Stratification

Estadísticas

1. Estratificación
EQUIPO 3 :
ARBALLO VELARDE SAMUEL
ARVIZU PARTIDA JULIA
AVILES LOPEZ ANA
GUTIERRES MARTINEZ DAMARIS

2. Whatisstratification?
Thestratificationisatechniqueusedincombinationwith
otherdataanalysistools.Whenthedata,fromavarietyof
sourcesorcategories,havebeengroupeditsmeaningmay
beimpossibletointerpret.Thistechniqueseparatesthedata
sothatthepatternsofdistributionoftwoormoregroups
canbedistinguished.

3. Objective
Thestratificationaimstounderstandaproblemoranalyzetheir
causesobservingfactorsorpossibleandunderstandableelements.
Thedatacollectedfromapopulationisdividedintolayersorlevels.
Theaimistoisolatethecauseofaproblem,identifyingthedegree
ofinfluenceofcertainfactorsontheresultofaprocess.
•Allowsyoutoisolatethecauseofaproblem,identifyingthe
degreeofinfluenceofcertainfactorsontheresultofaprocess.
•Youcansupportandbethebasisonqualitytools.

4. Strata
Thestrataaregroupingdatawithsimilarcharacteristics.The
mostfrequentareperformedinlathea:
•Commodityrawmaterial(dates,suppliers,composition).
•(Sex,age,seniority,experience,career)labor.
•Machinery&equipment(model,antique,technology,hours
ofuse).
•Time(shift,stations,hours,month,week).
•Locationorareasofthecompany(casino,systems,parking,
manufacturing,administrative,etc.)
•Processes(procurement,technology,projects,etc.)

5. Use in other quality tools
•Stratificationcanrelyonqualitytools,thehistogramisthe
moreusualpresentit.

6. For what do you use it
•Identifythecausesthathavegreaterinfluenceonthe
variation.
•Tounderstandindetailthestructureofagroupofdata,
allowingyoutoidentifythecausesoftheproblemand
carryoutsuitablecorrectiveactions.
•Examinethedifferencesbetweenthemeanvaluesandthe
variationbetweendifferentstrata,andtakeactionagainst
thedifferencethatmayexist.

7. ProcessingSteps
1.Definethetargetpopulation.
2.Thenweneedtoorganizeorarrangethedatawehavesothatthereis
consistency.
3.Useatool(histogram,Pareto,orcake)thatallowsyoutorepresentthedata
collected(thisisoptional).
4.Selectthefactorsofstratificationonthebasisofsamecharacteristics(strata).
5.Classifydataintohomogeneousgroupsaccordingtoselectedstratification
factors.
6.Calculatethephenomenonbeingmeasuredineachcategory.Graphically
representeachhomogeneousgroupofdata.Withthehelpofothertools
(histogramorPareto).
7.Showtheresultsbyhomogenousgroupsofdatafromeachstratificationcriteria
comparison.

8. Example of Stratification (Pareto graph)
Inthisexamplewehaveafewpiecesrejectedfordefects.Wecollect
dataandbuildaParetochart,butanalyzingitwefindthatthe
problemsaremoreorlessequallyimportantandnonestandsout.

9. However,tostratifythedatabaseintheweekinwhichthe
partswereproducedweclearlyseeadifference.

11. StratifiedSampling
Stratifiedsamplingisatechniqueofprobabilitysampling
whereresearcherdividesthepopulationintodifferent
subgroupsorstrata.Then,itrandomlyselectsthefinal
subjectsofthedifferentstratainproportion.

12. Typesof StratifiedSampling
•Proportionalstratifiedsampling:
Inthistechnique,thesizeofthesamplefromeachstratumis
proportionaltothesizeofthepopulationofthestratumwhen
comparedwiththetotalpopulation.Thismeansthateachlayer
hasthesamefractionofsampling.

13. •Example:Supposeyouhave3layerswith100,200and300
populationsizes,respectively.Theinvestigatorchoseafractionof½
sampling.Then,theresearchermustproverandom50,100and150
subjectsfromeachstratum,respectively.
Estrato A B C
Tamaño de la población 100 200 300
Fracción de muestreo ½ ½ ½
Tamaño final de la muestra 50 100 150

14. •Disproportionate stratified sampling:
Theonlydifferencebetweenstratifiedrandomsampling
providedandthedisproportionatesamplingfractionsthereof
are.Indisproportionatesampling,thedifferentlayershave
differentsamplingfractions.Theprecisionofthisdesignis
highlydependentontheallocationoffractionofsamplingof
theresearcher.

15. Example

16. Usingthehypotheticalexampledescribedinthetable
above,ifyouwanttocarryoutadetailedanalysisofthe
zone2,onecouldonsampleelementsofthatarea;for
example,insteadofasamplingofonly12items,itshows
130elements.Inordertocarryoutamoremeaningful
analysis,analyzesindetailthezone2,thesizeofthesample
forthatdistrictshouldbegreaterthan12elements.The
resultsofthedistributionofelementsinthesamplearea.