditscauses,local,regionalandnationalsecurityauthoritiesturnedtonew decisionsupporttoolssuchasGeographicInformationSystems(GIS)andotherinformation technologiestohelptheminfindingbettersolutions.Tounderstandthetruemagnitudeofall thevariablesinvolveditwasnecessarytospatiallycaptureandcorrelatethemtobetter quantifyandqualifythecontextwithinthephenomena. ThecityofLisbonwithisnewproposedadministrativedivision,reducingfrom53to24 freguesias(minimumadministrativedivisionandsimilartoparishs)impliesanenormous degreeofuncertaintyintheobservationandlocationofcriminaldata.Asthecrimeisnot treatedwithanexactpoint,butatthelevelofparish,itimpliesthatlargerparishesaretreated bytheaveragecrimeregardlessofplaceofoccurrence. Thisresearchcombinesstatisticalmethods(clusteranalysis)andspatialmodelscreatedwith GISbasedonpolicecrimereports.Italsodetailsaframeworkforshorttermtactical deploymentofpoliceresourcesinwhichtheobjectiveistheidentificationofareaswherethe crimelevelsarehigh(enough)toenableaccuratepredictivemodelsaswellastoproduce rigorousthematicmaps.Inrecentyearspoliceserviceshaveengagedonproactiveand IntelligenceLedPolicing(ILP)methods. Thisadvancewascoincidentwiththerecognitionoflawenforcementsolutionsatlocallevel. ThispaperisalsoanapproachtoILPasastrategicmethodologytoprovidetoolsforDecision SupportSystem(DSS)bypolicedepartments.

OSN | Observatrio de Segurana Nacional | 5

|TableofContents

1. Introduction 2. GIS and Crime 3. Intelligence-Led Policing 4. Crime Mapping 4.1 Hot-Spots of Crime 4.2 Statistics for Crime Analyses 4.3 Methodology 5. Conclusions 6. References

7 9 10 13

25 27

OSN | Observatrio de Segurana Nacional | 6

1. Introduction
Overthelastfewyearsanewworldwidesocioeconomicalorderleadtoanincreasingnumber oncrimeratesandraisedtheneedtofindnewwaystohandleinformationaboutcriminality.To better understand its causes, local, regional and national security authorities turned to new decision support tools such as Geographic Information Systems (GIS) and other information technologiestohelptheminfindingbettersolutions.Tounderstandthetruemagnitudeofall the variables involved it was necessary to spatially capture and correlate them to better quantifyandqualifythecontextwithinthephenomena. ThecityofLisbonwithisnewproposedadministrativedivision;reducingfrom53to24 parishs (minimum administrative division) implies an enormous degree of uncertainty in the observationandlocationofcriminaldata.Asthecrimeisnottreatedwithanexactpoint,butat thelevelofparish,itimpliesthatlargerparishesaretreatedbytheaveragecrimeregardlessof placeofoccurrence. InrecentyearspoliceserviceshaveengagedonproactiveandIntelligenceLedPolicing (ILP)methods.Thisadvancewascoincidentwiththerecognitionoflawenforcementsolutions atlocallevel. Thisresearchcombinesstatisticalmethods(clusteranalysis)andspatialmodelswithGIS basedonpolicecrimereports.Italsodetailsaframeworkforshorttermtacticaldeploymentof policeresourcesinwhichtheobjectiveistheidentificationofareaswherethecrimelevelsare high (enough) to enable accurate predictive models as well as to produce rigorous thematic maps. ItisalsoanapproachtoIntelligenceledpolicingasastrategicmethodologytoprovide toolsfordecisionsupportbypolicedepartments. Recent advances on geostatistics, information, data mining and GIS, the study and modeling of crime data to identify patterns has emerged as a new research field. Within the scopeofthispaper,somekeyquestionswillbeaddressed:

OSN | Observatrio de Segurana Nacional | 7

 Can crime patterns be extrapolated in small areas such as precincts accurately enough for useindeployment,schedulingforevaluatingpoliceeffectiveness? Canmultivariateforecastmodelspredictturningpointsandothernewpatterns? Is it possible using geostatistics tools such as kriging methods, to foresee and predict the occurrenceofincidents,beyondthemeredescriptivemodels?

