Advertisement

Case Study 1: Analysis of Air Conditioner Claims Data

  • Wallace R. Blischke
  • M. Rezaul Karim
  • D. N. Prabhakar Murthy
Chapter
Part of the Springer Series in Reliability Engineering book series (RELIABILITY)

Abstract

The first 18 months of warranty claims data on twenty components of a room air conditioner unit covered under a free-replacement warranty are analyzed. Analyses include preliminary data cleaning and outlier detection, data summary and description, histograms, and Pareto charts to identify most frequently failing components and failure modes, and to select data sets for further analysis. Detailed analyses applied to the selected data include analysis of variance, goodness-of-fit tests for model selection, and nonparametric methods. Time to failure at the component and product level are modeled and the results and used to estimate product reliability, predict future costs and compare alternative warranty policies.

Keywords

Failure Mode Claim Data Warranty Period Pareto Chart Compete Risk Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Blischke WR, Murthy DNP (1994) Warranty cost analysis. Marcel Dekker, New YorkGoogle Scholar
  2. 2.
    Blischke WR, Murthy DNP (eds) (1996) Product warranty handbook. Marcel Dekker, New YorkGoogle Scholar
  3. 3.
    Kalbfleisch JD, Lawless JF (1996) Statistical analysis of warranty claims data. In: Blischke WR, Murthy DNP (eds) Product warranty handbook, Chap 9. Marcel Dekker, New YorkGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • Wallace R. Blischke
    • 1
  • M. Rezaul Karim
    • 2
  • D. N. Prabhakar Murthy
    • 3
  1. 1.Sherman Oaks, Los AngelesUSA
  2. 2.Department of StatisticsRajshahi UniversityRajshahiBangladesh
  3. 3.School of Mechanical and Mining EngineeringThe University of QueenslandBrisbaneAustralia

Personalised recommendations