Connectivity measures have been widely used by researchers and practitioners in the air transport industry to evaluate the degree of transport provision at different levels of detail. This paper adds to the literature by presenting a comprehensive study of the predictive performance of connectivity indices in estimating aggregate itinerary market shares. Our empirical analysis encompasses both nonstop and connecting itineraries that originated or destined in Europe during 2018. The predictive accuracies of the respective measures are assessed against actual market shares and an ad-hoc benchmark derived from a logit-based calibrated index and evaluated in terms of their prediction-error distributions. Our results suggest that the use of connectivity indices can significantly improve the assessment of itinerary market shares relative to conventional size-based measures (up to 16.9% gain in accuracy over itinerary frequency). These improvements, along with their use of standard formulations and lack of a calibration requirement, make connectivity models a valuable tool for practitioners to use in allocating aggregate air travel flows. An examination of different scenarios—short-/medium (SH/MH)-vs. long-haul (LH) and sizeable vs. thin markets—reveals that determination of the best index is not a straightforward task and provides guidance to selecting the best connectivity measure.

(2021). Connectivity measures and passengers’ behavior: Comparing conventional connectivity models to predict itinerary market shares [journal article - articolo]. In JOURNAL OF AIR TRANSPORT MANAGEMENT. Retrieved from http://hdl.handle.net/10446/168794

Connectivity measures and passengers’ behavior: Comparing conventional connectivity models to predict itinerary market shares

Redondi, Renato;Birolini, Sebastian;Morlotti, Chiara;Paleari, Stefano
2021

Abstract

Connectivity measures have been widely used by researchers and practitioners in the air transport industry to evaluate the degree of transport provision at different levels of detail. This paper adds to the literature by presenting a comprehensive study of the predictive performance of connectivity indices in estimating aggregate itinerary market shares. Our empirical analysis encompasses both nonstop and connecting itineraries that originated or destined in Europe during 2018. The predictive accuracies of the respective measures are assessed against actual market shares and an ad-hoc benchmark derived from a logit-based calibrated index and evaluated in terms of their prediction-error distributions. Our results suggest that the use of connectivity indices can significantly improve the assessment of itinerary market shares relative to conventional size-based measures (up to 16.9% gain in accuracy over itinerary frequency). These improvements, along with their use of standard formulations and lack of a calibration requirement, make connectivity models a valuable tool for practitioners to use in allocating aggregate air travel flows. An examination of different scenarios—short-/medium (SH/MH)-vs. long-haul (LH) and sizeable vs. thin markets—reveals that determination of the best index is not a straightforward task and provides guidance to selecting the best connectivity measure.
articolo
Redondi, Renato; Birolini, Sebastian; Morlotti, Chiara; Paleari, Stefano
(2021). Connectivity measures and passengers’ behavior: Comparing conventional connectivity models to predict itinerary market shares [journal article - articolo]. In JOURNAL OF AIR TRANSPORT MANAGEMENT. Retrieved from http://hdl.handle.net/10446/168794
File allegato/i alla scheda:
File Dimensione del file Formato  
1-s2.0-S096969972030541X-main.pdf

Solo gestori di archivio

Versione: publisher's version - versione editoriale
Licenza: Licenza default Aisberg
Dimensione del file 983.4 kB
Formato Adobe PDF
983.4 kB Adobe PDF   Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10446/168794
Citazioni
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 4
social impact