Modelling Pipe Failures in Water Distribution Systems: Accounting for Harmful Repairs and a Time-dependent Covariate.

Vincent Couallier (1) , Génia Babykina

1 IMB - Institut de Mathématiques de Bordeaux

The paper deals with the statistical analysis of repeated failures in Water Distribution Systems, affected by a time-dependent covariate. Several systems observed over a given time period are considered. A model formulated in the counting process framework is employed. This model accounts for aging of systems, harmful repairs and covariates. Practical issues in maximum likelihood parameter estimations in the presence of a calendar time-dependent covariate are discussed. The proposed methodology is applied to a real dataset. It is shown that the integration of a calendar time-dependent covariate to the model improves the quality of estimates.

Mots clés: counting process; stochastic intensity; likelihood inference; recurrent events; harmful repair; time-dependent covariate

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

Vincent Couallier, Génia Babykina. Modelling Pipe Failures in Water Distribution Systems: Accounting for Harmful Repairs and a Time-dependent Covariate.. International Journal of Performability Engineering, 2014, 10 (1), pp. 41-52. ⟨hal-00967881⟩