3 parameter Weibull fit in .NET

Question

I'm helping work on an application written in C#.NET. Part of what it does is collect failure data for mechanical tests, and I've been asked to create Weibull distributions automatically based on that data. I've found several helpful libraries that use 2 parameter Weibull distributions, but the data I'm working with includes test that didn't fail, which (as far as I know) necessitates a 3 parameter distribution.

Does anyone know of any good resources out there for working with 3 parameter Weibull distributions that could be integrated into a .NET application?

Answer 1

You don't necessarily need a 3-parameter Weibull. Your non-failing data is called right-censored and requires survival analysis. A straightforward maximum likelihood approach should work here using just a 2-parameter Weibull model.