Prikaz osnovnih podataka o disertaciji

Improvement data envelopment analysis using multiattribute decision making methods

dc.contributor.advisorMartić, Milan
dc.contributor.otherKuzmanović, Marija
dc.contributor.otherSavić, Gordana
dc.contributor.otherSuknović, Milija
dc.contributor.otherBacković, Marko M.
dc.creatorPopović, Milena
dc.date.accessioned2020-02-27T11:22:06Z
dc.date.available2020-02-27T11:22:06Z
dc.date.available2020-07-03T09:38:55Z
dc.date.issued2019-09-24
dc.identifier.urihttp://eteze.bg.ac.rs/application/showtheses?thesesId=7267
dc.identifier.urihttps://nardus.mpn.gov.rs/handle/123456789/12120
dc.identifier.urihttps://fedorabg.bg.ac.rs/fedora/get/o:21012/bdef:Content/download
dc.identifier.urihttp://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=515677594
dc.description.abstractAnaliza obavijanja podataka (Data Envelopement Analysis - DEA) je neparametarska tehnika bazirana na linearnom programiranju za merenje efikasnosti jedinica o kojima se odlučuje - DMUs (Decision Making Units) sa raznorodnim ulazima/izlazima. S obzirom na veliki broj ulaza i izlaza koji se koriste u DEA, suštinski problem u primenama proizilazi iz činjenice da često nije jasno koje ulaze, a koje izlaze izabrati za upotrebu prilikom ocenjivanja efikasnosti. Pored toga svaka DMU može da zahteva da se vrednosti virtuelnih ulaza i izlaza računaju na način na koji joj najviše odgovara, pa može doći do različitih rezultata ocene efikasnosti. Iz tih razloga, problem adekvatnog izbora ulaza i izlaza postaje važno pitanje za unapređenje diskriminacione moći metode. Imajući u vidu uočene probleme za izbor i sažimanje relevantnih kriterijuma razvijeni su hibridni modeli za povezivanje sa metodama multiatributivnog odlučivanja. Jasno je da uticaj ovih integracija na rezultujuće efikasnosti nije isti. U cilju određivanja težina (važnosti) kriterijuma koji će biti uključenu u mogu se koristiti nalitički hijerarhijski proces ( HP) i Conjoint analiza čime se delimično prevazilaze nedostaci u primeni DEA metode. Conjoint analiza je istraživačka tehnika, a koja se koristi za merenje preferencije ispitanika ka određenim atributima proizvoda/usluge. Conjoint se bazira na jednostavnoj premisi da ispitanici vrše evaluaciju alternativa, pri čemu su te alternative sastavljene od kombinacije atributa čije parcijalne korisnosti istraživači ispituju. AHP metoda predstavlja metod za rešavanje kompleksnih problema multiatributivnog odlučivanja i sistemski način za rangiranje više alternativa i/ili za izbor najbolje iz skupa raspoloživih. U doktorskoj disertaciji predložen je nov metodološki okvir za merenje efikasnosti baziran na integraciji DEA metode sa AHP i Conjoint analizom. Primena HP metode pruža mogućnost hijerarhijske dekompozicije problema u procesu odlučivanja i omogućava potpuno rangiranje DMU, dok su Conjoint analizom definisane važnosti ključnih kriterijuma, sa jedne strane, a sa druge, omogućen je izbor adekvatnih ulaza i izlaza. Krajnji rezultat integracije DEA metode sa prethodno navedenim metodama omogućio je otklanjanje dosadašnjih slabosti prilikom merenje efikasnosti DMU i povećanje diskriminacione moći DEA metode i to na bolji način nego što je predloženo u dosadašnjim istraživanjima koja su uglavnom DEA metodu koristili pojedinačno...sr
dc.description.abstractData envelopment analysis (DEA) is a non-parametric technique based on linear programming used for measuring the efficiency of Decision Making Units - DMUs with multiple inputs and outputs. Due to a large number of inputs and outputs used in the DEA, the essential problem in applications arises from the fact that it is often not clear which inputs and outputs to choose in the process of efficiency assessment. Furthermore, each DMU may require that the virtual input and virtual output be calculated in the best suitable way for DMU, therefore different efficiency assessment results can be obtained. Consequently, the problem of an adequate choice of inputs and outputs becomes an important issue for improving the discriminatory power of DEA. Bearing in mind the identified problems of selection and compression of relevant criteria, hybrid models for integrating DEA with multiatributive decision making methods have been developed. It is clear that the impact of these integration processes on the resulting efficiencies is not the same. In order to determine the weights (importance) of the criteria to be included in the DEA, the Analytical Hierarchy Process (AHP) and the Conjoint analysis can be used to partially overcome deficiencies in the application of the DEA. Conjoint analysis is an experimental approach used for measuring individual’s preferences regarding the attributes of a product/ a service. Conjoint is based on a simple premise that individuals evaluate alternatives, with these alternatives being composed of a combination of attributes whose part-worth utilities are estimated by researchers. The AHP is an effective tool for solving complex multiatributive decision making problems and systemic mode for ranking multiple alternatives and/or for selecting the best from a set of available ones. In the PhD, a new methodological framework for efficiency measuring, based on the integration of the DEA method with AHP and Conjoint analysis is proposed. The application of the AHP method provides the possibility of hierarchical decomposition of problems in the decision-making process and allows full ranking of the DMU, while the Conjoint analysis defines the relative importance of each attribute, on one hand, and on the other, the selection of adequate inputs and outputs is enabled. The final result of the DEA method integration with the aforementioned methods enabled elimination of the existing deficiencies when measuring the efficiency of the DMU and increased the discriminatory power of the DEA method, and in a better way than it had been suggested in previous studies which had been mainly using by the DEA method individually...en
dc.formatapplication/pdf
dc.languagesr
dc.publisherУниверзитет у Београду, Факултет организационих наукаsr
dc.relationinfo:eu-repo/grantAgreement/MESTD/Technological Development (TD or TR)/33044/RS//
dc.rightsopenAccessen
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/4.0/
dc.sourceУниверзитет у Београдуsr
dc.subjectAnaliza obavijanja podatakasr
dc.subjectData envelopment analysisen
dc.subjectConjoint analysisen
dc.subjectAnalytical Hierarchy Processen
dc.subjectteachers’ efficiencyen
dc.subjecthigher education.en
dc.subjectConjoint analizasr
dc.subjectAnalitički hijerarhijski processr
dc.subjectefikasnost nastavnikasr
dc.subjectvisoko obrazovanjesr
dc.titleUnapređenje analize obavijanja podataka metodama multiatributivnog odlučivanjasr
dc.title.alternativeImprovement data envelopment analysis using multiattribute decision making methodsen
dc.typedoctoralThesisen
dc.rights.licenseBY-NC-SA
dc.identifier.fulltexthttps://nardus.mpn.gov.rs/bitstream/id/22227/Disertacija.pdf
dc.identifier.fulltexthttps://nardus.mpn.gov.rs/bitstream/id/22228/IzvestajKomisije22186.pdf
dc.identifier.rcubhttps://hdl.handle.net/21.15107/rcub_nardus_12120


Dokumenti za doktorsku disertaciju

Thumbnail
Thumbnail

Ova disertacija se pojavljuje u sledećim kolekcijama

Prikaz osnovnih podataka o disertaciji