Warranty Analysis: Introduction and Recent Advances
Reader in Operations Research
School of Mathematics, Statistics and Operations Research, Victoria University of Wellington, New Zealand
This talk starts with an introduction in warranty analysis and outlines the taxonomy of the mathematical models in warranty. We continue with an illustration of data mining approach in warranty. We deal with a type of truncation that occurs with typical automotive warranties. Warranty overage and the resulting claims data are limited by mileage as well as age. Age is known for all sold vehicles all the time, but mileage is only observed for a vehicle with a claim and only at the time of the claim. Here we concentrate on univariate solutions taking either age, mileage or calendar time as the usage measure. We take a nonparametric approach, so the methods are extensions of the usual calculations for the mean cumulative number of claims or cost of claims and its standard error. Under linear and piecewise linear models for the vehicles trajectories, we illustrate our approach with real data on several cases based on whether the usage measure is age, miles or calendar time and whether the results are adjusted for withdrawals from warranty coverage.