OSN | Observatrio de Segurana Nacional | 8

2. GISandCrime
Sincethe1960sGeographicalInformationSystems(GIS)havebeenappliedtoavastnumberof studiesandcriminalityisnotanexception.FromitsfirstapplicationsinCanada,GIShasbecome amajorinstrumentforaneffectiveterritorialplanning. From incar navigation, retail and commerce location, costumer geomarketing studies toriskmanagement,construction,weatherforecasting,militaryplanningandotherapplication fields. However,itwasonlyinthebeginningofthe1980swiththereductionsinthepriceof technologies(operatingsystems,processors,storagecapacity,memoryandhardware),thatGIS saw a significant development on new research areas, such as crime analysis, distribution of policeprecinctsandplanningcrimereduction. MuchoftheworkincrimemappingandanalyseswascarriedoutintheUnitedStatesby theMappingandAnalysisforPublicSafety(MAPS),formerlyknownastheNationalInstituteof JusticesCrimeMappingResearchCenter(CMRC). Thisworkservedasalaunchingplatformtothedevelopmentofcrimemappinginother countrieslikeSouthAfrica,AustraliaandUnitedKingdom Thecomputerizationofpolicerecordshascomewitharealizationthatthismaterialcan beusedforcrimeandintelligenceanalyses(Ratcliffe,2004).Thisworkpermitstherecognition ofpatternssometimeshiddenandoftennotperceivedbythepoliceandauthorities. Geography is also necessary for advances on spatial understanding and consequently hascontributedtomanydisciplineswhereunderstandingspaceandplaceisimportant,such aswithcrime(Ratcliffe,2004). WiththenewLisbonadministrativedivision,crimeanalyseswillbemoredifficultdueto area aggregation. For example on certain types of crime, aggregation will probably mask important pattern details. The comparison between the new and the old administrative divisions in Lisbon is an important and the use of predictive models can help authorities and providethenecessaryresultstoaneffectivedecision. Toproceedornotwiththenewadministrativedivisionisthemajorquestionthathasto beansweredshortly.Andthemostcorrectanswerwilldependuponarigorousandpertinent researchbasedoninformationandknowledge. The comparison between the new and the old administrative divisions in Lisbon is an important exercise to perceive pattern differentiation and has obvious implications on territorialplanningandpublicdomain. Theuseofgeostatisticstoolssuchaspredictivemodelsandkrigingmethodsallows,beyond themeredescriptionofphenomena,toforeseeandpredicttheoccurrenceofincidents.

OSN | Observatrio de Segurana Nacional | 9

3. IntelligenceLedPolicing
Police forces always struggling with a lack of human resources try to reduce crime on their jurisdiction by analyzing and correlate information from primary sources on criminal environment. Criminal historical data are analyzed to develop new strategies and actions to reduce crime. Itisaverydemandingtaskintermsoftechnologicalmeansandhumanresourcesbutit isthebeststrategytoreducecrimebecauseithasanapproach,bothpreventiveandrepressive.
Criminal environment

Intelligence

Decision-maker

Figure1:ILPandcrimereductionprocess(Ratcliffe,2005) An ILP model at its first stage enables the interpretation of the criminal environment. This is usually performed by an intelligence section, and relies on the range of informations sourcesbothwithinandexternaltothepoliceservice. The obtained information should, in an intelligenceled environment, be passed to people who can actually impact in a positive manner on the criminal environment (decision maker). Thisrequiresanintelligencestructuretobeabletoidentifyandinfluencethedecision makers.Itshouldbenotedthatthisrequiresbothanabilitytoidentifythedecisionmakers,as well as to influence their thinking regarding the types of strategies to achieve better criminal numbers.

