Field data analyses with additional after-warranty failure data

This paper proposes methods of estimating the lifetime distribution for sit uations where additional field data can be gathered after the warranty expi res in a parametric time to failure distribution. For satisfactory inferenc e about parameters involved, it is desirable to incorporate these after-war ranty data in the analysis. It is assumed that after-warranty data are repo rted with probability p(1)(<1), while within-warranty data are reported wit h probability 1. Methods of obtaining maximum likelihood estimators are out lined, their asymptotic properties are studied, and specific formulas for W eibull distribution are obtained. An estimation procedure using the expecta tion and maximization algorithm is also proposed when the reporting probabi lity is unknown. Simulation studies are performed to investigate the proper ties of the estimates. (C) 2001 Elsevier Science Ltd. All rights reserved.