Analysis of extended warranties for medical equipment: a Stackelberg game model using priority queues
Author
dc.contributor.author
Das Chagas Moura, Márcio
Author
dc.contributor.author
Mateus Santana, Mateus Santana
Author
dc.contributor.author
López Droguett, Enrique
Author
dc.contributor.author
Didier Lins, Isis
Author
dc.contributor.author
Nunes Guedes, Bruno
Admission date
dc.date.accessioned
2018-06-11T17:49:45Z
Available date
dc.date.available
2018-06-11T17:49:45Z
Publication date
dc.date.issued
2017
Cita de ítem
dc.identifier.citation
Reliability Engineering and System Safety 168 (2017): 338–354
es_ES
Identifier
dc.identifier.other
http://dx.doi.org/10.1016/j.ress.2017.05.040
Identifier
dc.identifier.uri
https://repositorio.uchile.cl/handle/2250/148776
Abstract
dc.description.abstract
Healthcare institutions make use of technology-intensive equipment that follows tight quality standards. These companies aim at ensuring service continuity and safety of patients. In this context, maintenance services are generally performed exclusively by the Original Equipment Manufacturer (OEM) because it detains the required expertise, tools and spare parts. Then, we here propose a model to analyze the interaction among hospitals and OEM. We consider the OEM can provide maintenance services for two different classes of hospitals, which have the option of either hiring an Extended Warranty (EW) or paying for each maintenance intervention on demand with or without priority. Class 1 customers are often large hospitals, whereas institutions of class 2 are generally small/medium ones, which have shorter budgets, and thus would choose a non-priority option. To that end, we adopt a Stackelberg game, where the OEM is the leader and the customer is the follower. Failures and repairs follow a 2-class G/M/1 priority queuing system. The OEM maximizes its expected profit by setting the EW and repair intervention prices, and selecting the optimal number of customers in each class. An application example is used to demonstrate the proposed model; a sensitivity analysis is also performed.