OSN | Observatrio de Segurana Nacional | 10

ILPstrivesforgreaterefficiencyinpolicing,butithasalsobeenaccompaniedbyother efficiencymethods,someofwhichconflictwithILP. There is a performance culture in many police services which strives to measure everything possible, and it is a concern that the benefits of ILP will be lost in a flood of operationalstatistics.Oneofthemajorissuesisresponsetime. Manypoliceserviceshavenowrecordsoftheresponsetimetoroutinecalls,andthey buildresponseimprovementprotocolsthatmaximizeperformance. Unfortunatelytheresearchevidenceisfairlyconclusive:improvingresponsetimestocallsfor service does not reduce crime. The intelligence led policing model, is more difficult to implementbutisalsothemostversatileinperformanceandresults. Thefollowingtablecomparesthevariousmodelsofpolicingintermsofimplementation, resourcesandresults: Table1:Strategicaspectsofpoliceactivity

OSN | Observatrio de Segurana Nacional | 11

Inrecentyearstherehasbeenamovewithinpoliceservicestowardsaproactiveand

ILP. This has coincided with recognition of the value of local policing solutions and the importanceoftheintelligencefunctionatthelocalarea.ThispaperisanapproachtoILPasa strategicmethodologytoprovideatoolforthedecisionsmakersinpolicedepartments. Knowing where the police become a crucial intervenient element provides a better

understandingoftheinterventionprogramandanticipatedoutcomesandeffects.Withoutsuch abaseline,evaluationsarelimitedastothepurposesandsometimesanticipateconsequences topoliceefforts.Intelligenceledpolicingisalsoaboutbeingasmartpolice. That means, increasing the effectiveness and efficiency of police interventions

through the use of the right information. Such efforts are data driven (quantitative and qualitative)andanalyticallyrigorous,assuringthanappropriatecarehasbeentakentocollect, organizeandanalyzeinformation,priortoaction. This ameliorates the deficiencies of rigid boundaries and moves towards a more

dynamic methodology. With the new Lisbon paradigm, from 53 to 24 parishes and assuming theseadministrativelimitations,crimeanalysiswillbemoredifficultduetotheaggregation.

OSN | Observatrio de Segurana Nacional | 12

4. CrimeMapping
Crime mapping is a technique based on software that converts geocoded addresses or locations(onesetoffiles)sothatmaps,tables,andfigurescanbemergedwiththemandmaps created. These maps can display an array of signs on maps of a city combined with pictures, sound, drawings, and diagrams. A wide range of facts can be included, such as fire risks, demographiccharacteristics,indicesofdisorderandqualityoflifeoffenses,addressesofthose on parole, registered sex offenders, and more conventional police generated data concerning juvenile gangs, patterns of adult crime, and traffic. Variations in density by location, types of crimes, or days of the week can be mapped, as can offenders residences and patterns of co offending. Anythingthatcanbeplottedspatiallycanberepresented.Ineffect,almostbydefault, thesedisplayshavecreatedacontextforproblemsolvingandreflection,whatislooselycalled crimeanalysis.Inpolicing,crimeanalysiscoversawiderangeofpractices.Atonelevel,itsimply meansexaminingthepatterningoftypesofcrimebytimeandspace. Withtheemergenceofgeographicinformationtechnologyanditssuccessfuluseasatoolfor crime analysis and forecasting, the study and modeling of historical or current crime data to identify spatial crime patterns has emerged as a new research area. However in Europe, this realityisstillrecent.Threekeyquestionscanbepointedout: Can univariate methods be used as a mean to extrapolate crime patterns in the shortrun smallareassuchasprecinctsaccurately? Are they robust enough for use in deployment, scheduling, and as counterfactuals for evaluatingpoliceeffectiveness?;and Are there standard indicators (of crime) for use in multivariate forecast models that can predictturningpointsandothernewpatterns,suchasthestartofanewcrime? For some crime types, aggregation may mask important seasonal variations in smaller ecologicalareas.

OSN | Observatrio de Segurana Nacional | 13

Forexample,universityareasmayhaveseasonalpatternsinpropertycrimesinfluencedby thecomingsandgoingsofthestudentsandteachers.Also,shoppingareasmayhavepeaksby holidaytimes. Law enforcement officers have been mapping crime virtually since the time that police agencieswereestablishedthroughtheuseofpushpinsandapapermapatthebeginningofthe 20Century(Harries,1999). By the late 70s and early 80s, there was a resurgence of interest in understanding and analyzingthespatialdimensionofcrimethroughthecharacteristicsofincident,itslocationand geographical analysis on incident (Boba, 2009). With the development of GIS in the 90s, law enforcement officers begun to consider the principles of geography and spatial information usingnewtechnologiesinordertorealizeanddevelopmechanismstocrimepreventionandthe publicsafety. Thecartographicrepresentationhassomeadvantagessuchas(Eck,2005&Boba,2009): Helpvisualanalysisandstatisticsofcrime; Aggregateinformationinspatialmatrix; Producethematicmapsthathelptocommunicatetheresultsoftheanalysis. Harris(1990:3),statesthatthepurposeofmapsistocommunicateinformation. Thecartographicrepresentationisatooltocommunicateinformationacrosstimeandspace. ThediffusionofGISintocrimeanalysishasbeenaslowprocessprimarilybecauseofcost(both hardwareandsoftware)andcomplexity. WhendiscussingthecurrentuseofGISforcrimeanalysis,activitiescanbedividedintocurrent and cutting edge applications (currently used in law enforcement agencies to support crime analysisactivities). The uses of GIS to support crime analysis activities in police daytoday operations are a powerfultoolforstrategicplanning(Johnson,2000).

