Evaluating Neural Spatial Interaction Modelling by Bootstrapping
Manfred Fischer and
MPRA Paper from University Library of Munich, Germany
This paper exposes problems of the commonly used technique of splitting the available data in neural spatial interaction modelling into training, validation, and test sets that are held fixed and warns about drawing too strong conclusions from such static splits. Using a bootstrapping procedure, we compare the uncertainty in the solution stemming from the data splitting with model specific uncertainties such as parameter initialization. Utilizing the Austrian interregional telecommunication traffic data and the differential evolution method for solving the parameter estimation task for a fixed topology of the network model [ i.e. J = 9] this paper illustrates that the variation due to different resamplings is significantly larger than the variation due to different parameter initializations. This result implies that it is important to not over-interpret a model, estimated on one specific static split of the data.
Keywords: Neural spatial interaction modelling; model evaluation; bootstrapping; interregional telecommunications (search for similar items in EconPapers)
JEL-codes: C21 C45 (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2) Track citations by RSS feed
Published in Networks and Spatial Economics 3.2(2002): pp. 255-268
Downloads: (external link)
https://mpra.ub.uni-muenchen.de/77790/1/MPRA_paper_77790.pdf original version (application/pdf)
Working Paper: EVALUATING NEURAL SPATIAL INTERACTION. MODELLING BY BOOTSTRAPPING (2000)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:pra:mprapa:77790
Access Statistics for this paper
More papers in MPRA Paper from University Library of Munich, Germany Ludwigstraße 33, D-80539 Munich, Germany. Contact information at EDIRC.
Bibliographic data for series maintained by Joachim Winter ().