If I have 210 widgets with an E(lifespan) of 1 week, and uniform age distribution [0,7] days, with instant replacement, is it reasonable to assume 210/7=30 widgets will need to be replaced daily? What other assumptions are lurking here? Does the shape of lifespan distro matter?
Conversation
This Tweet was deleted by the Tweet author. Learn more
yeah, I want to avoid modeling the stochastic process at the fine-grained level and just do a deterministic substitute... it is a longer time horizon model where week to week doesn't matter much
Replying to
The other assumptions are what you need to worry about when you remove the "instant replacement" and have to deal with lead time constraints. Then you need to calculate a safety stock level based on the mean & variance of lead time and your tolerance for stock-out events