OSN | Observatrio de Segurana Nacional | 14

4.1.HotSpotsofCrime Thisisthemostcommonmethodusedincriminalrepresentation.Itassumesthatthelocations of concentration criminal past will persist into the future, however the actual results of this method depends on the time period under review, usually this robust method only produces goodresultswhenappliedtoshorttimeseries(Spellman,1995). To AdmansFuller's (2001), an interesting feature in the detection of hotspots is its persistence and coincidence over time as shown by Anselin (2000), the hotspots reflect high levelsofcrimeinitiallymoderate,butovertime,usually,thiscrimewillchangetomoreviolent typesofcrimes(e.g.actsofvandalismtocrimesoftheft). Therefore,shouldbecontainedandcontrolledintimetopreventmoreseriousincidents topeopleandpropertyinthegeographicareacoveredbythehotspot. AccordingtoEck(2005),thismethodassumesthattheymustmapthelocationsandnot criminaloccurrencesthusunderstandwhycertainsettingsaremoreeasilycriminaloccurrences whileothersappeartoinhibitthesesameevents.Ainsworth(2001:88)refersthat"Acrimehot spotisusuallyunderstoodasalocationorsmallareawithboundariesclearlyidentifiedwhere thereisaconcentrationofcriminalincidents,whichexceedthenormalforthisarea,theterm canalsobeusedtodescribelocationsthatshowedanincreaseincrimeagivenperiodoftime". Most of these analyses give rise to shortterm interventions by police such as crackdowns, saturation patrol, or raids. More sophisticated versions of crime analysis may require models of the dynamics of areas, including disorder, crime, and their correlates, as a preludetolongertermplanningorinterventions. 4.2.StatisticsforCrimeAnalyses One of the most important tasks associated with analyzing criminality is know your data, this dataarethebaselineforanintelligenceanalyze,however,verylittleofthisdataarecollected withintelligenceanalysisinmind. Understanding the different types of data and their definitions is important because some types on analyses have been designed for particular types of data and may be inappropriateforanothertype.

OSN | Observatrio de Segurana Nacional | 15

Afterpreprocessingandcodingalltheinformation,datawasanalyzedandthedataset consisted in 35549 police records, distributed by 8 variables, according with the fallowing coding: Table2:Datacodingprocess
Variable Day Month Hour Minute Typeofcrime Min Max 1 1 0 0 1 31 12 23 59 6 34 112 53

Subtypeofcrime 1 Classification Parish 1 1

According to the Persons coefficient correlation matrix, there was no significant correlation between the variables witch let us to identify the variables as independent observations. Table3:Personcorrelationmatrix
Day Month Hour Minute Type Subtype Day 1 Month Hour Minute Type Subtype Classification Parish

0,011 1 0,008 0,003 1 0,007 0,000 0,019 1 0,050 0,016 0,013 0,020 1 0,004 0,002 0,003 0,004 0,020 1 1 0,032 1

Classification 0,014 0,009 0,010 0,009 0,008 0,000 Parish 0,002 0,005 0,007 0,013 0,012 0,020

Intermsofinformation,thedatarepresentedasmallpartofthecriminalreality,since there were only considered the crimes reported and recorded by the Public Safety Police (PolciadeSeguranaPblicaPSP).
OSN | Observatrio de Segurana Nacional | 16

Theprimarydatasetconsistofoneyearofcriminaloffencesforallindividualeventsfor 2009inLisbonCountyobtainedwithauthorizationfromthePSP. Thedatasetincludeallpersonalandpatrimonialoffences.Themostoftenstudiedcrime is robbery occurred in public transportation. All the records has a parish of reference, which permitstheclassificationoftheoffencesandtheirmappinginaGIS. Unfortunately the accuracy is not the ideal because we dont have the points of the occurrenceswhichpreventsusfromusingthegeoreferencepointbutonlytheparisharea. The histograms below show that the majority of crimes are robbery especially during the evening.

