Concerns in ID'ing a Suitable Distribution
Analysis of product lifetime data generally requires fitting a suitable distribution to the data at hand. The fitted distribution is used to estimate quantities of interest, such as the fraction of product failing after various times in service and selected distribution percentiles (for example, the estimated time by which 1% of the product population is expected to fail).
This article is published as Doganaksoy, N., Hahn, G.J., and Meeker, W.Q., (2020), Concerns in ID'ing a Suitable Distribution, Quality Progress, 53, December, 72–75. Posted with permission.