Treść książki

Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
12
1.Hedonicpricemethods
Apartfromtheabove-mentionedfunctionsmixedapproachesarealsoquite
commonlyapplied.Insuchcasessomeoftheindependentvariablesinthe
hedonicmodelarelinearandsomelogarithmic,dependingontheirtypeand
therelationshipwiththedependentvariable(inparticular,binaryvariablesdue
totheirnaturecannotbetransformedtologarithms).Alltheabove-mentioned
functionsarelinearinrespectofvariablesandparametersorcanbeeasily
transformedtolinearform,andthereforesimpleestimationmethods,suchas
theLeastSquaresmethod,maybeapplied.
Hedonicmodelshaveawidevarietyofapplicationfields.Firstofall,theestimate
ofthevectorofparametersβobtainedbyestimationofcorrectlyspecified
hedonicregressionmodelusingsufficientlylargedatasetallowsforcalculating
theoreticalpriceofagivengoodwithspecifiedsetofsignificantcharacteristics.
Thispropertyofhedonicmodels(i.e.,thepossibilitytoestimatethepriceandto
controlthequalityatthesametime)iscrucialfortheirapplicationinproviding
“true”pricechangeandadjustingpriceindicesinofficialstatistics.
Otherapplicationfieldsincludeestablishingthemarketvaluesofcommodities
(especiallyrealestates),aswellasestimatinghedonicpricesofgoods
characteristics.Thelatterisespeciallybeneficialincasesofattributesprices
whicharenotdirectlyobservableonthemarket(forexamplethebrand4).Yet
anotherimportantapplicationofhedonicmodelswasproposedbyJ.Dziechciarz
;2004b]whosuggestedjoinedapplicationofhedonictechniquesandconjoint
measurementanalysisfortheevaluationofconsumerpreferences.Theresults
obtainedinsuchawaymightbeusedintheprocessofconsumersclassification
(marketsegmentation),designingtheproductforvarioussegments,aswellasthe
formulationofpricingstrategyadequateforeachofthemarketsegments.This
ideawaslaterexploredandfurtherextendedintoothermultivariatestatistical
techniquessuchasmultidimensionalscaling,clustering,andlinearordination
[Dziechciarz-Duda,Król2014a,b,2017b;Dziechciarzetal.2018].
1.3.Researchmotivation
Themethodologicalandempiricalresearchinthefieldsofhedonicpriceindices
andqualityadjustmentsarenumerous.5However,considerabledeficiencies
stillexistespeciallyintheareasofapplicabilityconditionsanalysesand
investigationofproblemsinhedonicpriceindicesconstruction(see,e.g.,[von
4
5
Theapplicationofhedonicmodelsandothermultivariatestatisticalanalysismethods
suchasmultidimensionalscaling,classificationandlinearordinationforthevaluationof
brandsisdescribedin[Dziechciarz-Duda,Król2017a].
Theinterestedreadermayfindexhaustiveliteraturereviewin[Aizcorbe2014].