Figure2:Datahistograms 4.3.Methodology

Regarding the GIS methodology adopted, it was necessary to prepare the work with a set of layers and create a theme to match the expected distribution of parishes. Thematic maps showingthenumberofcrimesorothermetricswereaggregatedusingcolorpalettes(darkerfor morecrimesandbrighterforless). This method is widely used because it is perceived, for example by the county, those wherethecrimehasmoreimpact.However,althoughthisisalsoapopularmethod,itisunlikely that crime is fair by Municipality (e.g. Lisbon) and it can lead to interpretations that do not correspondtoreality. Themainreasonisbecausethepopulationdensityisdifferentineachplace.Inthiscase, theuseofratiosintherepresentationofcolorswouldbethewisestchoice.

OSN | Observatrio de Segurana Nacional | 17

This type of maps creates a jurisdictional conflict between the geographical areas and administrativedelimitations(orjurisdictions),whentheyaredifferent(asisthecaseofLisbon).

Figure3:Parishsadministrativedivision(actualandplanning) On crime analysis, cartograms were initially created to show absolute values in crime (recorded in 2009) by the Public Security Police (PSP) in Lisbon, according to the current structureof53parishesandthenewstructureof24parishes. Thisrepresentationwastheresultofthegeoreferencedcrimesrecordedin2009by53 existing parishes. To represent the crimes recorded by the new administrative structure was necessarytotheaggregatecrimedatabynewparishes. TheparishofSantaMariadosOlivais,underthenewstructurewillbedividedintotwo parishes,givingrisetoanewone,theOriente. In order to estimate the value of approaching crime in these two parishes, it was necessarytodividethetotalbythenewareaofcrime,multiplyingthecurrentarea.Theresult wasthensubtractedfromtheoldparishwithaviewtoobtainingtheaveragevalueestimated forthisnewdelineationoftwoparishes.
OSN | Observatrio de Segurana Nacional | 18

Itshouldbenotedthatthesedatacouldnotbeexactbecauseasmallerareamayhave moreorlessrecordedcrimes.However,forresearchpurposes,asinthiscase,themethodcan beused,providedthatisproperlyreferredto.

Figure4:TotalCrimesinLisbon Analyzingcrimedatabytheactualdivisionsandbythenewones,itseemsobviousan increaseinnumbers(inpartduetotheaggregationofvaluesrecordedinseveralparishesthat leadtonewadministrativearea).Importantly,thelownumberofcrimesinthesmallvillagesof thecurrentdivision,risingfromfirsttothelastclass(whenaggregatedthenewadministrative division). ThedatashowsaverylargecriminaldensityonOriente,buttheempiricalknowledgeof thisareacantellusthatmostcriminalincidentsoccurinits(new)aggregatedneighborhood. Next, we proceeded to calculate the criminal density, for the parish, dividing the total crimes persquareKminarea.

OSN | Observatrio de Segurana Nacional | 19

 Figure5:RatioofTotalCrimesperSquareKminLisbon Regarding criminal density, the new administrative division gives the perception of a reductionincrimenumbers.However,thisfactisinpartrelatedtothesignificantincreasein theareaofsomeparishes,thusreducingthedensityofcrimespersquareKm. In order to understand how it would be the spatial representation of crime according to the city'spopulation,createdacriminalincidencerate,basedondividingthenumberofcrimesby theresidentpopulation,theresultswereexpressedin. The data source for the population was raised in the Fourteenth general population censusconductedbytheNationalStatisticalInstitute(INE)in2001,wouldbemorecredibleto usevaluesforthepopulationin2009,butitwasnotpossibleduetothefactthatthecensusbe conductedonlyfrom10to10years,andpopulationestimatesrefertotheadministrativeunit abovethecity.
OSN | Observatrio de Segurana Nacional | 20

 Figure6:RatioofCriminalIncidenceper1000InhabitantsinLisbon In relation to the criminal incidence rate, the new administrative division gives the perception of a reduction in crime recorded even more significant, comparing with the result obtainedbycalculatingthedensitycriminal. Thereductionisdueinparttothesignificantincreaseintheareaofsomeparishesand their residents, thus reducing the incidence rate of crime in certain districts of the new administrativedivision. Itisknownthatthesouthernpartofthecity,correspondingtothedowntowndistrict, correspondtoanareathathasthehighestnumberofrecordedcrimes,mainlybecauseitisthe center of major economic, financial and commercial activities. But also because its the main tourismspotinthecity,whichtriggerscriminalactivity. An enormous lack of resident population must also be considered when analyzing the data.Withtheaggregationofexistingparisheswithverydifferentrates,thereisadecreasein thehighincidencerateinthecriminality.

OSN | Observatrio de Segurana Nacional | 21

In order to achieve different perspectives when analyzing the crime results across the city,itwasdecidedtomakethesumoftheresidentpopulationwiththemobilityofpopulation (population that enters and circulates in the city and tourists), in the sense that only by analyzing the criminal statistics according to the resident population of Lisbon, may be to overstatetheintensityofoccurrence.Assumingthatalargenumberofresidentpopulationand thismobilitymayleadtoanincreasedlikelihoodofacriminalcase(Machado,2007b:138).

Figure7:RatioofCriminalIncidenceper1000InhabitantsandPresentsinLisbon Lookingatthecrimeratewiththelocalpopulationandthis,itispossibletoobservethe emergenceofnewparisheswithhighrateofcrime,however,themaximumcrimerateismuch lowerwhencomparedtotherepresentationonlybytheresidentpopulation. Finally, it was created a spatial index based on crime incidence using spatial statistical tools.Thistypeofoperationshouldbeperformedatamicroscaleofanalysis,statisticallyequal tosubsection(Martins,2010),constitutingthehighestlevelofdisaggregationcorrespondingto theblockinurbanterms(Geirinhas,2001).

OSN | Observatrio de Segurana Nacional | 22

ThisindexwascalculatedusingaGeographicWeightedRegression(GWR)usingspatial contextofdynamicGaussianKernel.Thisoperationusesthesquarerootorlogofthevariables thatareselectedforanalysisbysmoothingtheabsolutevaluesandapproximatingthecurveof normaldistributioninparabolicform,reducingdisparitiesinthedistribution. Theresultisexpressedinstandarddeviationunits,whichisrepeatedlyusedasanindex ofrisk(Harries,1999).GWRprovidesalocalmodelofthevariableorprocessyouaretryingto understand/predict by fitting a regression equation to every feature in the dataset. GWR constructs a separate equation for every feature in the dataset incorporating the dependent andexplanatoryvariablesoffeaturesfallingwithinthebandwidthofeachtargetfeature. TheshapeandextentofthebandwidthisdependentonuserinputfortheKerneltype, Bandwidthmethod,DistanceandNumberofneighborsparameters The dependent variable for the GWR index, consisted on the criminal occurrences and as an independent variable, it was used the sum of the resident population with the mobility of population. It should be noted that this type of analysis can be a part of numerous independent variablesofsocioeconomicdevelopmentinordertoidentifyamorerealisticindex. However,withanareaofstudyattheparish,itwouldbeadifficultassignmentofcertainsocio economicvaluesinalargerscaledarea. It also worth mentioning that this type of fee (if used alone without performing a normalization of the variables) may generate incorrect analysis results (Harries, 1999) due to thefactthattherearehighlevelsofoccurrenceinareaswithlowpopulationandthishappening alsowithacartographicrepresentationofcrimerates.

OSN | Observatrio de Segurana Nacional | 23

 Figure8:SpatialIndexofCriminalIncidenceper1000Inhabitants(actualandplanning) LookingatthepreviousrepresentationandusingtheGWRoperation,itseemsevidentthe reductionofhighervaluesofdistributionaccordingtopopulation,mainlyincertainareasofthe newadministrativedivision.

OSN | Observatrio de Segurana Nacional | 24

5. Conclusions
The final results of this research can be vital to decide an effective police strategy. The decisiontoproceedwiththisnewadministrativescenarioissodifficultastodecideabout new forms to deal with this new territorial sketch. To decide what bases to consider and whattechnologiestoadoptarealsodifficultchoices. In recent years, researchers and technicians have made huge progresses in harnessing the analytic capabilities of GIS to track crime patterns over time and then, use this informationtocreatepredictivemodels. These advances turned GIS in a valuable tool to assist and support decisionmaking strategiesforthepoliceforcesandsecurityservices. Nowthatmanylawenforcementagencieshaveadoptedcrimemappingandhavebegun toproducethetypesoftoolsmentioned,theywantmore. Thedemandsformoresophisticatedspatialanalytictechniquesleadtotheresearchon predictivemodelstohelpthepreventionofthenextcrime. The crime must be examined in the context of threats and transforms the societies themselves, taking into account assessment of the demographic, economic, social and environmentalthatcouldaffectthecriminalactitself. Just seeing the real threats and developing solutions and using Geography, GIS and multivariatestatisticsanalysis,wecananalyzethecurrentmapofcriminality. Theadvancedspatialanalysiscametoidentifycrimepatternsandvulnerableareas(interms ofinsecurity).Thistypeofanalysisfacilitatesknowledgeinordertomakestrategicdecisions intocombatthecriminalphenomenon. However,onlyatmicroscale,thecriminaldatacanbeconsideredasusefultoastrategic planningagainstcrime.

OSN | Observatrio de Segurana Nacional | 25

Complementingspatialanalysisofcrimewiththeempiricalknowledgeofthehistoricaland culturalcomponents of a given territory, onemay identify thereason for the occurrence ofa particular type of crime in a given geographical area and therefore planning and resources in ordertopreventandreducingit. Nowadays, the level of spatial analysis and modeling techniques already permit the developmentoftacticalplanningstrategiestofightcrime. Data gathered in a form of information and properly worked can end up in an effective decisionsupport tool. And that can only be achieved by a combination of technology and humanknowledge.

OSN | Observatrio de Segurana Nacional | 26

6. References
Ainsworth,P.(2001),OffenderProfilingandCrimeAnalysis,UK,Devon,WilliamPublishing. Anselin,L.etal.(2000),SpatialAnalysesofCrime,CriminalJustice:Vol.4,USA,Washington. Boba,R.(2009),CrimeAnalysiswithCrimeMapping,SAGEPublications,Inc,California,2ndEd. Chainey, S. & Thompson, L. (editors) (2008), Crime Mapping Case Studies: Practice and Research,JohnWileyeSons,England. Eck,J.;Chainey,S.;Cameron,J.;Leitner,M.&Wilson,R.(2005),MappingCrime:Understanding HotSpots,USA,NationalInstituteofJustice. Geirinhas, J. (2001) Conceitos e Metodologias BGRI Base Geogrfica de Referenciao de Informao,DirecoRegionaldeLisboaeValedoTejo/INE2Semestrede2001. Harries,K.(1999),MappingCrime:PrincipleandPractice,Washington,DC,NIJ. Johnson,C.(2000),CrimeMappingandAnalysisUsingGIS.Geomatics2000:Conferenceon Longley,P.;Goodchild,M.;Maguire,D.&hind,D.(2005),GeographicInformationSystemsand Science,JohnWileyeSons,England,2ndEd. Machado,P.;Pereira,A.;Rebelo,M.;Menezes,M.;Craveiro,J.&Santos,A.(2007),Metrpoles Seguras:BasesparaumaIntervenoMultisectorialnasreasMetropolitanasdeLisboaePorto, 2Volume,Lisboa,LNECMAI. Ratcliffe,J.H.(2004),StrategicThinkinginCriminalIntelligence.Sydney:FederationPress. Ratcliffe,J.H.(2005),Theeffectivenessofpoliceintelligencemanagement:ANewZealandcase study. Wilson, R. & Smith, K. (2008), What is Applied Geography for the Study of Crime and Public Safety?, in Geography & Public Safety, Vol. 1, Issue 1, February 2008, Washington, DC, COPS, NIJ,U.S.DepartmentofJustice,pp.13.

OSN | Observatrio de Segurana Nacional | 27

OSN | Observatrio de Segurana Nacional

www.observatoriosegurancanacional.org